cutelemonlili commited on
Commit
492bec0
·
verified ·
1 Parent(s): d3e3883

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-1B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: lean_training_data_15k
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # lean_training_data_15k
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the lean_training_data_15k dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1689
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 8
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 2
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.1394 | 1.9763 | 500 | 0.1689 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.49.0
62
+ - Pytorch 2.6.0+cu124
63
+ - Datasets 3.2.0
64
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.16889452934265137,
4
+ "eval_runtime": 3.0655,
5
+ "eval_samples_per_second": 6.85,
6
+ "eval_steps_per_second": 1.957,
7
+ "total_flos": 6736634707968.0,
8
+ "train_loss": 0.1787011340083812,
9
+ "train_runtime": 1032.8943,
10
+ "train_samples_per_second": 3.913,
11
+ "train_steps_per_second": 0.49
12
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.49.0",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.16889452934265137,
4
+ "eval_runtime": 3.0655,
5
+ "eval_samples_per_second": 6.85,
6
+ "eval_steps_per_second": 1.957
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.49.0"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e778d75b2cfbc164bf7fd85445a2f2eaaaaca206bc0600527ff4394f2106e4
3
+ size 2471645608
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|eot_id|>"
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "extra_special_tokens": {},
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 4096,
2066
+ "pad_token": "<|eot_id|>",
2067
+ "padding_side": "right",
2068
+ "split_special_tokens": false,
2069
+ "tokenizer_class": "PreTrainedTokenizer"
2070
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 6736634707968.0,
4
+ "train_loss": 0.1787011340083812,
5
+ "train_runtime": 1032.8943,
6
+ "train_samples_per_second": 3.913,
7
+ "train_steps_per_second": 0.49
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,508 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 506, "loss": 1.0657, "lr": 9.999903631006022e-06, "epoch": 0.003952569169960474, "percentage": 0.2, "elapsed_time": "0:00:03", "remaining_time": "0:29:06"}
2
+ {"current_steps": 2, "total_steps": 506, "loss": 0.8817, "lr": 9.999614527738882e-06, "epoch": 0.007905138339920948, "percentage": 0.4, "elapsed_time": "0:00:06", "remaining_time": "0:25:48"}
3
+ {"current_steps": 3, "total_steps": 506, "loss": 0.6038, "lr": 9.99913270134281e-06, "epoch": 0.011857707509881422, "percentage": 0.59, "elapsed_time": "0:00:08", "remaining_time": "0:22:42"}
4
+ {"current_steps": 4, "total_steps": 506, "loss": 0.5555, "lr": 9.998458170391065e-06, "epoch": 0.015810276679841896, "percentage": 0.79, "elapsed_time": "0:00:10", "remaining_time": "0:21:07"}
5
+ {"current_steps": 5, "total_steps": 506, "loss": 0.4486, "lr": 9.99759096088519e-06, "epoch": 0.019762845849802372, "percentage": 0.99, "elapsed_time": "0:00:12", "remaining_time": "0:20:10"}
6
+ {"current_steps": 6, "total_steps": 506, "loss": 0.4616, "lr": 9.996531106254027e-06, "epoch": 0.023715415019762844, "percentage": 1.19, "elapsed_time": "0:00:14", "remaining_time": "0:19:34"}
7
+ {"current_steps": 7, "total_steps": 506, "loss": 0.4705, "lr": 9.995278647352428e-06, "epoch": 0.02766798418972332, "percentage": 1.38, "elapsed_time": "0:00:16", "remaining_time": "0:19:08"}
8
+ {"current_steps": 8, "total_steps": 506, "loss": 0.4065, "lr": 9.993833632459675e-06, "epoch": 0.03162055335968379, "percentage": 1.58, "elapsed_time": "0:00:18", "remaining_time": "0:18:47"}
9
+ {"current_steps": 9, "total_steps": 506, "loss": 0.3791, "lr": 9.99219611727762e-06, "epoch": 0.03557312252964427, "percentage": 1.78, "elapsed_time": "0:00:20", "remaining_time": "0:18:33"}
10
+ {"current_steps": 10, "total_steps": 506, "loss": 0.3968, "lr": 9.990366164928538e-06, "epoch": 0.039525691699604744, "percentage": 1.98, "elapsed_time": "0:00:22", "remaining_time": "0:18:19"}
11
+ {"current_steps": 11, "total_steps": 506, "loss": 0.3593, "lr": 9.988343845952697e-06, "epoch": 0.043478260869565216, "percentage": 2.17, "elapsed_time": "0:00:24", "remaining_time": "0:18:07"}
12
+ {"current_steps": 12, "total_steps": 506, "loss": 0.3241, "lr": 9.986129238305635e-06, "epoch": 0.04743083003952569, "percentage": 2.37, "elapsed_time": "0:00:26", "remaining_time": "0:17:57"}
13
+ {"current_steps": 13, "total_steps": 506, "loss": 0.3514, "lr": 9.983722427355157e-06, "epoch": 0.05138339920948617, "percentage": 2.57, "elapsed_time": "0:00:28", "remaining_time": "0:17:48"}
14
+ {"current_steps": 14, "total_steps": 506, "loss": 0.3307, "lr": 9.98112350587804e-06, "epoch": 0.05533596837944664, "percentage": 2.77, "elapsed_time": "0:00:30", "remaining_time": "0:17:40"}
15
+ {"current_steps": 15, "total_steps": 506, "loss": 0.3382, "lr": 9.978332574056468e-06, "epoch": 0.05928853754940711, "percentage": 2.96, "elapsed_time": "0:00:32", "remaining_time": "0:17:33"}
16
+ {"current_steps": 16, "total_steps": 506, "loss": 0.3025, "lr": 9.975349739474156e-06, "epoch": 0.06324110671936758, "percentage": 3.16, "elapsed_time": "0:00:34", "remaining_time": "0:17:27"}
17
+ {"current_steps": 17, "total_steps": 506, "loss": 0.3291, "lr": 9.972175117112208e-06, "epoch": 0.06719367588932806, "percentage": 3.36, "elapsed_time": "0:00:36", "remaining_time": "0:17:21"}
18
+ {"current_steps": 18, "total_steps": 506, "loss": 0.318, "lr": 9.968808829344692e-06, "epoch": 0.07114624505928854, "percentage": 3.56, "elapsed_time": "0:00:38", "remaining_time": "0:17:15"}
19
+ {"current_steps": 19, "total_steps": 506, "loss": 0.3029, "lr": 9.965251005933915e-06, "epoch": 0.07509881422924901, "percentage": 3.75, "elapsed_time": "0:00:40", "remaining_time": "0:17:10"}
20
+ {"current_steps": 20, "total_steps": 506, "loss": 0.3075, "lr": 9.961501784025423e-06, "epoch": 0.07905138339920949, "percentage": 3.95, "elapsed_time": "0:00:42", "remaining_time": "0:17:05"}
21
+ {"current_steps": 21, "total_steps": 506, "loss": 0.2733, "lr": 9.95756130814271e-06, "epoch": 0.08300395256916997, "percentage": 4.15, "elapsed_time": "0:00:44", "remaining_time": "0:17:01"}
22
+ {"current_steps": 22, "total_steps": 506, "loss": 0.3319, "lr": 9.953429730181653e-06, "epoch": 0.08695652173913043, "percentage": 4.35, "elapsed_time": "0:00:46", "remaining_time": "0:16:57"}
23
+ {"current_steps": 23, "total_steps": 506, "loss": 0.2998, "lr": 9.949107209404664e-06, "epoch": 0.09090909090909091, "percentage": 4.55, "elapsed_time": "0:00:48", "remaining_time": "0:16:53"}
24
+ {"current_steps": 24, "total_steps": 506, "loss": 0.2856, "lr": 9.94459391243453e-06, "epoch": 0.09486166007905138, "percentage": 4.74, "elapsed_time": "0:00:50", "remaining_time": "0:16:49"}
25
+ {"current_steps": 25, "total_steps": 506, "loss": 0.3287, "lr": 9.939890013248006e-06, "epoch": 0.09881422924901186, "percentage": 4.94, "elapsed_time": "0:00:52", "remaining_time": "0:16:46"}
26
+ {"current_steps": 26, "total_steps": 506, "loss": 0.2726, "lr": 9.934995693169104e-06, "epoch": 0.10276679841897234, "percentage": 5.14, "elapsed_time": "0:00:54", "remaining_time": "0:16:42"}
27
+ {"current_steps": 27, "total_steps": 506, "loss": 0.3412, "lr": 9.929911140862109e-06, "epoch": 0.1067193675889328, "percentage": 5.34, "elapsed_time": "0:00:56", "remaining_time": "0:16:38"}
28
+ {"current_steps": 28, "total_steps": 506, "loss": 0.2484, "lr": 9.924636552324296e-06, "epoch": 0.11067193675889328, "percentage": 5.53, "elapsed_time": "0:00:58", "remaining_time": "0:16:35"}
29
+ {"current_steps": 29, "total_steps": 506, "loss": 0.3265, "lr": 9.919172130878378e-06, "epoch": 0.11462450592885376, "percentage": 5.73, "elapsed_time": "0:01:00", "remaining_time": "0:16:32"}
30
+ {"current_steps": 30, "total_steps": 506, "loss": 0.285, "lr": 9.913518087164678e-06, "epoch": 0.11857707509881422, "percentage": 5.93, "elapsed_time": "0:01:02", "remaining_time": "0:16:29"}
31
+ {"current_steps": 31, "total_steps": 506, "loss": 0.2548, "lr": 9.907674639132995e-06, "epoch": 0.1225296442687747, "percentage": 6.13, "elapsed_time": "0:01:04", "remaining_time": "0:16:26"}
32
+ {"current_steps": 32, "total_steps": 506, "loss": 0.2508, "lr": 9.901642012034214e-06, "epoch": 0.12648221343873517, "percentage": 6.32, "elapsed_time": "0:01:06", "remaining_time": "0:16:23"}
33
+ {"current_steps": 33, "total_steps": 506, "loss": 0.2976, "lr": 9.895420438411616e-06, "epoch": 0.13043478260869565, "percentage": 6.52, "elapsed_time": "0:01:08", "remaining_time": "0:16:20"}
34
+ {"current_steps": 34, "total_steps": 506, "loss": 0.2572, "lr": 9.889010158091917e-06, "epoch": 0.13438735177865613, "percentage": 6.72, "elapsed_time": "0:01:10", "remaining_time": "0:16:17"}
35
+ {"current_steps": 35, "total_steps": 506, "loss": 0.2706, "lr": 9.882411418176023e-06, "epoch": 0.1383399209486166, "percentage": 6.92, "elapsed_time": "0:01:12", "remaining_time": "0:16:15"}
36
+ {"current_steps": 36, "total_steps": 506, "loss": 0.2545, "lr": 9.875624473029508e-06, "epoch": 0.1422924901185771, "percentage": 7.11, "elapsed_time": "0:01:14", "remaining_time": "0:16:12"}
37
+ {"current_steps": 37, "total_steps": 506, "loss": 0.2625, "lr": 9.8686495842728e-06, "epoch": 0.14624505928853754, "percentage": 7.31, "elapsed_time": "0:01:16", "remaining_time": "0:16:09"}
38
+ {"current_steps": 38, "total_steps": 506, "loss": 0.2591, "lr": 9.861487020771103e-06, "epoch": 0.15019762845849802, "percentage": 7.51, "elapsed_time": "0:01:18", "remaining_time": "0:16:06"}
39
+ {"current_steps": 39, "total_steps": 506, "loss": 0.2309, "lr": 9.854137058624034e-06, "epoch": 0.1541501976284585, "percentage": 7.71, "elapsed_time": "0:01:20", "remaining_time": "0:16:04"}
40
+ {"current_steps": 40, "total_steps": 506, "loss": 0.2326, "lr": 9.846599981154975e-06, "epoch": 0.15810276679841898, "percentage": 7.91, "elapsed_time": "0:01:22", "remaining_time": "0:16:01"}
41
+ {"current_steps": 41, "total_steps": 506, "loss": 0.2397, "lr": 9.838876078900158e-06, "epoch": 0.16205533596837945, "percentage": 8.1, "elapsed_time": "0:01:24", "remaining_time": "0:15:58"}
42
+ {"current_steps": 42, "total_steps": 506, "loss": 0.252, "lr": 9.830965649597455e-06, "epoch": 0.16600790513833993, "percentage": 8.3, "elapsed_time": "0:01:26", "remaining_time": "0:15:56"}
43
+ {"current_steps": 43, "total_steps": 506, "loss": 0.2448, "lr": 9.822868998174914e-06, "epoch": 0.16996047430830039, "percentage": 8.5, "elapsed_time": "0:01:28", "remaining_time": "0:15:53"}
44
+ {"current_steps": 44, "total_steps": 506, "loss": 0.2371, "lr": 9.814586436738998e-06, "epoch": 0.17391304347826086, "percentage": 8.7, "elapsed_time": "0:01:30", "remaining_time": "0:15:51"}
45
+ {"current_steps": 45, "total_steps": 506, "loss": 0.2907, "lr": 9.806118284562547e-06, "epoch": 0.17786561264822134, "percentage": 8.89, "elapsed_time": "0:01:32", "remaining_time": "0:15:48"}
46
+ {"current_steps": 46, "total_steps": 506, "loss": 0.2683, "lr": 9.797464868072489e-06, "epoch": 0.18181818181818182, "percentage": 9.09, "elapsed_time": "0:01:34", "remaining_time": "0:15:46"}
47
+ {"current_steps": 47, "total_steps": 506, "loss": 0.2473, "lr": 9.788626520837235e-06, "epoch": 0.1857707509881423, "percentage": 9.29, "elapsed_time": "0:01:36", "remaining_time": "0:15:43"}
48
+ {"current_steps": 48, "total_steps": 506, "loss": 0.2341, "lr": 9.779603583553842e-06, "epoch": 0.18972332015810275, "percentage": 9.49, "elapsed_time": "0:01:38", "remaining_time": "0:15:41"}
49
+ {"current_steps": 49, "total_steps": 506, "loss": 0.2675, "lr": 9.770396404034863e-06, "epoch": 0.19367588932806323, "percentage": 9.68, "elapsed_time": "0:01:40", "remaining_time": "0:15:38"}
50
+ {"current_steps": 50, "total_steps": 506, "loss": 0.2685, "lr": 9.76100533719495e-06, "epoch": 0.1976284584980237, "percentage": 9.88, "elapsed_time": "0:01:42", "remaining_time": "0:15:36"}
51
+ {"current_steps": 51, "total_steps": 506, "loss": 0.2311, "lr": 9.75143074503717e-06, "epoch": 0.2015810276679842, "percentage": 10.08, "elapsed_time": "0:01:44", "remaining_time": "0:15:33"}
52
+ {"current_steps": 52, "total_steps": 506, "loss": 0.2627, "lr": 9.741672996639046e-06, "epoch": 0.20553359683794467, "percentage": 10.28, "elapsed_time": "0:01:46", "remaining_time": "0:15:31"}
53
+ {"current_steps": 53, "total_steps": 506, "loss": 0.2512, "lr": 9.731732468138338e-06, "epoch": 0.20948616600790515, "percentage": 10.47, "elapsed_time": "0:01:48", "remaining_time": "0:15:29"}
54
+ {"current_steps": 54, "total_steps": 506, "loss": 0.248, "lr": 9.72160954271854e-06, "epoch": 0.2134387351778656, "percentage": 10.67, "elapsed_time": "0:01:50", "remaining_time": "0:15:26"}
55
+ {"current_steps": 55, "total_steps": 506, "loss": 0.2548, "lr": 9.711304610594104e-06, "epoch": 0.21739130434782608, "percentage": 10.87, "elapsed_time": "0:01:52", "remaining_time": "0:15:24"}
56
+ {"current_steps": 56, "total_steps": 506, "loss": 0.2115, "lr": 9.700818068995407e-06, "epoch": 0.22134387351778656, "percentage": 11.07, "elapsed_time": "0:01:54", "remaining_time": "0:15:22"}
57
+ {"current_steps": 57, "total_steps": 506, "loss": 0.2372, "lr": 9.69015032215344e-06, "epoch": 0.22529644268774704, "percentage": 11.26, "elapsed_time": "0:01:56", "remaining_time": "0:15:19"}
58
+ {"current_steps": 58, "total_steps": 506, "loss": 0.2586, "lr": 9.679301781284209e-06, "epoch": 0.22924901185770752, "percentage": 11.46, "elapsed_time": "0:01:58", "remaining_time": "0:15:18"}
59
+ {"current_steps": 59, "total_steps": 506, "loss": 0.2122, "lr": 9.668272864572904e-06, "epoch": 0.233201581027668, "percentage": 11.66, "elapsed_time": "0:02:00", "remaining_time": "0:15:15"}
60
+ {"current_steps": 60, "total_steps": 506, "loss": 0.2294, "lr": 9.65706399715777e-06, "epoch": 0.23715415019762845, "percentage": 11.86, "elapsed_time": "0:02:02", "remaining_time": "0:15:13"}
61
+ {"current_steps": 61, "total_steps": 506, "loss": 0.2234, "lr": 9.645675611113715e-06, "epoch": 0.24110671936758893, "percentage": 12.06, "elapsed_time": "0:02:04", "remaining_time": "0:15:11"}
62
+ {"current_steps": 62, "total_steps": 506, "loss": 0.2111, "lr": 9.634108145435665e-06, "epoch": 0.2450592885375494, "percentage": 12.25, "elapsed_time": "0:02:06", "remaining_time": "0:15:08"}
63
+ {"current_steps": 63, "total_steps": 506, "loss": 0.2423, "lr": 9.62236204602163e-06, "epoch": 0.2490118577075099, "percentage": 12.45, "elapsed_time": "0:02:08", "remaining_time": "0:15:06"}
64
+ {"current_steps": 64, "total_steps": 506, "loss": 0.2169, "lr": 9.610437765655522e-06, "epoch": 0.25296442687747034, "percentage": 12.65, "elapsed_time": "0:02:10", "remaining_time": "0:15:04"}
65
+ {"current_steps": 65, "total_steps": 506, "loss": 0.2387, "lr": 9.598335763989703e-06, "epoch": 0.25691699604743085, "percentage": 12.85, "elapsed_time": "0:02:12", "remaining_time": "0:15:02"}
66
+ {"current_steps": 66, "total_steps": 506, "loss": 0.2002, "lr": 9.586056507527266e-06, "epoch": 0.2608695652173913, "percentage": 13.04, "elapsed_time": "0:02:14", "remaining_time": "0:14:59"}
67
+ {"current_steps": 67, "total_steps": 506, "loss": 0.2345, "lr": 9.573600469604044e-06, "epoch": 0.2648221343873518, "percentage": 13.24, "elapsed_time": "0:02:16", "remaining_time": "0:14:57"}
68
+ {"current_steps": 68, "total_steps": 506, "loss": 0.257, "lr": 9.560968130370376e-06, "epoch": 0.26877470355731226, "percentage": 13.44, "elapsed_time": "0:02:19", "remaining_time": "0:14:55"}
69
+ {"current_steps": 69, "total_steps": 506, "loss": 0.2272, "lr": 9.548159976772593e-06, "epoch": 0.2727272727272727, "percentage": 13.64, "elapsed_time": "0:02:21", "remaining_time": "0:14:53"}
70
+ {"current_steps": 70, "total_steps": 506, "loss": 0.2011, "lr": 9.535176502534242e-06, "epoch": 0.2766798418972332, "percentage": 13.83, "elapsed_time": "0:02:23", "remaining_time": "0:14:50"}
71
+ {"current_steps": 71, "total_steps": 506, "loss": 0.2198, "lr": 9.522018208137066e-06, "epoch": 0.28063241106719367, "percentage": 14.03, "elapsed_time": "0:02:25", "remaining_time": "0:14:48"}
72
+ {"current_steps": 72, "total_steps": 506, "loss": 0.2277, "lr": 9.508685600801704e-06, "epoch": 0.2845849802371542, "percentage": 14.23, "elapsed_time": "0:02:27", "remaining_time": "0:14:46"}
73
+ {"current_steps": 73, "total_steps": 506, "loss": 0.2269, "lr": 9.495179194468135e-06, "epoch": 0.2885375494071146, "percentage": 14.43, "elapsed_time": "0:02:29", "remaining_time": "0:14:44"}
74
+ {"current_steps": 74, "total_steps": 506, "loss": 0.2229, "lr": 9.481499509775878e-06, "epoch": 0.2924901185770751, "percentage": 14.62, "elapsed_time": "0:02:31", "remaining_time": "0:14:42"}
75
+ {"current_steps": 75, "total_steps": 506, "loss": 0.2132, "lr": 9.467647074043911e-06, "epoch": 0.2964426877470356, "percentage": 14.82, "elapsed_time": "0:02:33", "remaining_time": "0:14:40"}
76
+ {"current_steps": 76, "total_steps": 506, "loss": 0.2261, "lr": 9.453622421250353e-06, "epoch": 0.30039525691699603, "percentage": 15.02, "elapsed_time": "0:02:35", "remaining_time": "0:14:38"}
77
+ {"current_steps": 77, "total_steps": 506, "loss": 0.2186, "lr": 9.439426092011877e-06, "epoch": 0.30434782608695654, "percentage": 15.22, "elapsed_time": "0:02:37", "remaining_time": "0:14:36"}
78
+ {"current_steps": 78, "total_steps": 506, "loss": 0.2241, "lr": 9.42505863356287e-06, "epoch": 0.308300395256917, "percentage": 15.42, "elapsed_time": "0:02:39", "remaining_time": "0:14:34"}
79
+ {"current_steps": 79, "total_steps": 506, "loss": 0.2195, "lr": 9.410520599734338e-06, "epoch": 0.31225296442687744, "percentage": 15.61, "elapsed_time": "0:02:41", "remaining_time": "0:14:31"}
80
+ {"current_steps": 80, "total_steps": 506, "loss": 0.2105, "lr": 9.395812550932559e-06, "epoch": 0.31620553359683795, "percentage": 15.81, "elapsed_time": "0:02:43", "remaining_time": "0:14:29"}
81
+ {"current_steps": 81, "total_steps": 506, "loss": 0.2112, "lr": 9.38093505411748e-06, "epoch": 0.3201581027667984, "percentage": 16.01, "elapsed_time": "0:02:45", "remaining_time": "0:14:27"}
82
+ {"current_steps": 82, "total_steps": 506, "loss": 0.2041, "lr": 9.365888682780862e-06, "epoch": 0.3241106719367589, "percentage": 16.21, "elapsed_time": "0:02:47", "remaining_time": "0:14:25"}
83
+ {"current_steps": 83, "total_steps": 506, "loss": 0.2133, "lr": 9.35067401692417e-06, "epoch": 0.32806324110671936, "percentage": 16.4, "elapsed_time": "0:02:49", "remaining_time": "0:14:23"}
84
+ {"current_steps": 84, "total_steps": 506, "loss": 0.1937, "lr": 9.335291643036221e-06, "epoch": 0.33201581027667987, "percentage": 16.6, "elapsed_time": "0:02:51", "remaining_time": "0:14:20"}
85
+ {"current_steps": 85, "total_steps": 506, "loss": 0.2127, "lr": 9.319742154070578e-06, "epoch": 0.3359683794466403, "percentage": 16.8, "elapsed_time": "0:02:53", "remaining_time": "0:14:18"}
86
+ {"current_steps": 86, "total_steps": 506, "loss": 0.2498, "lr": 9.30402614942268e-06, "epoch": 0.33992094861660077, "percentage": 17.0, "elapsed_time": "0:02:55", "remaining_time": "0:14:16"}
87
+ {"current_steps": 87, "total_steps": 506, "loss": 0.2582, "lr": 9.288144234906753e-06, "epoch": 0.3438735177865613, "percentage": 17.19, "elapsed_time": "0:02:57", "remaining_time": "0:14:14"}
88
+ {"current_steps": 88, "total_steps": 506, "loss": 0.2094, "lr": 9.272097022732444e-06, "epoch": 0.34782608695652173, "percentage": 17.39, "elapsed_time": "0:02:59", "remaining_time": "0:14:12"}
89
+ {"current_steps": 89, "total_steps": 506, "loss": 0.2333, "lr": 9.255885131481231e-06, "epoch": 0.35177865612648224, "percentage": 17.59, "elapsed_time": "0:03:01", "remaining_time": "0:14:10"}
90
+ {"current_steps": 90, "total_steps": 506, "loss": 0.1893, "lr": 9.239509186082574e-06, "epoch": 0.3557312252964427, "percentage": 17.79, "elapsed_time": "0:03:03", "remaining_time": "0:14:08"}
91
+ {"current_steps": 91, "total_steps": 506, "loss": 0.2124, "lr": 9.222969817789829e-06, "epoch": 0.35968379446640314, "percentage": 17.98, "elapsed_time": "0:03:05", "remaining_time": "0:14:06"}
92
+ {"current_steps": 92, "total_steps": 506, "loss": 0.1973, "lr": 9.206267664155906e-06, "epoch": 0.36363636363636365, "percentage": 18.18, "elapsed_time": "0:03:07", "remaining_time": "0:14:03"}
93
+ {"current_steps": 93, "total_steps": 506, "loss": 0.224, "lr": 9.189403369008704e-06, "epoch": 0.3675889328063241, "percentage": 18.38, "elapsed_time": "0:03:09", "remaining_time": "0:14:01"}
94
+ {"current_steps": 94, "total_steps": 506, "loss": 0.2366, "lr": 9.172377582426286e-06, "epoch": 0.3715415019762846, "percentage": 18.58, "elapsed_time": "0:03:11", "remaining_time": "0:13:59"}
95
+ {"current_steps": 95, "total_steps": 506, "loss": 0.2307, "lr": 9.155190960711822e-06, "epoch": 0.37549407114624506, "percentage": 18.77, "elapsed_time": "0:03:13", "remaining_time": "0:13:57"}
96
+ {"current_steps": 96, "total_steps": 506, "loss": 0.2358, "lr": 9.137844166368289e-06, "epoch": 0.3794466403162055, "percentage": 18.97, "elapsed_time": "0:03:15", "remaining_time": "0:13:55"}
97
+ {"current_steps": 97, "total_steps": 506, "loss": 0.1998, "lr": 9.120337868072933e-06, "epoch": 0.383399209486166, "percentage": 19.17, "elapsed_time": "0:03:17", "remaining_time": "0:13:53"}
98
+ {"current_steps": 98, "total_steps": 506, "loss": 0.1992, "lr": 9.1026727406515e-06, "epoch": 0.38735177865612647, "percentage": 19.37, "elapsed_time": "0:03:19", "remaining_time": "0:13:51"}
99
+ {"current_steps": 99, "total_steps": 506, "loss": 0.2103, "lr": 9.08484946505221e-06, "epoch": 0.391304347826087, "percentage": 19.57, "elapsed_time": "0:03:21", "remaining_time": "0:13:49"}
100
+ {"current_steps": 100, "total_steps": 506, "loss": 0.2431, "lr": 9.066868728319522e-06, "epoch": 0.3952569169960474, "percentage": 19.76, "elapsed_time": "0:03:23", "remaining_time": "0:13:47"}
101
+ {"current_steps": 101, "total_steps": 506, "loss": 0.2112, "lr": 9.048731223567636e-06, "epoch": 0.39920948616600793, "percentage": 19.96, "elapsed_time": "0:03:25", "remaining_time": "0:13:44"}
102
+ {"current_steps": 102, "total_steps": 506, "loss": 0.187, "lr": 9.03043764995379e-06, "epoch": 0.4031620553359684, "percentage": 20.16, "elapsed_time": "0:03:27", "remaining_time": "0:13:42"}
103
+ {"current_steps": 103, "total_steps": 506, "loss": 0.2254, "lr": 9.011988712651295e-06, "epoch": 0.40711462450592883, "percentage": 20.36, "elapsed_time": "0:03:29", "remaining_time": "0:13:40"}
104
+ {"current_steps": 104, "total_steps": 506, "loss": 0.196, "lr": 8.993385122822364e-06, "epoch": 0.41106719367588934, "percentage": 20.55, "elapsed_time": "0:03:31", "remaining_time": "0:13:38"}
105
+ {"current_steps": 105, "total_steps": 506, "loss": 0.1871, "lr": 8.974627597590693e-06, "epoch": 0.4150197628458498, "percentage": 20.75, "elapsed_time": "0:03:33", "remaining_time": "0:13:36"}
106
+ {"current_steps": 106, "total_steps": 506, "loss": 0.2061, "lr": 8.955716860013812e-06, "epoch": 0.4189723320158103, "percentage": 20.95, "elapsed_time": "0:03:35", "remaining_time": "0:13:34"}
107
+ {"current_steps": 107, "total_steps": 506, "loss": 0.2128, "lr": 8.936653639055225e-06, "epoch": 0.42292490118577075, "percentage": 21.15, "elapsed_time": "0:03:37", "remaining_time": "0:13:32"}
108
+ {"current_steps": 108, "total_steps": 506, "loss": 0.2154, "lr": 8.917438669556307e-06, "epoch": 0.4268774703557312, "percentage": 21.34, "elapsed_time": "0:03:39", "remaining_time": "0:13:30"}
109
+ {"current_steps": 109, "total_steps": 506, "loss": 0.2166, "lr": 8.898072692207964e-06, "epoch": 0.4308300395256917, "percentage": 21.54, "elapsed_time": "0:03:41", "remaining_time": "0:13:28"}
110
+ {"current_steps": 110, "total_steps": 506, "loss": 0.222, "lr": 8.8785564535221e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:03:43", "remaining_time": "0:13:25"}
111
+ {"current_steps": 111, "total_steps": 506, "loss": 0.2106, "lr": 8.85889070580283e-06, "epoch": 0.43873517786561267, "percentage": 21.94, "elapsed_time": "0:03:45", "remaining_time": "0:13:23"}
112
+ {"current_steps": 112, "total_steps": 506, "loss": 0.2428, "lr": 8.839076207117485e-06, "epoch": 0.4426877470355731, "percentage": 22.13, "elapsed_time": "0:03:47", "remaining_time": "0:13:21"}
113
+ {"current_steps": 113, "total_steps": 506, "loss": 0.231, "lr": 8.819113721267385e-06, "epoch": 0.44664031620553357, "percentage": 22.33, "elapsed_time": "0:03:49", "remaining_time": "0:13:19"}
114
+ {"current_steps": 114, "total_steps": 506, "loss": 0.1862, "lr": 8.7990040177584e-06, "epoch": 0.4505928853754941, "percentage": 22.53, "elapsed_time": "0:03:51", "remaining_time": "0:13:17"}
115
+ {"current_steps": 115, "total_steps": 506, "loss": 0.2015, "lr": 8.778747871771293e-06, "epoch": 0.45454545454545453, "percentage": 22.73, "elapsed_time": "0:03:53", "remaining_time": "0:13:15"}
116
+ {"current_steps": 116, "total_steps": 506, "loss": 0.2153, "lr": 8.758346064131824e-06, "epoch": 0.45849802371541504, "percentage": 22.92, "elapsed_time": "0:03:55", "remaining_time": "0:13:13"}
117
+ {"current_steps": 117, "total_steps": 506, "loss": 0.2027, "lr": 8.737799381280667e-06, "epoch": 0.4624505928853755, "percentage": 23.12, "elapsed_time": "0:03:57", "remaining_time": "0:13:11"}
118
+ {"current_steps": 118, "total_steps": 506, "loss": 0.2221, "lr": 8.717108615243081e-06, "epoch": 0.466403162055336, "percentage": 23.32, "elapsed_time": "0:03:59", "remaining_time": "0:13:09"}
119
+ {"current_steps": 119, "total_steps": 506, "loss": 0.2255, "lr": 8.696274563598395e-06, "epoch": 0.47035573122529645, "percentage": 23.52, "elapsed_time": "0:04:02", "remaining_time": "0:13:07"}
120
+ {"current_steps": 120, "total_steps": 506, "loss": 0.18, "lr": 8.675298029449241e-06, "epoch": 0.4743083003952569, "percentage": 23.72, "elapsed_time": "0:04:04", "remaining_time": "0:13:04"}
121
+ {"current_steps": 121, "total_steps": 506, "loss": 0.2204, "lr": 8.65417982139062e-06, "epoch": 0.4782608695652174, "percentage": 23.91, "elapsed_time": "0:04:06", "remaining_time": "0:13:02"}
122
+ {"current_steps": 122, "total_steps": 506, "loss": 0.2098, "lr": 8.63292075347872e-06, "epoch": 0.48221343873517786, "percentage": 24.11, "elapsed_time": "0:04:08", "remaining_time": "0:13:00"}
123
+ {"current_steps": 123, "total_steps": 506, "loss": 0.1699, "lr": 8.611521645199532e-06, "epoch": 0.48616600790513836, "percentage": 24.31, "elapsed_time": "0:04:10", "remaining_time": "0:12:58"}
124
+ {"current_steps": 124, "total_steps": 506, "loss": 0.2048, "lr": 8.589983321437271e-06, "epoch": 0.4901185770750988, "percentage": 24.51, "elapsed_time": "0:04:12", "remaining_time": "0:12:56"}
125
+ {"current_steps": 125, "total_steps": 506, "loss": 0.1818, "lr": 8.568306612442579e-06, "epoch": 0.49407114624505927, "percentage": 24.7, "elapsed_time": "0:04:14", "remaining_time": "0:12:54"}
126
+ {"current_steps": 126, "total_steps": 506, "loss": 0.1905, "lr": 8.546492353800504e-06, "epoch": 0.4980237154150198, "percentage": 24.9, "elapsed_time": "0:04:16", "remaining_time": "0:12:52"}
127
+ {"current_steps": 127, "total_steps": 506, "loss": 0.2249, "lr": 8.524541386398318e-06, "epoch": 0.5019762845849802, "percentage": 25.1, "elapsed_time": "0:04:18", "remaining_time": "0:12:50"}
128
+ {"current_steps": 128, "total_steps": 506, "loss": 0.1853, "lr": 8.502454556393071e-06, "epoch": 0.5059288537549407, "percentage": 25.3, "elapsed_time": "0:04:20", "remaining_time": "0:12:48"}
129
+ {"current_steps": 129, "total_steps": 506, "loss": 0.2268, "lr": 8.480232715179004e-06, "epoch": 0.5098814229249012, "percentage": 25.49, "elapsed_time": "0:04:22", "remaining_time": "0:12:45"}
130
+ {"current_steps": 130, "total_steps": 506, "loss": 0.2159, "lr": 8.457876719354708e-06, "epoch": 0.5138339920948617, "percentage": 25.69, "elapsed_time": "0:04:24", "remaining_time": "0:12:43"}
131
+ {"current_steps": 131, "total_steps": 506, "loss": 0.2071, "lr": 8.435387430690114e-06, "epoch": 0.5177865612648221, "percentage": 25.89, "elapsed_time": "0:04:26", "remaining_time": "0:12:41"}
132
+ {"current_steps": 132, "total_steps": 506, "loss": 0.1978, "lr": 8.412765716093273e-06, "epoch": 0.5217391304347826, "percentage": 26.09, "elapsed_time": "0:04:28", "remaining_time": "0:12:39"}
133
+ {"current_steps": 133, "total_steps": 506, "loss": 0.1681, "lr": 8.390012447576931e-06, "epoch": 0.525691699604743, "percentage": 26.28, "elapsed_time": "0:04:30", "remaining_time": "0:12:37"}
134
+ {"current_steps": 134, "total_steps": 506, "loss": 0.1799, "lr": 8.367128502224931e-06, "epoch": 0.5296442687747036, "percentage": 26.48, "elapsed_time": "0:04:32", "remaining_time": "0:12:35"}
135
+ {"current_steps": 135, "total_steps": 506, "loss": 0.1945, "lr": 8.344114762158391e-06, "epoch": 0.5335968379446641, "percentage": 26.68, "elapsed_time": "0:04:34", "remaining_time": "0:12:33"}
136
+ {"current_steps": 136, "total_steps": 506, "loss": 0.1994, "lr": 8.320972114501698e-06, "epoch": 0.5375494071146245, "percentage": 26.88, "elapsed_time": "0:04:36", "remaining_time": "0:12:31"}
137
+ {"current_steps": 137, "total_steps": 506, "loss": 0.1982, "lr": 8.297701451348324e-06, "epoch": 0.541501976284585, "percentage": 27.08, "elapsed_time": "0:04:38", "remaining_time": "0:12:29"}
138
+ {"current_steps": 138, "total_steps": 506, "loss": 0.1961, "lr": 8.274303669726427e-06, "epoch": 0.5454545454545454, "percentage": 27.27, "elapsed_time": "0:04:40", "remaining_time": "0:12:27"}
139
+ {"current_steps": 139, "total_steps": 506, "loss": 0.205, "lr": 8.250779671564277e-06, "epoch": 0.549407114624506, "percentage": 27.47, "elapsed_time": "0:04:42", "remaining_time": "0:12:25"}
140
+ {"current_steps": 140, "total_steps": 506, "loss": 0.2056, "lr": 8.22713036365549e-06, "epoch": 0.5533596837944664, "percentage": 27.67, "elapsed_time": "0:04:44", "remaining_time": "0:12:23"}
141
+ {"current_steps": 141, "total_steps": 506, "loss": 0.2152, "lr": 8.20335665762407e-06, "epoch": 0.5573122529644269, "percentage": 27.87, "elapsed_time": "0:04:46", "remaining_time": "0:12:21"}
142
+ {"current_steps": 142, "total_steps": 506, "loss": 0.2154, "lr": 8.179459469889269e-06, "epoch": 0.5612648221343873, "percentage": 28.06, "elapsed_time": "0:04:48", "remaining_time": "0:12:19"}
143
+ {"current_steps": 143, "total_steps": 506, "loss": 0.2175, "lr": 8.155439721630265e-06, "epoch": 0.5652173913043478, "percentage": 28.26, "elapsed_time": "0:04:50", "remaining_time": "0:12:17"}
144
+ {"current_steps": 144, "total_steps": 506, "loss": 0.1892, "lr": 8.131298338750648e-06, "epoch": 0.5691699604743083, "percentage": 28.46, "elapsed_time": "0:04:52", "remaining_time": "0:12:14"}
145
+ {"current_steps": 145, "total_steps": 506, "loss": 0.1972, "lr": 8.10703625184273e-06, "epoch": 0.5731225296442688, "percentage": 28.66, "elapsed_time": "0:04:54", "remaining_time": "0:12:12"}
146
+ {"current_steps": 146, "total_steps": 506, "loss": 0.2156, "lr": 8.082654396151676e-06, "epoch": 0.5770750988142292, "percentage": 28.85, "elapsed_time": "0:04:56", "remaining_time": "0:12:10"}
147
+ {"current_steps": 147, "total_steps": 506, "loss": 0.2089, "lr": 8.058153711539444e-06, "epoch": 0.5810276679841897, "percentage": 29.05, "elapsed_time": "0:04:58", "remaining_time": "0:12:08"}
148
+ {"current_steps": 148, "total_steps": 506, "loss": 0.1809, "lr": 8.03353514244857e-06, "epoch": 0.5849802371541502, "percentage": 29.25, "elapsed_time": "0:05:00", "remaining_time": "0:12:06"}
149
+ {"current_steps": 149, "total_steps": 506, "loss": 0.2023, "lr": 8.008799637865741e-06, "epoch": 0.5889328063241107, "percentage": 29.45, "elapsed_time": "0:05:02", "remaining_time": "0:12:04"}
150
+ {"current_steps": 150, "total_steps": 506, "loss": 0.1796, "lr": 7.983948151285242e-06, "epoch": 0.5928853754940712, "percentage": 29.64, "elapsed_time": "0:05:04", "remaining_time": "0:12:02"}
151
+ {"current_steps": 151, "total_steps": 506, "loss": 0.1977, "lr": 7.958981640672173e-06, "epoch": 0.5968379446640316, "percentage": 29.84, "elapsed_time": "0:05:06", "remaining_time": "0:12:00"}
152
+ {"current_steps": 152, "total_steps": 506, "loss": 0.1731, "lr": 7.933901068425539e-06, "epoch": 0.6007905138339921, "percentage": 30.04, "elapsed_time": "0:05:08", "remaining_time": "0:11:58"}
153
+ {"current_steps": 153, "total_steps": 506, "loss": 0.2216, "lr": 7.908707401341146e-06, "epoch": 0.6047430830039525, "percentage": 30.24, "elapsed_time": "0:05:10", "remaining_time": "0:11:56"}
154
+ {"current_steps": 154, "total_steps": 506, "loss": 0.1908, "lr": 7.883401610574338e-06, "epoch": 0.6086956521739131, "percentage": 30.43, "elapsed_time": "0:05:12", "remaining_time": "0:11:54"}
155
+ {"current_steps": 155, "total_steps": 506, "loss": 0.2008, "lr": 7.857984671602547e-06, "epoch": 0.6126482213438735, "percentage": 30.63, "elapsed_time": "0:05:14", "remaining_time": "0:11:52"}
156
+ {"current_steps": 156, "total_steps": 506, "loss": 0.1706, "lr": 7.832457564187715e-06, "epoch": 0.616600790513834, "percentage": 30.83, "elapsed_time": "0:05:16", "remaining_time": "0:11:50"}
157
+ {"current_steps": 157, "total_steps": 506, "loss": 0.2054, "lr": 7.806821272338504e-06, "epoch": 0.6205533596837944, "percentage": 31.03, "elapsed_time": "0:05:18", "remaining_time": "0:11:48"}
158
+ {"current_steps": 158, "total_steps": 506, "loss": 0.1911, "lr": 7.781076784272377e-06, "epoch": 0.6245059288537549, "percentage": 31.23, "elapsed_time": "0:05:20", "remaining_time": "0:11:46"}
159
+ {"current_steps": 159, "total_steps": 506, "loss": 0.2123, "lr": 7.755225092377498e-06, "epoch": 0.6284584980237155, "percentage": 31.42, "elapsed_time": "0:05:22", "remaining_time": "0:11:44"}
160
+ {"current_steps": 160, "total_steps": 506, "loss": 0.2166, "lr": 7.729267193174483e-06, "epoch": 0.6324110671936759, "percentage": 31.62, "elapsed_time": "0:05:24", "remaining_time": "0:11:41"}
161
+ {"current_steps": 161, "total_steps": 506, "loss": 0.1919, "lr": 7.703204087277989e-06, "epoch": 0.6363636363636364, "percentage": 31.82, "elapsed_time": "0:05:26", "remaining_time": "0:11:40"}
162
+ {"current_steps": 162, "total_steps": 506, "loss": 0.2178, "lr": 7.67703677935813e-06, "epoch": 0.6403162055335968, "percentage": 32.02, "elapsed_time": "0:05:28", "remaining_time": "0:11:37"}
163
+ {"current_steps": 163, "total_steps": 506, "loss": 0.197, "lr": 7.650766278101762e-06, "epoch": 0.6442687747035574, "percentage": 32.21, "elapsed_time": "0:05:30", "remaining_time": "0:11:35"}
164
+ {"current_steps": 164, "total_steps": 506, "loss": 0.2381, "lr": 7.624393596173598e-06, "epoch": 0.6482213438735178, "percentage": 32.41, "elapsed_time": "0:05:32", "remaining_time": "0:11:33"}
165
+ {"current_steps": 165, "total_steps": 506, "loss": 0.1808, "lr": 7.597919750177168e-06, "epoch": 0.6521739130434783, "percentage": 32.61, "elapsed_time": "0:05:34", "remaining_time": "0:11:31"}
166
+ {"current_steps": 166, "total_steps": 506, "loss": 0.219, "lr": 7.5713457606156335e-06, "epoch": 0.6561264822134387, "percentage": 32.81, "elapsed_time": "0:05:36", "remaining_time": "0:11:29"}
167
+ {"current_steps": 167, "total_steps": 506, "loss": 0.2049, "lr": 7.5446726518524505e-06, "epoch": 0.6600790513833992, "percentage": 33.0, "elapsed_time": "0:05:38", "remaining_time": "0:11:27"}
168
+ {"current_steps": 168, "total_steps": 506, "loss": 0.2103, "lr": 7.51790145207188e-06, "epoch": 0.6640316205533597, "percentage": 33.2, "elapsed_time": "0:05:40", "remaining_time": "0:11:25"}
169
+ {"current_steps": 169, "total_steps": 506, "loss": 0.199, "lr": 7.4910331932393634e-06, "epoch": 0.6679841897233202, "percentage": 33.4, "elapsed_time": "0:05:42", "remaining_time": "0:11:23"}
170
+ {"current_steps": 170, "total_steps": 506, "loss": 0.2096, "lr": 7.464068911061726e-06, "epoch": 0.6719367588932806, "percentage": 33.6, "elapsed_time": "0:05:44", "remaining_time": "0:11:21"}
171
+ {"current_steps": 171, "total_steps": 506, "loss": 0.1987, "lr": 7.437009644947268e-06, "epoch": 0.6758893280632411, "percentage": 33.79, "elapsed_time": "0:05:46", "remaining_time": "0:11:19"}
172
+ {"current_steps": 172, "total_steps": 506, "loss": 0.2198, "lr": 7.40985643796569e-06, "epoch": 0.6798418972332015, "percentage": 33.99, "elapsed_time": "0:05:48", "remaining_time": "0:11:17"}
173
+ {"current_steps": 173, "total_steps": 506, "loss": 0.1735, "lr": 7.382610336807887e-06, "epoch": 0.6837944664031621, "percentage": 34.19, "elapsed_time": "0:05:50", "remaining_time": "0:11:15"}
174
+ {"current_steps": 174, "total_steps": 506, "loss": 0.201, "lr": 7.355272391745605e-06, "epoch": 0.6877470355731226, "percentage": 34.39, "elapsed_time": "0:05:52", "remaining_time": "0:11:13"}
175
+ {"current_steps": 175, "total_steps": 506, "loss": 0.1997, "lr": 7.327843656590948e-06, "epoch": 0.691699604743083, "percentage": 34.58, "elapsed_time": "0:05:54", "remaining_time": "0:11:11"}
176
+ {"current_steps": 176, "total_steps": 506, "loss": 0.175, "lr": 7.300325188655762e-06, "epoch": 0.6956521739130435, "percentage": 34.78, "elapsed_time": "0:05:56", "remaining_time": "0:11:09"}
177
+ {"current_steps": 177, "total_steps": 506, "loss": 0.2316, "lr": 7.2727180487108725e-06, "epoch": 0.6996047430830039, "percentage": 34.98, "elapsed_time": "0:05:58", "remaining_time": "0:11:07"}
178
+ {"current_steps": 178, "total_steps": 506, "loss": 0.2086, "lr": 7.245023300945203e-06, "epoch": 0.7035573122529645, "percentage": 35.18, "elapsed_time": "0:06:00", "remaining_time": "0:11:05"}
179
+ {"current_steps": 179, "total_steps": 506, "loss": 0.1614, "lr": 7.217242012924747e-06, "epoch": 0.7075098814229249, "percentage": 35.38, "elapsed_time": "0:06:02", "remaining_time": "0:11:03"}
180
+ {"current_steps": 180, "total_steps": 506, "loss": 0.2129, "lr": 7.189375255551413e-06, "epoch": 0.7114624505928854, "percentage": 35.57, "elapsed_time": "0:06:04", "remaining_time": "0:11:00"}
181
+ {"current_steps": 181, "total_steps": 506, "loss": 0.186, "lr": 7.161424103021752e-06, "epoch": 0.7154150197628458, "percentage": 35.77, "elapsed_time": "0:06:06", "remaining_time": "0:10:58"}
182
+ {"current_steps": 182, "total_steps": 506, "loss": 0.18, "lr": 7.133389632785543e-06, "epoch": 0.7193675889328063, "percentage": 35.97, "elapsed_time": "0:06:08", "remaining_time": "0:10:56"}
183
+ {"current_steps": 183, "total_steps": 506, "loss": 0.1738, "lr": 7.1052729255042645e-06, "epoch": 0.7233201581027668, "percentage": 36.17, "elapsed_time": "0:06:10", "remaining_time": "0:10:54"}
184
+ {"current_steps": 184, "total_steps": 506, "loss": 0.1888, "lr": 7.0770750650094335e-06, "epoch": 0.7272727272727273, "percentage": 36.36, "elapsed_time": "0:06:12", "remaining_time": "0:10:52"}
185
+ {"current_steps": 185, "total_steps": 506, "loss": 0.1938, "lr": 7.048797138260829e-06, "epoch": 0.7312252964426877, "percentage": 36.56, "elapsed_time": "0:06:15", "remaining_time": "0:10:50"}
186
+ {"current_steps": 186, "total_steps": 506, "loss": 0.1541, "lr": 7.020440235304593e-06, "epoch": 0.7351778656126482, "percentage": 36.76, "elapsed_time": "0:06:17", "remaining_time": "0:10:48"}
187
+ {"current_steps": 187, "total_steps": 506, "loss": 0.1863, "lr": 6.9920054492312086e-06, "epoch": 0.7391304347826086, "percentage": 36.96, "elapsed_time": "0:06:19", "remaining_time": "0:10:46"}
188
+ {"current_steps": 188, "total_steps": 506, "loss": 0.1991, "lr": 6.963493876133367e-06, "epoch": 0.7430830039525692, "percentage": 37.15, "elapsed_time": "0:06:21", "remaining_time": "0:10:44"}
189
+ {"current_steps": 189, "total_steps": 506, "loss": 0.2202, "lr": 6.934906615063716e-06, "epoch": 0.7470355731225297, "percentage": 37.35, "elapsed_time": "0:06:23", "remaining_time": "0:10:42"}
190
+ {"current_steps": 190, "total_steps": 506, "loss": 0.1755, "lr": 6.90624476799249e-06, "epoch": 0.7509881422924901, "percentage": 37.55, "elapsed_time": "0:06:25", "remaining_time": "0:10:40"}
191
+ {"current_steps": 191, "total_steps": 506, "loss": 0.1669, "lr": 6.8775094397650375e-06, "epoch": 0.7549407114624506, "percentage": 37.75, "elapsed_time": "0:06:27", "remaining_time": "0:10:38"}
192
+ {"current_steps": 192, "total_steps": 506, "loss": 0.1962, "lr": 6.8487017380592266e-06, "epoch": 0.758893280632411, "percentage": 37.94, "elapsed_time": "0:06:29", "remaining_time": "0:10:36"}
193
+ {"current_steps": 193, "total_steps": 506, "loss": 0.1864, "lr": 6.81982277334275e-06, "epoch": 0.7628458498023716, "percentage": 38.14, "elapsed_time": "0:06:31", "remaining_time": "0:10:34"}
194
+ {"current_steps": 194, "total_steps": 506, "loss": 0.1972, "lr": 6.790873658830321e-06, "epoch": 0.766798418972332, "percentage": 38.34, "elapsed_time": "0:06:33", "remaining_time": "0:10:32"}
195
+ {"current_steps": 195, "total_steps": 506, "loss": 0.1817, "lr": 6.761855510440752e-06, "epoch": 0.7707509881422925, "percentage": 38.54, "elapsed_time": "0:06:35", "remaining_time": "0:10:30"}
196
+ {"current_steps": 196, "total_steps": 506, "loss": 0.175, "lr": 6.732769446753954e-06, "epoch": 0.7747035573122529, "percentage": 38.74, "elapsed_time": "0:06:37", "remaining_time": "0:10:28"}
197
+ {"current_steps": 197, "total_steps": 506, "loss": 0.2146, "lr": 6.703616588967804e-06, "epoch": 0.7786561264822134, "percentage": 38.93, "elapsed_time": "0:06:39", "remaining_time": "0:10:26"}
198
+ {"current_steps": 198, "total_steps": 506, "loss": 0.2065, "lr": 6.674398060854931e-06, "epoch": 0.782608695652174, "percentage": 39.13, "elapsed_time": "0:06:41", "remaining_time": "0:10:24"}
199
+ {"current_steps": 199, "total_steps": 506, "loss": 0.218, "lr": 6.645114988719401e-06, "epoch": 0.7865612648221344, "percentage": 39.33, "elapsed_time": "0:06:43", "remaining_time": "0:10:22"}
200
+ {"current_steps": 200, "total_steps": 506, "loss": 0.1911, "lr": 6.615768501353297e-06, "epoch": 0.7905138339920948, "percentage": 39.53, "elapsed_time": "0:06:45", "remaining_time": "0:10:19"}
201
+ {"current_steps": 201, "total_steps": 506, "loss": 0.2033, "lr": 6.5863597299932e-06, "epoch": 0.7944664031620553, "percentage": 39.72, "elapsed_time": "0:06:47", "remaining_time": "0:10:17"}
202
+ {"current_steps": 202, "total_steps": 506, "loss": 0.1885, "lr": 6.5568898082765945e-06, "epoch": 0.7984189723320159, "percentage": 39.92, "elapsed_time": "0:06:49", "remaining_time": "0:10:15"}
203
+ {"current_steps": 203, "total_steps": 506, "loss": 0.2087, "lr": 6.527359872198166e-06, "epoch": 0.8023715415019763, "percentage": 40.12, "elapsed_time": "0:06:51", "remaining_time": "0:10:13"}
204
+ {"current_steps": 204, "total_steps": 506, "loss": 0.1673, "lr": 6.497771060066008e-06, "epoch": 0.8063241106719368, "percentage": 40.32, "elapsed_time": "0:06:53", "remaining_time": "0:10:11"}
205
+ {"current_steps": 205, "total_steps": 506, "loss": 0.2173, "lr": 6.468124512457743e-06, "epoch": 0.8102766798418972, "percentage": 40.51, "elapsed_time": "0:06:55", "remaining_time": "0:10:09"}
206
+ {"current_steps": 206, "total_steps": 506, "loss": 0.1821, "lr": 6.4384213721765565e-06, "epoch": 0.8142292490118577, "percentage": 40.71, "elapsed_time": "0:06:57", "remaining_time": "0:10:07"}
207
+ {"current_steps": 207, "total_steps": 506, "loss": 0.1809, "lr": 6.408662784207149e-06, "epoch": 0.8181818181818182, "percentage": 40.91, "elapsed_time": "0:06:59", "remaining_time": "0:10:05"}
208
+ {"current_steps": 208, "total_steps": 506, "loss": 0.1807, "lr": 6.378849895671594e-06, "epoch": 0.8221343873517787, "percentage": 41.11, "elapsed_time": "0:07:01", "remaining_time": "0:10:03"}
209
+ {"current_steps": 209, "total_steps": 506, "loss": 0.193, "lr": 6.348983855785122e-06, "epoch": 0.8260869565217391, "percentage": 41.3, "elapsed_time": "0:07:03", "remaining_time": "0:10:01"}
210
+ {"current_steps": 210, "total_steps": 506, "loss": 0.1736, "lr": 6.3190658158118205e-06, "epoch": 0.8300395256916996, "percentage": 41.5, "elapsed_time": "0:07:05", "remaining_time": "0:09:59"}
211
+ {"current_steps": 211, "total_steps": 506, "loss": 0.1737, "lr": 6.289096929020254e-06, "epoch": 0.83399209486166, "percentage": 41.7, "elapsed_time": "0:07:07", "remaining_time": "0:09:57"}
212
+ {"current_steps": 212, "total_steps": 506, "loss": 0.185, "lr": 6.25907835063901e-06, "epoch": 0.8379446640316206, "percentage": 41.9, "elapsed_time": "0:07:09", "remaining_time": "0:09:55"}
213
+ {"current_steps": 213, "total_steps": 506, "loss": 0.2183, "lr": 6.229011237812172e-06, "epoch": 0.841897233201581, "percentage": 42.09, "elapsed_time": "0:07:11", "remaining_time": "0:09:53"}
214
+ {"current_steps": 214, "total_steps": 506, "loss": 0.1705, "lr": 6.1988967495547016e-06, "epoch": 0.8458498023715415, "percentage": 42.29, "elapsed_time": "0:07:13", "remaining_time": "0:09:51"}
215
+ {"current_steps": 215, "total_steps": 506, "loss": 0.2087, "lr": 6.168736046707777e-06, "epoch": 0.849802371541502, "percentage": 42.49, "elapsed_time": "0:07:15", "remaining_time": "0:09:49"}
216
+ {"current_steps": 216, "total_steps": 506, "loss": 0.1599, "lr": 6.138530291894033e-06, "epoch": 0.8537549407114624, "percentage": 42.69, "elapsed_time": "0:07:17", "remaining_time": "0:09:47"}
217
+ {"current_steps": 217, "total_steps": 506, "loss": 0.1977, "lr": 6.108280649472751e-06, "epoch": 0.857707509881423, "percentage": 42.89, "elapsed_time": "0:07:19", "remaining_time": "0:09:45"}
218
+ {"current_steps": 218, "total_steps": 506, "loss": 0.1916, "lr": 6.0779882854949745e-06, "epoch": 0.8616600790513834, "percentage": 43.08, "elapsed_time": "0:07:21", "remaining_time": "0:09:43"}
219
+ {"current_steps": 219, "total_steps": 506, "loss": 0.1877, "lr": 6.047654367658563e-06, "epoch": 0.8656126482213439, "percentage": 43.28, "elapsed_time": "0:07:23", "remaining_time": "0:09:41"}
220
+ {"current_steps": 220, "total_steps": 506, "loss": 0.1941, "lr": 6.0172800652631706e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:07:25", "remaining_time": "0:09:39"}
221
+ {"current_steps": 221, "total_steps": 506, "loss": 0.1841, "lr": 5.986866549165185e-06, "epoch": 0.8735177865612648, "percentage": 43.68, "elapsed_time": "0:07:27", "remaining_time": "0:09:37"}
222
+ {"current_steps": 222, "total_steps": 506, "loss": 0.1776, "lr": 5.9564149917325845e-06, "epoch": 0.8774703557312253, "percentage": 43.87, "elapsed_time": "0:07:29", "remaining_time": "0:09:35"}
223
+ {"current_steps": 223, "total_steps": 506, "loss": 0.1923, "lr": 5.925926566799754e-06, "epoch": 0.8814229249011858, "percentage": 44.07, "elapsed_time": "0:07:31", "remaining_time": "0:09:33"}
224
+ {"current_steps": 224, "total_steps": 506, "loss": 0.1772, "lr": 5.895402449622226e-06, "epoch": 0.8853754940711462, "percentage": 44.27, "elapsed_time": "0:07:33", "remaining_time": "0:09:30"}
225
+ {"current_steps": 225, "total_steps": 506, "loss": 0.1844, "lr": 5.864843816831388e-06, "epoch": 0.8893280632411067, "percentage": 44.47, "elapsed_time": "0:07:35", "remaining_time": "0:09:28"}
226
+ {"current_steps": 226, "total_steps": 506, "loss": 0.1632, "lr": 5.8342518463891195e-06, "epoch": 0.8932806324110671, "percentage": 44.66, "elapsed_time": "0:07:37", "remaining_time": "0:09:26"}
227
+ {"current_steps": 227, "total_steps": 506, "loss": 0.1961, "lr": 5.803627717542386e-06, "epoch": 0.8972332015810277, "percentage": 44.86, "elapsed_time": "0:07:39", "remaining_time": "0:09:24"}
228
+ {"current_steps": 228, "total_steps": 506, "loss": 0.1884, "lr": 5.7729726107777855e-06, "epoch": 0.9011857707509882, "percentage": 45.06, "elapsed_time": "0:07:41", "remaining_time": "0:09:22"}
229
+ {"current_steps": 229, "total_steps": 506, "loss": 0.1746, "lr": 5.742287707776034e-06, "epoch": 0.9051383399209486, "percentage": 45.26, "elapsed_time": "0:07:43", "remaining_time": "0:09:20"}
230
+ {"current_steps": 230, "total_steps": 506, "loss": 0.1767, "lr": 5.711574191366427e-06, "epoch": 0.9090909090909091, "percentage": 45.45, "elapsed_time": "0:07:45", "remaining_time": "0:09:18"}
231
+ {"current_steps": 231, "total_steps": 506, "loss": 0.1748, "lr": 5.680833245481234e-06, "epoch": 0.9130434782608695, "percentage": 45.65, "elapsed_time": "0:07:47", "remaining_time": "0:09:16"}
232
+ {"current_steps": 232, "total_steps": 506, "loss": 0.1682, "lr": 5.650066055110067e-06, "epoch": 0.9169960474308301, "percentage": 45.85, "elapsed_time": "0:07:49", "remaining_time": "0:09:14"}
233
+ {"current_steps": 233, "total_steps": 506, "loss": 0.1883, "lr": 5.6192738062542e-06, "epoch": 0.9209486166007905, "percentage": 46.05, "elapsed_time": "0:07:51", "remaining_time": "0:09:12"}
234
+ {"current_steps": 234, "total_steps": 506, "loss": 0.1634, "lr": 5.588457685880851e-06, "epoch": 0.924901185770751, "percentage": 46.25, "elapsed_time": "0:07:53", "remaining_time": "0:09:10"}
235
+ {"current_steps": 235, "total_steps": 506, "loss": 0.1745, "lr": 5.557618881877428e-06, "epoch": 0.9288537549407114, "percentage": 46.44, "elapsed_time": "0:07:55", "remaining_time": "0:09:08"}
236
+ {"current_steps": 236, "total_steps": 506, "loss": 0.2153, "lr": 5.526758583005736e-06, "epoch": 0.932806324110672, "percentage": 46.64, "elapsed_time": "0:07:57", "remaining_time": "0:09:06"}
237
+ {"current_steps": 237, "total_steps": 506, "loss": 0.1962, "lr": 5.495877978856159e-06, "epoch": 0.9367588932806324, "percentage": 46.84, "elapsed_time": "0:07:59", "remaining_time": "0:09:04"}
238
+ {"current_steps": 238, "total_steps": 506, "loss": 0.1765, "lr": 5.464978259801797e-06, "epoch": 0.9407114624505929, "percentage": 47.04, "elapsed_time": "0:08:01", "remaining_time": "0:09:02"}
239
+ {"current_steps": 239, "total_steps": 506, "loss": 0.1948, "lr": 5.4340606169525915e-06, "epoch": 0.9446640316205533, "percentage": 47.23, "elapsed_time": "0:08:03", "remaining_time": "0:09:00"}
240
+ {"current_steps": 240, "total_steps": 506, "loss": 0.1958, "lr": 5.40312624210939e-06, "epoch": 0.9486166007905138, "percentage": 47.43, "elapsed_time": "0:08:05", "remaining_time": "0:08:58"}
241
+ {"current_steps": 241, "total_steps": 506, "loss": 0.1772, "lr": 5.372176327718029e-06, "epoch": 0.9525691699604744, "percentage": 47.63, "elapsed_time": "0:08:07", "remaining_time": "0:08:56"}
242
+ {"current_steps": 242, "total_steps": 506, "loss": 0.2068, "lr": 5.341212066823356e-06, "epoch": 0.9565217391304348, "percentage": 47.83, "elapsed_time": "0:08:09", "remaining_time": "0:08:54"}
243
+ {"current_steps": 243, "total_steps": 506, "loss": 0.1983, "lr": 5.3102346530232365e-06, "epoch": 0.9604743083003953, "percentage": 48.02, "elapsed_time": "0:08:11", "remaining_time": "0:08:52"}
244
+ {"current_steps": 244, "total_steps": 506, "loss": 0.203, "lr": 5.2792452804225535e-06, "epoch": 0.9644268774703557, "percentage": 48.22, "elapsed_time": "0:08:13", "remaining_time": "0:08:50"}
245
+ {"current_steps": 245, "total_steps": 506, "loss": 0.1838, "lr": 5.248245143587172e-06, "epoch": 0.9683794466403162, "percentage": 48.42, "elapsed_time": "0:08:15", "remaining_time": "0:08:48"}
246
+ {"current_steps": 246, "total_steps": 506, "loss": 0.1843, "lr": 5.2172354374978905e-06, "epoch": 0.9723320158102767, "percentage": 48.62, "elapsed_time": "0:08:17", "remaining_time": "0:08:46"}
247
+ {"current_steps": 247, "total_steps": 506, "loss": 0.1971, "lr": 5.186217357504382e-06, "epoch": 0.9762845849802372, "percentage": 48.81, "elapsed_time": "0:08:19", "remaining_time": "0:08:44"}
248
+ {"current_steps": 248, "total_steps": 506, "loss": 0.1581, "lr": 5.155192099279113e-06, "epoch": 0.9802371541501976, "percentage": 49.01, "elapsed_time": "0:08:21", "remaining_time": "0:08:42"}
249
+ {"current_steps": 249, "total_steps": 506, "loss": 0.1868, "lr": 5.124160858771252e-06, "epoch": 0.9841897233201581, "percentage": 49.21, "elapsed_time": "0:08:23", "remaining_time": "0:08:40"}
250
+ {"current_steps": 250, "total_steps": 506, "loss": 0.1702, "lr": 5.093124832160569e-06, "epoch": 0.9881422924901185, "percentage": 49.41, "elapsed_time": "0:08:25", "remaining_time": "0:08:38"}
251
+ {"current_steps": 251, "total_steps": 506, "loss": 0.1758, "lr": 5.06208521581133e-06, "epoch": 0.9920948616600791, "percentage": 49.6, "elapsed_time": "0:08:27", "remaining_time": "0:08:36"}
252
+ {"current_steps": 252, "total_steps": 506, "loss": 0.1718, "lr": 5.0310432062261764e-06, "epoch": 0.9960474308300395, "percentage": 49.8, "elapsed_time": "0:08:29", "remaining_time": "0:08:33"}
253
+ {"current_steps": 253, "total_steps": 506, "loss": 0.18, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:08:30", "remaining_time": "0:08:30"}
254
+ {"current_steps": 254, "total_steps": 506, "loss": 0.128, "lr": 4.968956793773825e-06, "epoch": 1.0039525691699605, "percentage": 50.2, "elapsed_time": "0:08:33", "remaining_time": "0:08:29"}
255
+ {"current_steps": 255, "total_steps": 506, "loss": 0.1374, "lr": 4.9379147841886715e-06, "epoch": 1.007905138339921, "percentage": 50.4, "elapsed_time": "0:08:35", "remaining_time": "0:08:27"}
256
+ {"current_steps": 256, "total_steps": 506, "loss": 0.1295, "lr": 4.906875167839433e-06, "epoch": 1.0118577075098814, "percentage": 50.59, "elapsed_time": "0:08:37", "remaining_time": "0:08:25"}
257
+ {"current_steps": 257, "total_steps": 506, "loss": 0.1435, "lr": 4.875839141228751e-06, "epoch": 1.0158102766798418, "percentage": 50.79, "elapsed_time": "0:08:39", "remaining_time": "0:08:23"}
258
+ {"current_steps": 258, "total_steps": 506, "loss": 0.1369, "lr": 4.844807900720888e-06, "epoch": 1.0197628458498025, "percentage": 50.99, "elapsed_time": "0:08:41", "remaining_time": "0:08:20"}
259
+ {"current_steps": 259, "total_steps": 506, "loss": 0.1299, "lr": 4.813782642495618e-06, "epoch": 1.023715415019763, "percentage": 51.19, "elapsed_time": "0:08:43", "remaining_time": "0:08:18"}
260
+ {"current_steps": 260, "total_steps": 506, "loss": 0.1393, "lr": 4.78276456250211e-06, "epoch": 1.0276679841897234, "percentage": 51.38, "elapsed_time": "0:08:45", "remaining_time": "0:08:16"}
261
+ {"current_steps": 261, "total_steps": 506, "loss": 0.1587, "lr": 4.75175485641283e-06, "epoch": 1.0316205533596838, "percentage": 51.58, "elapsed_time": "0:08:47", "remaining_time": "0:08:14"}
262
+ {"current_steps": 262, "total_steps": 506, "loss": 0.1417, "lr": 4.720754719577448e-06, "epoch": 1.0355731225296443, "percentage": 51.78, "elapsed_time": "0:08:49", "remaining_time": "0:08:12"}
263
+ {"current_steps": 263, "total_steps": 506, "loss": 0.1414, "lr": 4.689765346976765e-06, "epoch": 1.0395256916996047, "percentage": 51.98, "elapsed_time": "0:08:51", "remaining_time": "0:08:10"}
264
+ {"current_steps": 264, "total_steps": 506, "loss": 0.1541, "lr": 4.6587879331766465e-06, "epoch": 1.0434782608695652, "percentage": 52.17, "elapsed_time": "0:08:53", "remaining_time": "0:08:08"}
265
+ {"current_steps": 265, "total_steps": 506, "loss": 0.1566, "lr": 4.627823672281972e-06, "epoch": 1.0474308300395256, "percentage": 52.37, "elapsed_time": "0:08:55", "remaining_time": "0:08:06"}
266
+ {"current_steps": 266, "total_steps": 506, "loss": 0.1381, "lr": 4.596873757890612e-06, "epoch": 1.051383399209486, "percentage": 52.57, "elapsed_time": "0:08:57", "remaining_time": "0:08:04"}
267
+ {"current_steps": 267, "total_steps": 506, "loss": 0.1135, "lr": 4.565939383047411e-06, "epoch": 1.0553359683794465, "percentage": 52.77, "elapsed_time": "0:08:59", "remaining_time": "0:08:02"}
268
+ {"current_steps": 268, "total_steps": 506, "loss": 0.1609, "lr": 4.535021740198202e-06, "epoch": 1.0592885375494072, "percentage": 52.96, "elapsed_time": "0:09:01", "remaining_time": "0:08:00"}
269
+ {"current_steps": 269, "total_steps": 506, "loss": 0.1454, "lr": 4.504122021143842e-06, "epoch": 1.0632411067193677, "percentage": 53.16, "elapsed_time": "0:09:03", "remaining_time": "0:07:58"}
270
+ {"current_steps": 270, "total_steps": 506, "loss": 0.1374, "lr": 4.473241416994265e-06, "epoch": 1.0671936758893281, "percentage": 53.36, "elapsed_time": "0:09:05", "remaining_time": "0:07:56"}
271
+ {"current_steps": 271, "total_steps": 506, "loss": 0.1249, "lr": 4.442381118122573e-06, "epoch": 1.0711462450592886, "percentage": 53.56, "elapsed_time": "0:09:07", "remaining_time": "0:07:54"}
272
+ {"current_steps": 272, "total_steps": 506, "loss": 0.1179, "lr": 4.41154231411915e-06, "epoch": 1.075098814229249, "percentage": 53.75, "elapsed_time": "0:09:09", "remaining_time": "0:07:52"}
273
+ {"current_steps": 273, "total_steps": 506, "loss": 0.1446, "lr": 4.3807261937458005e-06, "epoch": 1.0790513833992095, "percentage": 53.95, "elapsed_time": "0:09:11", "remaining_time": "0:07:50"}
274
+ {"current_steps": 274, "total_steps": 506, "loss": 0.1085, "lr": 4.349933944889934e-06, "epoch": 1.08300395256917, "percentage": 54.15, "elapsed_time": "0:09:13", "remaining_time": "0:07:48"}
275
+ {"current_steps": 275, "total_steps": 506, "loss": 0.1277, "lr": 4.319166754518768e-06, "epoch": 1.0869565217391304, "percentage": 54.35, "elapsed_time": "0:09:15", "remaining_time": "0:07:46"}
276
+ {"current_steps": 276, "total_steps": 506, "loss": 0.1394, "lr": 4.2884258086335755e-06, "epoch": 1.0909090909090908, "percentage": 54.55, "elapsed_time": "0:09:17", "remaining_time": "0:07:44"}
277
+ {"current_steps": 277, "total_steps": 506, "loss": 0.1342, "lr": 4.257712292223967e-06, "epoch": 1.0948616600790513, "percentage": 54.74, "elapsed_time": "0:09:19", "remaining_time": "0:07:42"}
278
+ {"current_steps": 278, "total_steps": 506, "loss": 0.1344, "lr": 4.227027389222215e-06, "epoch": 1.098814229249012, "percentage": 54.94, "elapsed_time": "0:09:21", "remaining_time": "0:07:40"}
279
+ {"current_steps": 279, "total_steps": 506, "loss": 0.1127, "lr": 4.196372282457614e-06, "epoch": 1.1027667984189724, "percentage": 55.14, "elapsed_time": "0:09:23", "remaining_time": "0:07:38"}
280
+ {"current_steps": 280, "total_steps": 506, "loss": 0.1293, "lr": 4.165748153610881e-06, "epoch": 1.1067193675889329, "percentage": 55.34, "elapsed_time": "0:09:25", "remaining_time": "0:07:36"}
281
+ {"current_steps": 281, "total_steps": 506, "loss": 0.1332, "lr": 4.1351561831686136e-06, "epoch": 1.1106719367588933, "percentage": 55.53, "elapsed_time": "0:09:27", "remaining_time": "0:07:34"}
282
+ {"current_steps": 282, "total_steps": 506, "loss": 0.1263, "lr": 4.104597550377776e-06, "epoch": 1.1146245059288538, "percentage": 55.73, "elapsed_time": "0:09:29", "remaining_time": "0:07:32"}
283
+ {"current_steps": 283, "total_steps": 506, "loss": 0.1285, "lr": 4.074073433200249e-06, "epoch": 1.1185770750988142, "percentage": 55.93, "elapsed_time": "0:09:31", "remaining_time": "0:07:30"}
284
+ {"current_steps": 284, "total_steps": 506, "loss": 0.118, "lr": 4.043585008267418e-06, "epoch": 1.1225296442687747, "percentage": 56.13, "elapsed_time": "0:09:33", "remaining_time": "0:07:28"}
285
+ {"current_steps": 285, "total_steps": 506, "loss": 0.1532, "lr": 4.013133450834818e-06, "epoch": 1.1264822134387351, "percentage": 56.32, "elapsed_time": "0:09:35", "remaining_time": "0:07:26"}
286
+ {"current_steps": 286, "total_steps": 506, "loss": 0.0988, "lr": 3.982719934736832e-06, "epoch": 1.1304347826086956, "percentage": 56.52, "elapsed_time": "0:09:37", "remaining_time": "0:07:24"}
287
+ {"current_steps": 287, "total_steps": 506, "loss": 0.1148, "lr": 3.95234563234144e-06, "epoch": 1.1343873517786562, "percentage": 56.72, "elapsed_time": "0:09:39", "remaining_time": "0:07:22"}
288
+ {"current_steps": 288, "total_steps": 506, "loss": 0.1346, "lr": 3.9220117145050254e-06, "epoch": 1.1383399209486167, "percentage": 56.92, "elapsed_time": "0:09:41", "remaining_time": "0:07:20"}
289
+ {"current_steps": 289, "total_steps": 506, "loss": 0.132, "lr": 3.89171935052725e-06, "epoch": 1.1422924901185771, "percentage": 57.11, "elapsed_time": "0:09:43", "remaining_time": "0:07:18"}
290
+ {"current_steps": 290, "total_steps": 506, "loss": 0.1262, "lr": 3.861469708105969e-06, "epoch": 1.1462450592885376, "percentage": 57.31, "elapsed_time": "0:09:45", "remaining_time": "0:07:16"}
291
+ {"current_steps": 291, "total_steps": 506, "loss": 0.1464, "lr": 3.831263953292225e-06, "epoch": 1.150197628458498, "percentage": 57.51, "elapsed_time": "0:09:47", "remaining_time": "0:07:14"}
292
+ {"current_steps": 292, "total_steps": 506, "loss": 0.1303, "lr": 3.8011032504453e-06, "epoch": 1.1541501976284585, "percentage": 57.71, "elapsed_time": "0:09:49", "remaining_time": "0:07:12"}
293
+ {"current_steps": 293, "total_steps": 506, "loss": 0.1237, "lr": 3.7709887621878305e-06, "epoch": 1.158102766798419, "percentage": 57.91, "elapsed_time": "0:09:51", "remaining_time": "0:07:10"}
294
+ {"current_steps": 294, "total_steps": 506, "loss": 0.1329, "lr": 3.740921649360991e-06, "epoch": 1.1620553359683794, "percentage": 58.1, "elapsed_time": "0:09:53", "remaining_time": "0:07:08"}
295
+ {"current_steps": 295, "total_steps": 506, "loss": 0.146, "lr": 3.710903070979749e-06, "epoch": 1.1660079051383399, "percentage": 58.3, "elapsed_time": "0:09:55", "remaining_time": "0:07:06"}
296
+ {"current_steps": 296, "total_steps": 506, "loss": 0.1369, "lr": 3.680934184188182e-06, "epoch": 1.1699604743083003, "percentage": 58.5, "elapsed_time": "0:09:57", "remaining_time": "0:07:04"}
297
+ {"current_steps": 297, "total_steps": 506, "loss": 0.1224, "lr": 3.6510161442148783e-06, "epoch": 1.1739130434782608, "percentage": 58.7, "elapsed_time": "0:09:59", "remaining_time": "0:07:02"}
298
+ {"current_steps": 298, "total_steps": 506, "loss": 0.1248, "lr": 3.621150104328407e-06, "epoch": 1.1778656126482214, "percentage": 58.89, "elapsed_time": "0:10:01", "remaining_time": "0:07:00"}
299
+ {"current_steps": 299, "total_steps": 506, "loss": 0.1224, "lr": 3.5913372157928515e-06, "epoch": 1.1818181818181819, "percentage": 59.09, "elapsed_time": "0:10:03", "remaining_time": "0:06:58"}
300
+ {"current_steps": 300, "total_steps": 506, "loss": 0.1491, "lr": 3.5615786278234443e-06, "epoch": 1.1857707509881423, "percentage": 59.29, "elapsed_time": "0:10:05", "remaining_time": "0:06:56"}
301
+ {"current_steps": 301, "total_steps": 506, "loss": 0.1347, "lr": 3.5318754875422588e-06, "epoch": 1.1897233201581028, "percentage": 59.49, "elapsed_time": "0:10:07", "remaining_time": "0:06:54"}
302
+ {"current_steps": 302, "total_steps": 506, "loss": 0.1022, "lr": 3.5022289399339933e-06, "epoch": 1.1936758893280632, "percentage": 59.68, "elapsed_time": "0:10:09", "remaining_time": "0:06:52"}
303
+ {"current_steps": 303, "total_steps": 506, "loss": 0.1134, "lr": 3.4726401278018353e-06, "epoch": 1.1976284584980237, "percentage": 59.88, "elapsed_time": "0:10:11", "remaining_time": "0:06:49"}
304
+ {"current_steps": 304, "total_steps": 506, "loss": 0.127, "lr": 3.443110191723407e-06, "epoch": 1.2015810276679841, "percentage": 60.08, "elapsed_time": "0:10:13", "remaining_time": "0:06:47"}
305
+ {"current_steps": 305, "total_steps": 506, "loss": 0.1242, "lr": 3.4136402700068034e-06, "epoch": 1.2055335968379446, "percentage": 60.28, "elapsed_time": "0:10:16", "remaining_time": "0:06:45"}
306
+ {"current_steps": 306, "total_steps": 506, "loss": 0.1302, "lr": 3.384231498646706e-06, "epoch": 1.2094861660079053, "percentage": 60.47, "elapsed_time": "0:10:18", "remaining_time": "0:06:43"}
307
+ {"current_steps": 307, "total_steps": 506, "loss": 0.1345, "lr": 3.3548850112805985e-06, "epoch": 1.2134387351778657, "percentage": 60.67, "elapsed_time": "0:10:20", "remaining_time": "0:06:41"}
308
+ {"current_steps": 308, "total_steps": 506, "loss": 0.124, "lr": 3.3256019391450696e-06, "epoch": 1.2173913043478262, "percentage": 60.87, "elapsed_time": "0:10:22", "remaining_time": "0:06:39"}
309
+ {"current_steps": 309, "total_steps": 506, "loss": 0.1592, "lr": 3.296383411032198e-06, "epoch": 1.2213438735177866, "percentage": 61.07, "elapsed_time": "0:10:24", "remaining_time": "0:06:37"}
310
+ {"current_steps": 310, "total_steps": 506, "loss": 0.1374, "lr": 3.267230553246047e-06, "epoch": 1.225296442687747, "percentage": 61.26, "elapsed_time": "0:10:26", "remaining_time": "0:06:35"}
311
+ {"current_steps": 311, "total_steps": 506, "loss": 0.1599, "lr": 3.2381444895592483e-06, "epoch": 1.2292490118577075, "percentage": 61.46, "elapsed_time": "0:10:28", "remaining_time": "0:06:33"}
312
+ {"current_steps": 312, "total_steps": 506, "loss": 0.1178, "lr": 3.209126341169681e-06, "epoch": 1.233201581027668, "percentage": 61.66, "elapsed_time": "0:10:30", "remaining_time": "0:06:31"}
313
+ {"current_steps": 313, "total_steps": 506, "loss": 0.1324, "lr": 3.180177226657251e-06, "epoch": 1.2371541501976284, "percentage": 61.86, "elapsed_time": "0:10:32", "remaining_time": "0:06:29"}
314
+ {"current_steps": 314, "total_steps": 506, "loss": 0.1354, "lr": 3.151298261940775e-06, "epoch": 1.2411067193675889, "percentage": 62.06, "elapsed_time": "0:10:34", "remaining_time": "0:06:27"}
315
+ {"current_steps": 315, "total_steps": 506, "loss": 0.1316, "lr": 3.122490560234964e-06, "epoch": 1.2450592885375493, "percentage": 62.25, "elapsed_time": "0:10:36", "remaining_time": "0:06:25"}
316
+ {"current_steps": 316, "total_steps": 506, "loss": 0.1237, "lr": 3.0937552320075116e-06, "epoch": 1.2490118577075098, "percentage": 62.45, "elapsed_time": "0:10:38", "remaining_time": "0:06:23"}
317
+ {"current_steps": 317, "total_steps": 506, "loss": 0.1385, "lr": 3.065093384936285e-06, "epoch": 1.2529644268774702, "percentage": 62.65, "elapsed_time": "0:10:40", "remaining_time": "0:06:21"}
318
+ {"current_steps": 318, "total_steps": 506, "loss": 0.1442, "lr": 3.0365061238666336e-06, "epoch": 1.256916996047431, "percentage": 62.85, "elapsed_time": "0:10:42", "remaining_time": "0:06:19"}
319
+ {"current_steps": 319, "total_steps": 506, "loss": 0.136, "lr": 3.007994550768793e-06, "epoch": 1.2608695652173914, "percentage": 63.04, "elapsed_time": "0:10:44", "remaining_time": "0:06:17"}
320
+ {"current_steps": 320, "total_steps": 506, "loss": 0.1447, "lr": 2.979559764695409e-06, "epoch": 1.2648221343873518, "percentage": 63.24, "elapsed_time": "0:10:46", "remaining_time": "0:06:15"}
321
+ {"current_steps": 321, "total_steps": 506, "loss": 0.1282, "lr": 2.951202861739173e-06, "epoch": 1.2687747035573123, "percentage": 63.44, "elapsed_time": "0:10:48", "remaining_time": "0:06:13"}
322
+ {"current_steps": 322, "total_steps": 506, "loss": 0.1212, "lr": 2.9229249349905686e-06, "epoch": 1.2727272727272727, "percentage": 63.64, "elapsed_time": "0:10:50", "remaining_time": "0:06:11"}
323
+ {"current_steps": 323, "total_steps": 506, "loss": 0.1173, "lr": 2.8947270744957385e-06, "epoch": 1.2766798418972332, "percentage": 63.83, "elapsed_time": "0:10:52", "remaining_time": "0:06:09"}
324
+ {"current_steps": 324, "total_steps": 506, "loss": 0.1407, "lr": 2.8666103672144597e-06, "epoch": 1.2806324110671936, "percentage": 64.03, "elapsed_time": "0:10:54", "remaining_time": "0:06:07"}
325
+ {"current_steps": 325, "total_steps": 506, "loss": 0.1286, "lr": 2.8385758969782507e-06, "epoch": 1.2845849802371543, "percentage": 64.23, "elapsed_time": "0:10:56", "remaining_time": "0:06:05"}
326
+ {"current_steps": 326, "total_steps": 506, "loss": 0.128, "lr": 2.810624744448588e-06, "epoch": 1.2885375494071147, "percentage": 64.43, "elapsed_time": "0:10:58", "remaining_time": "0:06:03"}
327
+ {"current_steps": 327, "total_steps": 506, "loss": 0.136, "lr": 2.7827579870752542e-06, "epoch": 1.2924901185770752, "percentage": 64.62, "elapsed_time": "0:11:00", "remaining_time": "0:06:01"}
328
+ {"current_steps": 328, "total_steps": 506, "loss": 0.1238, "lr": 2.7549766990547973e-06, "epoch": 1.2964426877470356, "percentage": 64.82, "elapsed_time": "0:11:02", "remaining_time": "0:05:59"}
329
+ {"current_steps": 329, "total_steps": 506, "loss": 0.1333, "lr": 2.727281951289128e-06, "epoch": 1.300395256916996, "percentage": 65.02, "elapsed_time": "0:11:04", "remaining_time": "0:05:57"}
330
+ {"current_steps": 330, "total_steps": 506, "loss": 0.1223, "lr": 2.6996748113442397e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "0:11:06", "remaining_time": "0:05:55"}
331
+ {"current_steps": 331, "total_steps": 506, "loss": 0.1349, "lr": 2.672156343409053e-06, "epoch": 1.308300395256917, "percentage": 65.42, "elapsed_time": "0:11:08", "remaining_time": "0:05:53"}
332
+ {"current_steps": 332, "total_steps": 506, "loss": 0.1215, "lr": 2.644727608254396e-06, "epoch": 1.3122529644268774, "percentage": 65.61, "elapsed_time": "0:11:10", "remaining_time": "0:05:51"}
333
+ {"current_steps": 333, "total_steps": 506, "loss": 0.1405, "lr": 2.6173896631921134e-06, "epoch": 1.316205533596838, "percentage": 65.81, "elapsed_time": "0:11:12", "remaining_time": "0:05:49"}
334
+ {"current_steps": 334, "total_steps": 506, "loss": 0.1297, "lr": 2.590143562034312e-06, "epoch": 1.3201581027667983, "percentage": 66.01, "elapsed_time": "0:11:14", "remaining_time": "0:05:47"}
335
+ {"current_steps": 335, "total_steps": 506, "loss": 0.1032, "lr": 2.5629903550527343e-06, "epoch": 1.3241106719367588, "percentage": 66.21, "elapsed_time": "0:11:16", "remaining_time": "0:05:45"}
336
+ {"current_steps": 336, "total_steps": 506, "loss": 0.1342, "lr": 2.535931088938274e-06, "epoch": 1.3280632411067192, "percentage": 66.4, "elapsed_time": "0:11:18", "remaining_time": "0:05:43"}
337
+ {"current_steps": 337, "total_steps": 506, "loss": 0.1185, "lr": 2.5089668067606365e-06, "epoch": 1.33201581027668, "percentage": 66.6, "elapsed_time": "0:11:20", "remaining_time": "0:05:41"}
338
+ {"current_steps": 338, "total_steps": 506, "loss": 0.1139, "lr": 2.4820985479281184e-06, "epoch": 1.3359683794466404, "percentage": 66.8, "elapsed_time": "0:11:22", "remaining_time": "0:05:39"}
339
+ {"current_steps": 339, "total_steps": 506, "loss": 0.134, "lr": 2.45532734814755e-06, "epoch": 1.3399209486166008, "percentage": 67.0, "elapsed_time": "0:11:24", "remaining_time": "0:05:37"}
340
+ {"current_steps": 340, "total_steps": 506, "loss": 0.1281, "lr": 2.4286542393843665e-06, "epoch": 1.3438735177865613, "percentage": 67.19, "elapsed_time": "0:11:26", "remaining_time": "0:05:35"}
341
+ {"current_steps": 341, "total_steps": 506, "loss": 0.1432, "lr": 2.4020802498228333e-06, "epoch": 1.3478260869565217, "percentage": 67.39, "elapsed_time": "0:11:28", "remaining_time": "0:05:33"}
342
+ {"current_steps": 342, "total_steps": 506, "loss": 0.134, "lr": 2.3756064038264033e-06, "epoch": 1.3517786561264822, "percentage": 67.59, "elapsed_time": "0:11:30", "remaining_time": "0:05:31"}
343
+ {"current_steps": 343, "total_steps": 506, "loss": 0.1285, "lr": 2.3492337218982396e-06, "epoch": 1.3557312252964426, "percentage": 67.79, "elapsed_time": "0:11:32", "remaining_time": "0:05:29"}
344
+ {"current_steps": 344, "total_steps": 506, "loss": 0.1055, "lr": 2.3229632206418727e-06, "epoch": 1.359683794466403, "percentage": 67.98, "elapsed_time": "0:11:34", "remaining_time": "0:05:27"}
345
+ {"current_steps": 345, "total_steps": 506, "loss": 0.1164, "lr": 2.296795912722014e-06, "epoch": 1.3636363636363638, "percentage": 68.18, "elapsed_time": "0:11:36", "remaining_time": "0:05:25"}
346
+ {"current_steps": 346, "total_steps": 506, "loss": 0.1413, "lr": 2.270732806825517e-06, "epoch": 1.3675889328063242, "percentage": 68.38, "elapsed_time": "0:11:38", "remaining_time": "0:05:23"}
347
+ {"current_steps": 347, "total_steps": 506, "loss": 0.1312, "lr": 2.244774907622504e-06, "epoch": 1.3715415019762847, "percentage": 68.58, "elapsed_time": "0:11:40", "remaining_time": "0:05:21"}
348
+ {"current_steps": 348, "total_steps": 506, "loss": 0.1379, "lr": 2.2189232157276247e-06, "epoch": 1.3754940711462451, "percentage": 68.77, "elapsed_time": "0:11:42", "remaining_time": "0:05:19"}
349
+ {"current_steps": 349, "total_steps": 506, "loss": 0.1178, "lr": 2.1931787276614968e-06, "epoch": 1.3794466403162056, "percentage": 68.97, "elapsed_time": "0:11:44", "remaining_time": "0:05:17"}
350
+ {"current_steps": 350, "total_steps": 506, "loss": 0.1356, "lr": 2.167542435812286e-06, "epoch": 1.383399209486166, "percentage": 69.17, "elapsed_time": "0:11:46", "remaining_time": "0:05:15"}
351
+ {"current_steps": 351, "total_steps": 506, "loss": 0.1237, "lr": 2.142015328397454e-06, "epoch": 1.3873517786561265, "percentage": 69.37, "elapsed_time": "0:11:48", "remaining_time": "0:05:13"}
352
+ {"current_steps": 352, "total_steps": 506, "loss": 0.1255, "lr": 2.1165983894256647e-06, "epoch": 1.391304347826087, "percentage": 69.57, "elapsed_time": "0:11:50", "remaining_time": "0:05:11"}
353
+ {"current_steps": 353, "total_steps": 506, "loss": 0.1389, "lr": 2.0912925986588547e-06, "epoch": 1.3952569169960474, "percentage": 69.76, "elapsed_time": "0:11:52", "remaining_time": "0:05:08"}
354
+ {"current_steps": 354, "total_steps": 506, "loss": 0.1168, "lr": 2.0660989315744624e-06, "epoch": 1.3992094861660078, "percentage": 69.96, "elapsed_time": "0:11:54", "remaining_time": "0:05:06"}
355
+ {"current_steps": 355, "total_steps": 506, "loss": 0.1367, "lr": 2.0410183593278287e-06, "epoch": 1.4031620553359683, "percentage": 70.16, "elapsed_time": "0:11:56", "remaining_time": "0:05:04"}
356
+ {"current_steps": 356, "total_steps": 506, "loss": 0.131, "lr": 2.016051848714758e-06, "epoch": 1.4071146245059287, "percentage": 70.36, "elapsed_time": "0:11:58", "remaining_time": "0:05:02"}
357
+ {"current_steps": 357, "total_steps": 506, "loss": 0.1668, "lr": 1.991200362134258e-06, "epoch": 1.4110671936758894, "percentage": 70.55, "elapsed_time": "0:12:00", "remaining_time": "0:05:00"}
358
+ {"current_steps": 358, "total_steps": 506, "loss": 0.1309, "lr": 1.9664648575514316e-06, "epoch": 1.4150197628458498, "percentage": 70.75, "elapsed_time": "0:12:02", "remaining_time": "0:04:58"}
359
+ {"current_steps": 359, "total_steps": 506, "loss": 0.1407, "lr": 1.9418462884605555e-06, "epoch": 1.4189723320158103, "percentage": 70.95, "elapsed_time": "0:12:04", "remaining_time": "0:04:56"}
360
+ {"current_steps": 360, "total_steps": 506, "loss": 0.0989, "lr": 1.9173456038483244e-06, "epoch": 1.4229249011857708, "percentage": 71.15, "elapsed_time": "0:12:06", "remaining_time": "0:04:54"}
361
+ {"current_steps": 361, "total_steps": 506, "loss": 0.1233, "lr": 1.8929637481572715e-06, "epoch": 1.4268774703557312, "percentage": 71.34, "elapsed_time": "0:12:08", "remaining_time": "0:04:52"}
362
+ {"current_steps": 362, "total_steps": 506, "loss": 0.1266, "lr": 1.8687016612493542e-06, "epoch": 1.4308300395256917, "percentage": 71.54, "elapsed_time": "0:12:11", "remaining_time": "0:04:50"}
363
+ {"current_steps": 363, "total_steps": 506, "loss": 0.1383, "lr": 1.8445602783697375e-06, "epoch": 1.434782608695652, "percentage": 71.74, "elapsed_time": "0:12:13", "remaining_time": "0:04:48"}
364
+ {"current_steps": 364, "total_steps": 506, "loss": 0.1183, "lr": 1.8205405301107343e-06, "epoch": 1.4387351778656128, "percentage": 71.94, "elapsed_time": "0:12:15", "remaining_time": "0:04:46"}
365
+ {"current_steps": 365, "total_steps": 506, "loss": 0.1452, "lr": 1.7966433423759327e-06, "epoch": 1.4426877470355732, "percentage": 72.13, "elapsed_time": "0:12:17", "remaining_time": "0:04:44"}
366
+ {"current_steps": 366, "total_steps": 506, "loss": 0.111, "lr": 1.772869636344512e-06, "epoch": 1.4466403162055337, "percentage": 72.33, "elapsed_time": "0:12:19", "remaining_time": "0:04:42"}
367
+ {"current_steps": 367, "total_steps": 506, "loss": 0.1362, "lr": 1.7492203284357245e-06, "epoch": 1.4505928853754941, "percentage": 72.53, "elapsed_time": "0:12:21", "remaining_time": "0:04:40"}
368
+ {"current_steps": 368, "total_steps": 506, "loss": 0.1202, "lr": 1.7256963302735752e-06, "epoch": 1.4545454545454546, "percentage": 72.73, "elapsed_time": "0:12:23", "remaining_time": "0:04:38"}
369
+ {"current_steps": 369, "total_steps": 506, "loss": 0.1162, "lr": 1.702298548651678e-06, "epoch": 1.458498023715415, "percentage": 72.92, "elapsed_time": "0:12:25", "remaining_time": "0:04:36"}
370
+ {"current_steps": 370, "total_steps": 506, "loss": 0.1322, "lr": 1.6790278854983033e-06, "epoch": 1.4624505928853755, "percentage": 73.12, "elapsed_time": "0:12:27", "remaining_time": "0:04:34"}
371
+ {"current_steps": 371, "total_steps": 506, "loss": 0.1362, "lr": 1.6558852378416113e-06, "epoch": 1.466403162055336, "percentage": 73.32, "elapsed_time": "0:12:29", "remaining_time": "0:04:32"}
372
+ {"current_steps": 372, "total_steps": 506, "loss": 0.1239, "lr": 1.6328714977750698e-06, "epoch": 1.4703557312252964, "percentage": 73.52, "elapsed_time": "0:12:31", "remaining_time": "0:04:30"}
373
+ {"current_steps": 373, "total_steps": 506, "loss": 0.1476, "lr": 1.6099875524230707e-06, "epoch": 1.4743083003952568, "percentage": 73.72, "elapsed_time": "0:12:33", "remaining_time": "0:04:28"}
374
+ {"current_steps": 374, "total_steps": 506, "loss": 0.1381, "lr": 1.5872342839067305e-06, "epoch": 1.4782608695652173, "percentage": 73.91, "elapsed_time": "0:12:35", "remaining_time": "0:04:26"}
375
+ {"current_steps": 375, "total_steps": 506, "loss": 0.1295, "lr": 1.5646125693098863e-06, "epoch": 1.4822134387351777, "percentage": 74.11, "elapsed_time": "0:12:37", "remaining_time": "0:04:24"}
376
+ {"current_steps": 376, "total_steps": 506, "loss": 0.1234, "lr": 1.542123280645292e-06, "epoch": 1.4861660079051384, "percentage": 74.31, "elapsed_time": "0:12:39", "remaining_time": "0:04:22"}
377
+ {"current_steps": 377, "total_steps": 506, "loss": 0.1152, "lr": 1.519767284820996e-06, "epoch": 1.4901185770750989, "percentage": 74.51, "elapsed_time": "0:12:41", "remaining_time": "0:04:20"}
378
+ {"current_steps": 378, "total_steps": 506, "loss": 0.1114, "lr": 1.4975454436069292e-06, "epoch": 1.4940711462450593, "percentage": 74.7, "elapsed_time": "0:12:43", "remaining_time": "0:04:18"}
379
+ {"current_steps": 379, "total_steps": 506, "loss": 0.127, "lr": 1.4754586136016841e-06, "epoch": 1.4980237154150198, "percentage": 74.9, "elapsed_time": "0:12:45", "remaining_time": "0:04:16"}
380
+ {"current_steps": 380, "total_steps": 506, "loss": 0.1243, "lr": 1.4535076461994974e-06, "epoch": 1.5019762845849802, "percentage": 75.1, "elapsed_time": "0:12:47", "remaining_time": "0:04:14"}
381
+ {"current_steps": 381, "total_steps": 506, "loss": 0.1007, "lr": 1.431693387557424e-06, "epoch": 1.5059288537549407, "percentage": 75.3, "elapsed_time": "0:12:49", "remaining_time": "0:04:12"}
382
+ {"current_steps": 382, "total_steps": 506, "loss": 0.1201, "lr": 1.4100166785627301e-06, "epoch": 1.5098814229249014, "percentage": 75.49, "elapsed_time": "0:12:51", "remaining_time": "0:04:10"}
383
+ {"current_steps": 383, "total_steps": 506, "loss": 0.1208, "lr": 1.3884783548004704e-06, "epoch": 1.5138339920948618, "percentage": 75.69, "elapsed_time": "0:12:53", "remaining_time": "0:04:08"}
384
+ {"current_steps": 384, "total_steps": 506, "loss": 0.131, "lr": 1.3670792465212828e-06, "epoch": 1.5177865612648223, "percentage": 75.89, "elapsed_time": "0:12:55", "remaining_time": "0:04:06"}
385
+ {"current_steps": 385, "total_steps": 506, "loss": 0.1426, "lr": 1.3458201786093795e-06, "epoch": 1.5217391304347827, "percentage": 76.09, "elapsed_time": "0:12:57", "remaining_time": "0:04:04"}
386
+ {"current_steps": 386, "total_steps": 506, "loss": 0.107, "lr": 1.3247019705507596e-06, "epoch": 1.5256916996047432, "percentage": 76.28, "elapsed_time": "0:12:59", "remaining_time": "0:04:02"}
387
+ {"current_steps": 387, "total_steps": 506, "loss": 0.1106, "lr": 1.3037254364016068e-06, "epoch": 1.5296442687747036, "percentage": 76.48, "elapsed_time": "0:13:01", "remaining_time": "0:04:00"}
388
+ {"current_steps": 388, "total_steps": 506, "loss": 0.126, "lr": 1.2828913847569185e-06, "epoch": 1.533596837944664, "percentage": 76.68, "elapsed_time": "0:13:03", "remaining_time": "0:03:58"}
389
+ {"current_steps": 389, "total_steps": 506, "loss": 0.1169, "lr": 1.2622006187193348e-06, "epoch": 1.5375494071146245, "percentage": 76.88, "elapsed_time": "0:13:05", "remaining_time": "0:03:56"}
390
+ {"current_steps": 390, "total_steps": 506, "loss": 0.1243, "lr": 1.2416539358681772e-06, "epoch": 1.541501976284585, "percentage": 77.08, "elapsed_time": "0:13:07", "remaining_time": "0:03:54"}
391
+ {"current_steps": 391, "total_steps": 506, "loss": 0.129, "lr": 1.2212521282287093e-06, "epoch": 1.5454545454545454, "percentage": 77.27, "elapsed_time": "0:13:09", "remaining_time": "0:03:52"}
392
+ {"current_steps": 392, "total_steps": 506, "loss": 0.1382, "lr": 1.2009959822416012e-06, "epoch": 1.5494071146245059, "percentage": 77.47, "elapsed_time": "0:13:11", "remaining_time": "0:03:50"}
393
+ {"current_steps": 393, "total_steps": 506, "loss": 0.1217, "lr": 1.1808862787326176e-06, "epoch": 1.5533596837944663, "percentage": 77.67, "elapsed_time": "0:13:13", "remaining_time": "0:03:48"}
394
+ {"current_steps": 394, "total_steps": 506, "loss": 0.1392, "lr": 1.1609237928825174e-06, "epoch": 1.5573122529644268, "percentage": 77.87, "elapsed_time": "0:13:15", "remaining_time": "0:03:46"}
395
+ {"current_steps": 395, "total_steps": 506, "loss": 0.1334, "lr": 1.1411092941971702e-06, "epoch": 1.5612648221343872, "percentage": 78.06, "elapsed_time": "0:13:17", "remaining_time": "0:03:44"}
396
+ {"current_steps": 396, "total_steps": 506, "loss": 0.1092, "lr": 1.1214435464779006e-06, "epoch": 1.5652173913043477, "percentage": 78.26, "elapsed_time": "0:13:19", "remaining_time": "0:03:42"}
397
+ {"current_steps": 397, "total_steps": 506, "loss": 0.1199, "lr": 1.1019273077920366e-06, "epoch": 1.5691699604743083, "percentage": 78.46, "elapsed_time": "0:13:21", "remaining_time": "0:03:40"}
398
+ {"current_steps": 398, "total_steps": 506, "loss": 0.1214, "lr": 1.0825613304436938e-06, "epoch": 1.5731225296442688, "percentage": 78.66, "elapsed_time": "0:13:23", "remaining_time": "0:03:38"}
399
+ {"current_steps": 399, "total_steps": 506, "loss": 0.1137, "lr": 1.0633463609447753e-06, "epoch": 1.5770750988142292, "percentage": 78.85, "elapsed_time": "0:13:25", "remaining_time": "0:03:36"}
400
+ {"current_steps": 400, "total_steps": 506, "loss": 0.1116, "lr": 1.0442831399861903e-06, "epoch": 1.5810276679841897, "percentage": 79.05, "elapsed_time": "0:13:27", "remaining_time": "0:03:33"}
401
+ {"current_steps": 401, "total_steps": 506, "loss": 0.1259, "lr": 1.0253724024093103e-06, "epoch": 1.5849802371541502, "percentage": 79.25, "elapsed_time": "0:13:29", "remaining_time": "0:03:31"}
402
+ {"current_steps": 402, "total_steps": 506, "loss": 0.1398, "lr": 1.006614877177638e-06, "epoch": 1.5889328063241108, "percentage": 79.45, "elapsed_time": "0:13:31", "remaining_time": "0:03:29"}
403
+ {"current_steps": 403, "total_steps": 506, "loss": 0.1435, "lr": 9.880112873487068e-07, "epoch": 1.5928853754940713, "percentage": 79.64, "elapsed_time": "0:13:33", "remaining_time": "0:03:27"}
404
+ {"current_steps": 404, "total_steps": 506, "loss": 0.1213, "lr": 9.695623500462114e-07, "epoch": 1.5968379446640317, "percentage": 79.84, "elapsed_time": "0:13:35", "remaining_time": "0:03:25"}
405
+ {"current_steps": 405, "total_steps": 506, "loss": 0.1309, "lr": 9.512687764323647e-07, "epoch": 1.6007905138339922, "percentage": 80.04, "elapsed_time": "0:13:37", "remaining_time": "0:03:23"}
406
+ {"current_steps": 406, "total_steps": 506, "loss": 0.1353, "lr": 9.331312716804791e-07, "epoch": 1.6047430830039526, "percentage": 80.24, "elapsed_time": "0:13:39", "remaining_time": "0:03:21"}
407
+ {"current_steps": 407, "total_steps": 506, "loss": 0.1126, "lr": 9.151505349477901e-07, "epoch": 1.608695652173913, "percentage": 80.43, "elapsed_time": "0:13:41", "remaining_time": "0:03:19"}
408
+ {"current_steps": 408, "total_steps": 506, "loss": 0.1232, "lr": 8.973272593485011e-07, "epoch": 1.6126482213438735, "percentage": 80.63, "elapsed_time": "0:13:43", "remaining_time": "0:03:17"}
409
+ {"current_steps": 409, "total_steps": 506, "loss": 0.1381, "lr": 8.796621319270676e-07, "epoch": 1.616600790513834, "percentage": 80.83, "elapsed_time": "0:13:45", "remaining_time": "0:03:15"}
410
+ {"current_steps": 410, "total_steps": 506, "loss": 0.125, "lr": 8.621558336317132e-07, "epoch": 1.6205533596837944, "percentage": 81.03, "elapsed_time": "0:13:47", "remaining_time": "0:03:13"}
411
+ {"current_steps": 411, "total_steps": 506, "loss": 0.1434, "lr": 8.448090392881797e-07, "epoch": 1.6245059288537549, "percentage": 81.23, "elapsed_time": "0:13:49", "remaining_time": "0:03:11"}
412
+ {"current_steps": 412, "total_steps": 506, "loss": 0.1341, "lr": 8.276224175737152e-07, "epoch": 1.6284584980237153, "percentage": 81.42, "elapsed_time": "0:13:51", "remaining_time": "0:03:09"}
413
+ {"current_steps": 413, "total_steps": 506, "loss": 0.119, "lr": 8.105966309912966e-07, "epoch": 1.6324110671936758, "percentage": 81.62, "elapsed_time": "0:13:53", "remaining_time": "0:03:07"}
414
+ {"current_steps": 414, "total_steps": 506, "loss": 0.1365, "lr": 7.937323358440935e-07, "epoch": 1.6363636363636362, "percentage": 81.82, "elapsed_time": "0:13:55", "remaining_time": "0:03:05"}
415
+ {"current_steps": 415, "total_steps": 506, "loss": 0.1056, "lr": 7.770301822101712e-07, "epoch": 1.6403162055335967, "percentage": 82.02, "elapsed_time": "0:13:57", "remaining_time": "0:03:03"}
416
+ {"current_steps": 416, "total_steps": 506, "loss": 0.1098, "lr": 7.604908139174255e-07, "epoch": 1.6442687747035574, "percentage": 82.21, "elapsed_time": "0:13:59", "remaining_time": "0:03:01"}
417
+ {"current_steps": 417, "total_steps": 506, "loss": 0.1341, "lr": 7.441148685187694e-07, "epoch": 1.6482213438735178, "percentage": 82.41, "elapsed_time": "0:14:01", "remaining_time": "0:02:59"}
418
+ {"current_steps": 418, "total_steps": 506, "loss": 0.1336, "lr": 7.279029772675572e-07, "epoch": 1.6521739130434783, "percentage": 82.61, "elapsed_time": "0:14:03", "remaining_time": "0:02:57"}
419
+ {"current_steps": 419, "total_steps": 506, "loss": 0.1379, "lr": 7.11855765093249e-07, "epoch": 1.6561264822134387, "percentage": 82.81, "elapsed_time": "0:14:05", "remaining_time": "0:02:55"}
420
+ {"current_steps": 420, "total_steps": 506, "loss": 0.1373, "lr": 6.959738505773211e-07, "epoch": 1.6600790513833992, "percentage": 83.0, "elapsed_time": "0:14:07", "remaining_time": "0:02:53"}
421
+ {"current_steps": 421, "total_steps": 506, "loss": 0.1274, "lr": 6.802578459294235e-07, "epoch": 1.6640316205533598, "percentage": 83.2, "elapsed_time": "0:14:09", "remaining_time": "0:02:51"}
422
+ {"current_steps": 422, "total_steps": 506, "loss": 0.1208, "lr": 6.647083569637797e-07, "epoch": 1.6679841897233203, "percentage": 83.4, "elapsed_time": "0:14:11", "remaining_time": "0:02:49"}
423
+ {"current_steps": 423, "total_steps": 506, "loss": 0.1181, "lr": 6.493259830758325e-07, "epoch": 1.6719367588932808, "percentage": 83.6, "elapsed_time": "0:14:13", "remaining_time": "0:02:47"}
424
+ {"current_steps": 424, "total_steps": 506, "loss": 0.1251, "lr": 6.341113172191399e-07, "epoch": 1.6758893280632412, "percentage": 83.79, "elapsed_time": "0:14:15", "remaining_time": "0:02:45"}
425
+ {"current_steps": 425, "total_steps": 506, "loss": 0.1373, "lr": 6.190649458825204e-07, "epoch": 1.6798418972332017, "percentage": 83.99, "elapsed_time": "0:14:17", "remaining_time": "0:02:43"}
426
+ {"current_steps": 426, "total_steps": 506, "loss": 0.1183, "lr": 6.041874490674416e-07, "epoch": 1.683794466403162, "percentage": 84.19, "elapsed_time": "0:14:19", "remaining_time": "0:02:41"}
427
+ {"current_steps": 427, "total_steps": 506, "loss": 0.1276, "lr": 5.894794002656628e-07, "epoch": 1.6877470355731226, "percentage": 84.39, "elapsed_time": "0:14:22", "remaining_time": "0:02:39"}
428
+ {"current_steps": 428, "total_steps": 506, "loss": 0.1314, "lr": 5.749413664371312e-07, "epoch": 1.691699604743083, "percentage": 84.58, "elapsed_time": "0:14:24", "remaining_time": "0:02:37"}
429
+ {"current_steps": 429, "total_steps": 506, "loss": 0.1172, "lr": 5.60573907988124e-07, "epoch": 1.6956521739130435, "percentage": 84.78, "elapsed_time": "0:14:26", "remaining_time": "0:02:35"}
430
+ {"current_steps": 430, "total_steps": 506, "loss": 0.1345, "lr": 5.463775787496484e-07, "epoch": 1.699604743083004, "percentage": 84.98, "elapsed_time": "0:14:28", "remaining_time": "0:02:33"}
431
+ {"current_steps": 431, "total_steps": 506, "loss": 0.1337, "lr": 5.323529259560911e-07, "epoch": 1.7035573122529644, "percentage": 85.18, "elapsed_time": "0:14:30", "remaining_time": "0:02:31"}
432
+ {"current_steps": 432, "total_steps": 506, "loss": 0.1125, "lr": 5.185004902241241e-07, "epoch": 1.7075098814229248, "percentage": 85.38, "elapsed_time": "0:14:32", "remaining_time": "0:02:29"}
433
+ {"current_steps": 433, "total_steps": 506, "loss": 0.1059, "lr": 5.04820805531866e-07, "epoch": 1.7114624505928853, "percentage": 85.57, "elapsed_time": "0:14:34", "remaining_time": "0:02:27"}
434
+ {"current_steps": 434, "total_steps": 506, "loss": 0.0999, "lr": 4.91314399198296e-07, "epoch": 1.7154150197628457, "percentage": 85.77, "elapsed_time": "0:14:36", "remaining_time": "0:02:25"}
435
+ {"current_steps": 435, "total_steps": 506, "loss": 0.1257, "lr": 4.779817918629326e-07, "epoch": 1.7193675889328062, "percentage": 85.97, "elapsed_time": "0:14:38", "remaining_time": "0:02:23"}
436
+ {"current_steps": 436, "total_steps": 506, "loss": 0.1236, "lr": 4.6482349746575783e-07, "epoch": 1.7233201581027668, "percentage": 86.17, "elapsed_time": "0:14:40", "remaining_time": "0:02:21"}
437
+ {"current_steps": 437, "total_steps": 506, "loss": 0.1066, "lr": 4.5184002322740784e-07, "epoch": 1.7272727272727273, "percentage": 86.36, "elapsed_time": "0:14:42", "remaining_time": "0:02:19"}
438
+ {"current_steps": 438, "total_steps": 506, "loss": 0.1149, "lr": 4.390318696296247e-07, "epoch": 1.7312252964426877, "percentage": 86.56, "elapsed_time": "0:14:44", "remaining_time": "0:02:17"}
439
+ {"current_steps": 439, "total_steps": 506, "loss": 0.135, "lr": 4.2639953039595725e-07, "epoch": 1.7351778656126482, "percentage": 86.76, "elapsed_time": "0:14:46", "remaining_time": "0:02:15"}
440
+ {"current_steps": 440, "total_steps": 506, "loss": 0.1349, "lr": 4.139434924727359e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:14:48", "remaining_time": "0:02:13"}
441
+ {"current_steps": 441, "total_steps": 506, "loss": 0.1157, "lr": 4.0166423601029735e-07, "epoch": 1.7430830039525693, "percentage": 87.15, "elapsed_time": "0:14:50", "remaining_time": "0:02:11"}
442
+ {"current_steps": 442, "total_steps": 506, "loss": 0.136, "lr": 3.8956223434447936e-07, "epoch": 1.7470355731225298, "percentage": 87.35, "elapsed_time": "0:14:52", "remaining_time": "0:02:09"}
443
+ {"current_steps": 443, "total_steps": 506, "loss": 0.1223, "lr": 3.776379539783709e-07, "epoch": 1.7509881422924902, "percentage": 87.55, "elapsed_time": "0:14:54", "remaining_time": "0:02:07"}
444
+ {"current_steps": 444, "total_steps": 506, "loss": 0.1485, "lr": 3.658918545643353e-07, "epoch": 1.7549407114624507, "percentage": 87.75, "elapsed_time": "0:14:56", "remaining_time": "0:02:05"}
445
+ {"current_steps": 445, "total_steps": 506, "loss": 0.1212, "lr": 3.543243888862841e-07, "epoch": 1.7588932806324111, "percentage": 87.94, "elapsed_time": "0:14:58", "remaining_time": "0:02:03"}
446
+ {"current_steps": 446, "total_steps": 506, "loss": 0.1193, "lr": 3.429360028422307e-07, "epoch": 1.7628458498023716, "percentage": 88.14, "elapsed_time": "0:15:00", "remaining_time": "0:02:01"}
447
+ {"current_steps": 447, "total_steps": 506, "loss": 0.1133, "lr": 3.317271354270968e-07, "epoch": 1.766798418972332, "percentage": 88.34, "elapsed_time": "0:15:02", "remaining_time": "0:01:59"}
448
+ {"current_steps": 448, "total_steps": 506, "loss": 0.1333, "lr": 3.2069821871579255e-07, "epoch": 1.7707509881422925, "percentage": 88.54, "elapsed_time": "0:15:04", "remaining_time": "0:01:57"}
449
+ {"current_steps": 449, "total_steps": 506, "loss": 0.1181, "lr": 3.098496778465621e-07, "epoch": 1.774703557312253, "percentage": 88.74, "elapsed_time": "0:15:06", "remaining_time": "0:01:55"}
450
+ {"current_steps": 450, "total_steps": 506, "loss": 0.1189, "lr": 2.991819310045929e-07, "epoch": 1.7786561264822134, "percentage": 88.93, "elapsed_time": "0:15:08", "remaining_time": "0:01:53"}
451
+ {"current_steps": 451, "total_steps": 506, "loss": 0.1103, "lr": 2.88695389405898e-07, "epoch": 1.7826086956521738, "percentage": 89.13, "elapsed_time": "0:15:10", "remaining_time": "0:01:51"}
452
+ {"current_steps": 452, "total_steps": 506, "loss": 0.1285, "lr": 2.783904572814622e-07, "epoch": 1.7865612648221343, "percentage": 89.33, "elapsed_time": "0:15:12", "remaining_time": "0:01:49"}
453
+ {"current_steps": 453, "total_steps": 506, "loss": 0.1294, "lr": 2.682675318616618e-07, "epoch": 1.7905138339920947, "percentage": 89.53, "elapsed_time": "0:15:14", "remaining_time": "0:01:46"}
454
+ {"current_steps": 454, "total_steps": 506, "loss": 0.1123, "lr": 2.583270033609536e-07, "epoch": 1.7944664031620552, "percentage": 89.72, "elapsed_time": "0:15:16", "remaining_time": "0:01:44"}
455
+ {"current_steps": 455, "total_steps": 506, "loss": 0.1104, "lr": 2.4856925496283045e-07, "epoch": 1.7984189723320159, "percentage": 89.92, "elapsed_time": "0:15:18", "remaining_time": "0:01:42"}
456
+ {"current_steps": 456, "total_steps": 506, "loss": 0.1126, "lr": 2.3899466280504936e-07, "epoch": 1.8023715415019763, "percentage": 90.12, "elapsed_time": "0:15:20", "remaining_time": "0:01:40"}
457
+ {"current_steps": 457, "total_steps": 506, "loss": 0.1351, "lr": 2.2960359596513714e-07, "epoch": 1.8063241106719368, "percentage": 90.32, "elapsed_time": "0:15:22", "remaining_time": "0:01:38"}
458
+ {"current_steps": 458, "total_steps": 506, "loss": 0.1369, "lr": 2.203964164461597e-07, "epoch": 1.8102766798418972, "percentage": 90.51, "elapsed_time": "0:15:24", "remaining_time": "0:01:36"}
459
+ {"current_steps": 459, "total_steps": 506, "loss": 0.1291, "lr": 2.113734791627664e-07, "epoch": 1.8142292490118577, "percentage": 90.71, "elapsed_time": "0:15:26", "remaining_time": "0:01:34"}
460
+ {"current_steps": 460, "total_steps": 506, "loss": 0.1469, "lr": 2.0253513192751374e-07, "epoch": 1.8181818181818183, "percentage": 90.91, "elapsed_time": "0:15:28", "remaining_time": "0:01:32"}
461
+ {"current_steps": 461, "total_steps": 506, "loss": 0.1379, "lr": 1.9388171543745394e-07, "epoch": 1.8221343873517788, "percentage": 91.11, "elapsed_time": "0:15:30", "remaining_time": "0:01:30"}
462
+ {"current_steps": 462, "total_steps": 506, "loss": 0.1117, "lr": 1.8541356326100436e-07, "epoch": 1.8260869565217392, "percentage": 91.3, "elapsed_time": "0:15:32", "remaining_time": "0:01:28"}
463
+ {"current_steps": 463, "total_steps": 506, "loss": 0.1398, "lr": 1.7713100182508604e-07, "epoch": 1.8300395256916997, "percentage": 91.5, "elapsed_time": "0:15:34", "remaining_time": "0:01:26"}
464
+ {"current_steps": 464, "total_steps": 506, "loss": 0.1128, "lr": 1.6903435040254545e-07, "epoch": 1.8339920948616601, "percentage": 91.7, "elapsed_time": "0:15:36", "remaining_time": "0:01:24"}
465
+ {"current_steps": 465, "total_steps": 506, "loss": 0.1099, "lr": 1.6112392109984386e-07, "epoch": 1.8379446640316206, "percentage": 91.9, "elapsed_time": "0:15:38", "remaining_time": "0:01:22"}
466
+ {"current_steps": 466, "total_steps": 506, "loss": 0.1262, "lr": 1.5340001884502577e-07, "epoch": 1.841897233201581, "percentage": 92.09, "elapsed_time": "0:15:40", "remaining_time": "0:01:20"}
467
+ {"current_steps": 467, "total_steps": 506, "loss": 0.1193, "lr": 1.4586294137596768e-07, "epoch": 1.8458498023715415, "percentage": 92.29, "elapsed_time": "0:15:42", "remaining_time": "0:01:18"}
468
+ {"current_steps": 468, "total_steps": 506, "loss": 0.1041, "lr": 1.385129792288986e-07, "epoch": 1.849802371541502, "percentage": 92.49, "elapsed_time": "0:15:44", "remaining_time": "0:01:16"}
469
+ {"current_steps": 469, "total_steps": 506, "loss": 0.1301, "lr": 1.313504157272022e-07, "epoch": 1.8537549407114624, "percentage": 92.69, "elapsed_time": "0:15:46", "remaining_time": "0:01:14"}
470
+ {"current_steps": 470, "total_steps": 506, "loss": 0.1289, "lr": 1.2437552697049327e-07, "epoch": 1.8577075098814229, "percentage": 92.89, "elapsed_time": "0:15:48", "remaining_time": "0:01:12"}
471
+ {"current_steps": 471, "total_steps": 506, "loss": 0.1283, "lr": 1.1758858182397692e-07, "epoch": 1.8616600790513833, "percentage": 93.08, "elapsed_time": "0:15:50", "remaining_time": "0:01:10"}
472
+ {"current_steps": 472, "total_steps": 506, "loss": 0.1335, "lr": 1.1098984190808403e-07, "epoch": 1.8656126482213438, "percentage": 93.28, "elapsed_time": "0:15:52", "remaining_time": "0:01:08"}
473
+ {"current_steps": 473, "total_steps": 506, "loss": 0.0996, "lr": 1.0457956158838545e-07, "epoch": 1.8695652173913042, "percentage": 93.48, "elapsed_time": "0:15:54", "remaining_time": "0:01:06"}
474
+ {"current_steps": 474, "total_steps": 506, "loss": 0.1153, "lr": 9.835798796578755e-08, "epoch": 1.8735177865612647, "percentage": 93.68, "elapsed_time": "0:15:56", "remaining_time": "0:01:04"}
475
+ {"current_steps": 475, "total_steps": 506, "loss": 0.1304, "lr": 9.232536086700605e-08, "epoch": 1.8774703557312253, "percentage": 93.87, "elapsed_time": "0:15:58", "remaining_time": "0:01:02"}
476
+ {"current_steps": 476, "total_steps": 506, "loss": 0.1213, "lr": 8.648191283532337e-08, "epoch": 1.8814229249011858, "percentage": 94.07, "elapsed_time": "0:16:00", "remaining_time": "0:01:00"}
477
+ {"current_steps": 477, "total_steps": 506, "loss": 0.1161, "lr": 8.082786912162243e-08, "epoch": 1.8853754940711462, "percentage": 94.27, "elapsed_time": "0:16:02", "remaining_time": "0:00:58"}
478
+ {"current_steps": 478, "total_steps": 506, "loss": 0.1141, "lr": 7.536344767570536e-08, "epoch": 1.8893280632411067, "percentage": 94.47, "elapsed_time": "0:16:04", "remaining_time": "0:00:56"}
479
+ {"current_steps": 479, "total_steps": 506, "loss": 0.1228, "lr": 7.008885913789066e-08, "epoch": 1.8932806324110671, "percentage": 94.66, "elapsed_time": "0:16:06", "remaining_time": "0:00:54"}
480
+ {"current_steps": 480, "total_steps": 506, "loss": 0.1303, "lr": 6.500430683089532e-08, "epoch": 1.8972332015810278, "percentage": 94.86, "elapsed_time": "0:16:08", "remaining_time": "0:00:52"}
481
+ {"current_steps": 481, "total_steps": 506, "loss": 0.1338, "lr": 6.010998675199554e-08, "epoch": 1.9011857707509883, "percentage": 95.06, "elapsed_time": "0:16:10", "remaining_time": "0:00:50"}
482
+ {"current_steps": 482, "total_steps": 506, "loss": 0.1405, "lr": 5.5406087565471054e-08, "epoch": 1.9051383399209487, "percentage": 95.26, "elapsed_time": "0:16:12", "remaining_time": "0:00:48"}
483
+ {"current_steps": 483, "total_steps": 506, "loss": 0.1281, "lr": 5.089279059533658e-08, "epoch": 1.9090909090909092, "percentage": 95.45, "elapsed_time": "0:16:14", "remaining_time": "0:00:46"}
484
+ {"current_steps": 484, "total_steps": 506, "loss": 0.12, "lr": 4.657026981834623e-08, "epoch": 1.9130434782608696, "percentage": 95.65, "elapsed_time": "0:16:16", "remaining_time": "0:00:44"}
485
+ {"current_steps": 485, "total_steps": 506, "loss": 0.1144, "lr": 4.2438691857292215e-08, "epoch": 1.91699604743083, "percentage": 95.85, "elapsed_time": "0:16:18", "remaining_time": "0:00:42"}
486
+ {"current_steps": 486, "total_steps": 506, "loss": 0.1347, "lr": 3.849821597457892e-08, "epoch": 1.9209486166007905, "percentage": 96.05, "elapsed_time": "0:16:20", "remaining_time": "0:00:40"}
487
+ {"current_steps": 487, "total_steps": 506, "loss": 0.1129, "lr": 3.474899406608501e-08, "epoch": 1.924901185770751, "percentage": 96.25, "elapsed_time": "0:16:23", "remaining_time": "0:00:38"}
488
+ {"current_steps": 488, "total_steps": 506, "loss": 0.123, "lr": 3.119117065530808e-08, "epoch": 1.9288537549407114, "percentage": 96.44, "elapsed_time": "0:16:25", "remaining_time": "0:00:36"}
489
+ {"current_steps": 489, "total_steps": 506, "loss": 0.1538, "lr": 2.7824882887793058e-08, "epoch": 1.9328063241106719, "percentage": 96.64, "elapsed_time": "0:16:27", "remaining_time": "0:00:34"}
490
+ {"current_steps": 490, "total_steps": 506, "loss": 0.1416, "lr": 2.4650260525846404e-08, "epoch": 1.9367588932806323, "percentage": 96.84, "elapsed_time": "0:16:29", "remaining_time": "0:00:32"}
491
+ {"current_steps": 491, "total_steps": 506, "loss": 0.1147, "lr": 2.1667425943532884e-08, "epoch": 1.9407114624505928, "percentage": 97.04, "elapsed_time": "0:16:31", "remaining_time": "0:00:30"}
492
+ {"current_steps": 492, "total_steps": 506, "loss": 0.1289, "lr": 1.8876494121959908e-08, "epoch": 1.9446640316205532, "percentage": 97.23, "elapsed_time": "0:16:33", "remaining_time": "0:00:28"}
493
+ {"current_steps": 493, "total_steps": 506, "loss": 0.1294, "lr": 1.627757264484442e-08, "epoch": 1.9486166007905137, "percentage": 97.43, "elapsed_time": "0:16:35", "remaining_time": "0:00:26"}
494
+ {"current_steps": 494, "total_steps": 506, "loss": 0.1262, "lr": 1.387076169436563e-08, "epoch": 1.9525691699604744, "percentage": 97.63, "elapsed_time": "0:16:37", "remaining_time": "0:00:24"}
495
+ {"current_steps": 495, "total_steps": 506, "loss": 0.1126, "lr": 1.1656154047303691e-08, "epoch": 1.9565217391304348, "percentage": 97.83, "elapsed_time": "0:16:39", "remaining_time": "0:00:22"}
496
+ {"current_steps": 496, "total_steps": 506, "loss": 0.1485, "lr": 9.633835071463094e-09, "epoch": 1.9604743083003953, "percentage": 98.02, "elapsed_time": "0:16:41", "remaining_time": "0:00:20"}
497
+ {"current_steps": 497, "total_steps": 506, "loss": 0.1293, "lr": 7.803882722381417e-09, "epoch": 1.9644268774703557, "percentage": 98.22, "elapsed_time": "0:16:43", "remaining_time": "0:00:18"}
498
+ {"current_steps": 498, "total_steps": 506, "loss": 0.1428, "lr": 6.166367540325624e-09, "epoch": 1.9683794466403162, "percentage": 98.42, "elapsed_time": "0:16:45", "remaining_time": "0:00:16"}
499
+ {"current_steps": 499, "total_steps": 506, "loss": 0.1129, "lr": 4.721352647572564e-09, "epoch": 1.9723320158102768, "percentage": 98.62, "elapsed_time": "0:16:47", "remaining_time": "0:00:14"}
500
+ {"current_steps": 500, "total_steps": 506, "loss": 0.1394, "lr": 3.4688937459737004e-09, "epoch": 1.9762845849802373, "percentage": 98.81, "elapsed_time": "0:16:49", "remaining_time": "0:00:12"}
501
+ {"current_steps": 500, "total_steps": 506, "eval_loss": 0.16894643008708954, "epoch": 1.9762845849802373, "percentage": 98.81, "elapsed_time": "0:16:52", "remaining_time": "0:00:12"}
502
+ {"current_steps": 501, "total_steps": 506, "loss": 0.126, "lr": 2.4090391148112734e-09, "epoch": 1.9802371541501977, "percentage": 99.01, "elapsed_time": "0:16:54", "remaining_time": "0:00:10"}
503
+ {"current_steps": 502, "total_steps": 506, "loss": 0.1161, "lr": 1.5418296089358964e-09, "epoch": 1.9841897233201582, "percentage": 99.21, "elapsed_time": "0:16:56", "remaining_time": "0:00:08"}
504
+ {"current_steps": 503, "total_steps": 506, "loss": 0.1159, "lr": 8.672986571894859e-10, "epoch": 1.9881422924901186, "percentage": 99.41, "elapsed_time": "0:16:58", "remaining_time": "0:00:06"}
505
+ {"current_steps": 504, "total_steps": 506, "loss": 0.1143, "lr": 3.854722611201789e-10, "epoch": 1.992094861660079, "percentage": 99.6, "elapsed_time": "0:17:00", "remaining_time": "0:00:04"}
506
+ {"current_steps": 505, "total_steps": 506, "loss": 0.1237, "lr": 9.636899397813537e-11, "epoch": 1.9960474308300395, "percentage": 99.8, "elapsed_time": "0:17:01", "remaining_time": "0:00:02"}
507
+ {"current_steps": 506, "total_steps": 506, "loss": 0.1028, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:17:02", "remaining_time": "0:00:00"}
508
+ {"current_steps": 506, "total_steps": 506, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:17:12", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 506,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003952569169960474,
13
+ "grad_norm": 16.020900110158806,
14
+ "learning_rate": 9.999903631006022e-06,
15
+ "loss": 1.0657,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.007905138339920948,
20
+ "grad_norm": 9.896813279978835,
21
+ "learning_rate": 9.999614527738882e-06,
22
+ "loss": 0.8817,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.011857707509881422,
27
+ "grad_norm": 4.710814039433313,
28
+ "learning_rate": 9.99913270134281e-06,
29
+ "loss": 0.6038,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.015810276679841896,
34
+ "grad_norm": 3.213510727342975,
35
+ "learning_rate": 9.998458170391065e-06,
36
+ "loss": 0.5555,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.019762845849802372,
41
+ "grad_norm": 3.399601233005852,
42
+ "learning_rate": 9.99759096088519e-06,
43
+ "loss": 0.4486,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.023715415019762844,
48
+ "grad_norm": 3.2249204890399112,
49
+ "learning_rate": 9.996531106254027e-06,
50
+ "loss": 0.4616,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.02766798418972332,
55
+ "grad_norm": 2.5076762498803196,
56
+ "learning_rate": 9.995278647352428e-06,
57
+ "loss": 0.4705,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03162055335968379,
62
+ "grad_norm": 2.865637105499682,
63
+ "learning_rate": 9.993833632459675e-06,
64
+ "loss": 0.4065,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03557312252964427,
69
+ "grad_norm": 2.182471312496633,
70
+ "learning_rate": 9.99219611727762e-06,
71
+ "loss": 0.3791,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.039525691699604744,
76
+ "grad_norm": 1.8817059063630837,
77
+ "learning_rate": 9.990366164928538e-06,
78
+ "loss": 0.3968,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.043478260869565216,
83
+ "grad_norm": 1.7437964277471723,
84
+ "learning_rate": 9.988343845952697e-06,
85
+ "loss": 0.3593,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04743083003952569,
90
+ "grad_norm": 1.718975131845364,
91
+ "learning_rate": 9.986129238305635e-06,
92
+ "loss": 0.3241,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05138339920948617,
97
+ "grad_norm": 1.7519764781357152,
98
+ "learning_rate": 9.983722427355157e-06,
99
+ "loss": 0.3514,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.05533596837944664,
104
+ "grad_norm": 1.8585607479109172,
105
+ "learning_rate": 9.98112350587804e-06,
106
+ "loss": 0.3307,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.05928853754940711,
111
+ "grad_norm": 1.648833246586736,
112
+ "learning_rate": 9.978332574056468e-06,
113
+ "loss": 0.3382,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06324110671936758,
118
+ "grad_norm": 1.5144376829290096,
119
+ "learning_rate": 9.975349739474156e-06,
120
+ "loss": 0.3025,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.06719367588932806,
125
+ "grad_norm": 1.4722946130746835,
126
+ "learning_rate": 9.972175117112208e-06,
127
+ "loss": 0.3291,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07114624505928854,
132
+ "grad_norm": 1.5590402414570852,
133
+ "learning_rate": 9.968808829344692e-06,
134
+ "loss": 0.318,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.07509881422924901,
139
+ "grad_norm": 1.529364514445946,
140
+ "learning_rate": 9.965251005933915e-06,
141
+ "loss": 0.3029,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.07905138339920949,
146
+ "grad_norm": 1.5355343280276874,
147
+ "learning_rate": 9.961501784025423e-06,
148
+ "loss": 0.3075,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.08300395256916997,
153
+ "grad_norm": 1.4284315641862246,
154
+ "learning_rate": 9.95756130814271e-06,
155
+ "loss": 0.2733,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.08695652173913043,
160
+ "grad_norm": 1.529934818238827,
161
+ "learning_rate": 9.953429730181653e-06,
162
+ "loss": 0.3319,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.09090909090909091,
167
+ "grad_norm": 1.5594666788219782,
168
+ "learning_rate": 9.949107209404664e-06,
169
+ "loss": 0.2998,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.09486166007905138,
174
+ "grad_norm": 1.43783031647119,
175
+ "learning_rate": 9.94459391243453e-06,
176
+ "loss": 0.2856,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.09881422924901186,
181
+ "grad_norm": 1.6552583911804946,
182
+ "learning_rate": 9.939890013248006e-06,
183
+ "loss": 0.3287,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.10276679841897234,
188
+ "grad_norm": 1.4553289738630346,
189
+ "learning_rate": 9.934995693169104e-06,
190
+ "loss": 0.2726,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.1067193675889328,
195
+ "grad_norm": 1.7057032170116595,
196
+ "learning_rate": 9.929911140862109e-06,
197
+ "loss": 0.3412,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11067193675889328,
202
+ "grad_norm": 1.4032529471627393,
203
+ "learning_rate": 9.924636552324296e-06,
204
+ "loss": 0.2484,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.11462450592885376,
209
+ "grad_norm": 1.6007146129563619,
210
+ "learning_rate": 9.919172130878378e-06,
211
+ "loss": 0.3265,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.11857707509881422,
216
+ "grad_norm": 1.4391496848114302,
217
+ "learning_rate": 9.913518087164678e-06,
218
+ "loss": 0.285,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.1225296442687747,
223
+ "grad_norm": 1.4062720696044961,
224
+ "learning_rate": 9.907674639132995e-06,
225
+ "loss": 0.2548,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.12648221343873517,
230
+ "grad_norm": 1.410271063639066,
231
+ "learning_rate": 9.901642012034214e-06,
232
+ "loss": 0.2508,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.13043478260869565,
237
+ "grad_norm": 1.5527348593856665,
238
+ "learning_rate": 9.895420438411616e-06,
239
+ "loss": 0.2976,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.13438735177865613,
244
+ "grad_norm": 1.321537975619614,
245
+ "learning_rate": 9.889010158091917e-06,
246
+ "loss": 0.2572,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.1383399209486166,
251
+ "grad_norm": 1.421996806107464,
252
+ "learning_rate": 9.882411418176023e-06,
253
+ "loss": 0.2706,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1422924901185771,
258
+ "grad_norm": 1.3572216549078873,
259
+ "learning_rate": 9.875624473029508e-06,
260
+ "loss": 0.2545,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.14624505928853754,
265
+ "grad_norm": 1.2631690700776463,
266
+ "learning_rate": 9.8686495842728e-06,
267
+ "loss": 0.2625,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.15019762845849802,
272
+ "grad_norm": 1.2621066835028363,
273
+ "learning_rate": 9.861487020771103e-06,
274
+ "loss": 0.2591,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1541501976284585,
279
+ "grad_norm": 1.2949235488783764,
280
+ "learning_rate": 9.854137058624034e-06,
281
+ "loss": 0.2309,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.15810276679841898,
286
+ "grad_norm": 1.3003116841403821,
287
+ "learning_rate": 9.846599981154975e-06,
288
+ "loss": 0.2326,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.16205533596837945,
293
+ "grad_norm": 1.3768166039897276,
294
+ "learning_rate": 9.838876078900158e-06,
295
+ "loss": 0.2397,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.16600790513833993,
300
+ "grad_norm": 1.3538215396932514,
301
+ "learning_rate": 9.830965649597455e-06,
302
+ "loss": 0.252,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.16996047430830039,
307
+ "grad_norm": 1.4163162387664199,
308
+ "learning_rate": 9.822868998174914e-06,
309
+ "loss": 0.2448,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.17391304347826086,
314
+ "grad_norm": 1.4257156730091618,
315
+ "learning_rate": 9.814586436738998e-06,
316
+ "loss": 0.2371,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.17786561264822134,
321
+ "grad_norm": 1.4437391682465417,
322
+ "learning_rate": 9.806118284562547e-06,
323
+ "loss": 0.2907,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.18181818181818182,
328
+ "grad_norm": 1.391249530608691,
329
+ "learning_rate": 9.797464868072489e-06,
330
+ "loss": 0.2683,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.1857707509881423,
335
+ "grad_norm": 1.4016200934541518,
336
+ "learning_rate": 9.788626520837235e-06,
337
+ "loss": 0.2473,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.18972332015810275,
342
+ "grad_norm": 1.279328106626107,
343
+ "learning_rate": 9.779603583553842e-06,
344
+ "loss": 0.2341,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.19367588932806323,
349
+ "grad_norm": 1.3404807365252567,
350
+ "learning_rate": 9.770396404034863e-06,
351
+ "loss": 0.2675,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.1976284584980237,
356
+ "grad_norm": 1.4585279577064512,
357
+ "learning_rate": 9.76100533719495e-06,
358
+ "loss": 0.2685,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.2015810276679842,
363
+ "grad_norm": 1.4424775598833863,
364
+ "learning_rate": 9.75143074503717e-06,
365
+ "loss": 0.2311,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.20553359683794467,
370
+ "grad_norm": 1.3955125763500507,
371
+ "learning_rate": 9.741672996639046e-06,
372
+ "loss": 0.2627,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.20948616600790515,
377
+ "grad_norm": 1.4097242793234939,
378
+ "learning_rate": 9.731732468138338e-06,
379
+ "loss": 0.2512,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.2134387351778656,
384
+ "grad_norm": 1.2779409261860988,
385
+ "learning_rate": 9.72160954271854e-06,
386
+ "loss": 0.248,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.21739130434782608,
391
+ "grad_norm": 1.3115141733721187,
392
+ "learning_rate": 9.711304610594104e-06,
393
+ "loss": 0.2548,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.22134387351778656,
398
+ "grad_norm": 1.3040054071646883,
399
+ "learning_rate": 9.700818068995407e-06,
400
+ "loss": 0.2115,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.22529644268774704,
405
+ "grad_norm": 1.3228671690231326,
406
+ "learning_rate": 9.69015032215344e-06,
407
+ "loss": 0.2372,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.22924901185770752,
412
+ "grad_norm": 1.2810295113715335,
413
+ "learning_rate": 9.679301781284209e-06,
414
+ "loss": 0.2586,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.233201581027668,
419
+ "grad_norm": 1.2300547258655599,
420
+ "learning_rate": 9.668272864572904e-06,
421
+ "loss": 0.2122,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.23715415019762845,
426
+ "grad_norm": 1.331764793327734,
427
+ "learning_rate": 9.65706399715777e-06,
428
+ "loss": 0.2294,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.24110671936758893,
433
+ "grad_norm": 1.245135656410948,
434
+ "learning_rate": 9.645675611113715e-06,
435
+ "loss": 0.2234,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2450592885375494,
440
+ "grad_norm": 1.2821048117267706,
441
+ "learning_rate": 9.634108145435665e-06,
442
+ "loss": 0.2111,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.2490118577075099,
447
+ "grad_norm": 1.3953990850010947,
448
+ "learning_rate": 9.62236204602163e-06,
449
+ "loss": 0.2423,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.25296442687747034,
454
+ "grad_norm": 1.3305442952896998,
455
+ "learning_rate": 9.610437765655522e-06,
456
+ "loss": 0.2169,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.25691699604743085,
461
+ "grad_norm": 1.3427264285897607,
462
+ "learning_rate": 9.598335763989703e-06,
463
+ "loss": 0.2387,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2608695652173913,
468
+ "grad_norm": 1.2462397253811373,
469
+ "learning_rate": 9.586056507527266e-06,
470
+ "loss": 0.2002,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.2648221343873518,
475
+ "grad_norm": 1.4106601403861017,
476
+ "learning_rate": 9.573600469604044e-06,
477
+ "loss": 0.2345,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.26877470355731226,
482
+ "grad_norm": 1.4558970695841007,
483
+ "learning_rate": 9.560968130370376e-06,
484
+ "loss": 0.257,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.2727272727272727,
489
+ "grad_norm": 1.2869342015693788,
490
+ "learning_rate": 9.548159976772593e-06,
491
+ "loss": 0.2272,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.2766798418972332,
496
+ "grad_norm": 1.2457392708337578,
497
+ "learning_rate": 9.535176502534242e-06,
498
+ "loss": 0.2011,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.28063241106719367,
503
+ "grad_norm": 1.2710277485877495,
504
+ "learning_rate": 9.522018208137066e-06,
505
+ "loss": 0.2198,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.2845849802371542,
510
+ "grad_norm": 1.4429390388818002,
511
+ "learning_rate": 9.508685600801704e-06,
512
+ "loss": 0.2277,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.2885375494071146,
517
+ "grad_norm": 1.2389843654949855,
518
+ "learning_rate": 9.495179194468135e-06,
519
+ "loss": 0.2269,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.2924901185770751,
524
+ "grad_norm": 1.2313451113400058,
525
+ "learning_rate": 9.481499509775878e-06,
526
+ "loss": 0.2229,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.2964426877470356,
531
+ "grad_norm": 1.2005736870957262,
532
+ "learning_rate": 9.467647074043911e-06,
533
+ "loss": 0.2132,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.30039525691699603,
538
+ "grad_norm": 1.3356666012024943,
539
+ "learning_rate": 9.453622421250353e-06,
540
+ "loss": 0.2261,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.30434782608695654,
545
+ "grad_norm": 1.307750115235254,
546
+ "learning_rate": 9.439426092011877e-06,
547
+ "loss": 0.2186,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.308300395256917,
552
+ "grad_norm": 1.3023411955103703,
553
+ "learning_rate": 9.42505863356287e-06,
554
+ "loss": 0.2241,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.31225296442687744,
559
+ "grad_norm": 1.2340243980259775,
560
+ "learning_rate": 9.410520599734338e-06,
561
+ "loss": 0.2195,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.31620553359683795,
566
+ "grad_norm": 1.2136232872238946,
567
+ "learning_rate": 9.395812550932559e-06,
568
+ "loss": 0.2105,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3201581027667984,
573
+ "grad_norm": 1.3027913426674749,
574
+ "learning_rate": 9.38093505411748e-06,
575
+ "loss": 0.2112,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3241106719367589,
580
+ "grad_norm": 1.2355979390019485,
581
+ "learning_rate": 9.365888682780862e-06,
582
+ "loss": 0.2041,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.32806324110671936,
587
+ "grad_norm": 1.3255611172622812,
588
+ "learning_rate": 9.35067401692417e-06,
589
+ "loss": 0.2133,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.33201581027667987,
594
+ "grad_norm": 1.2110730151497104,
595
+ "learning_rate": 9.335291643036221e-06,
596
+ "loss": 0.1937,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3359683794466403,
601
+ "grad_norm": 1.2302820012512985,
602
+ "learning_rate": 9.319742154070578e-06,
603
+ "loss": 0.2127,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.33992094861660077,
608
+ "grad_norm": 1.396952411441183,
609
+ "learning_rate": 9.30402614942268e-06,
610
+ "loss": 0.2498,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3438735177865613,
615
+ "grad_norm": 1.4467617558469186,
616
+ "learning_rate": 9.288144234906753e-06,
617
+ "loss": 0.2582,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.34782608695652173,
622
+ "grad_norm": 1.2724563579817645,
623
+ "learning_rate": 9.272097022732444e-06,
624
+ "loss": 0.2094,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.35177865612648224,
629
+ "grad_norm": 1.374464706651341,
630
+ "learning_rate": 9.255885131481231e-06,
631
+ "loss": 0.2333,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.3557312252964427,
636
+ "grad_norm": 1.1876568411175543,
637
+ "learning_rate": 9.239509186082574e-06,
638
+ "loss": 0.1893,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.35968379446640314,
643
+ "grad_norm": 1.3268240601065355,
644
+ "learning_rate": 9.222969817789829e-06,
645
+ "loss": 0.2124,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.36363636363636365,
650
+ "grad_norm": 1.2681330364031638,
651
+ "learning_rate": 9.206267664155906e-06,
652
+ "loss": 0.1973,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.3675889328063241,
657
+ "grad_norm": 1.2255166053795126,
658
+ "learning_rate": 9.189403369008704e-06,
659
+ "loss": 0.224,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3715415019762846,
664
+ "grad_norm": 1.3042156326130103,
665
+ "learning_rate": 9.172377582426286e-06,
666
+ "loss": 0.2366,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.37549407114624506,
671
+ "grad_norm": 1.2467295856925376,
672
+ "learning_rate": 9.155190960711822e-06,
673
+ "loss": 0.2307,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.3794466403162055,
678
+ "grad_norm": 1.3438520348323209,
679
+ "learning_rate": 9.137844166368289e-06,
680
+ "loss": 0.2358,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.383399209486166,
685
+ "grad_norm": 1.195811544532563,
686
+ "learning_rate": 9.120337868072933e-06,
687
+ "loss": 0.1998,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.38735177865612647,
692
+ "grad_norm": 1.1483129999113106,
693
+ "learning_rate": 9.1026727406515e-06,
694
+ "loss": 0.1992,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.391304347826087,
699
+ "grad_norm": 1.2903993706253556,
700
+ "learning_rate": 9.08484946505221e-06,
701
+ "loss": 0.2103,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.3952569169960474,
706
+ "grad_norm": 1.3546933181924383,
707
+ "learning_rate": 9.066868728319522e-06,
708
+ "loss": 0.2431,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.39920948616600793,
713
+ "grad_norm": 1.2376669346579956,
714
+ "learning_rate": 9.048731223567636e-06,
715
+ "loss": 0.2112,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4031620553359684,
720
+ "grad_norm": 1.1433249084583228,
721
+ "learning_rate": 9.03043764995379e-06,
722
+ "loss": 0.187,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.40711462450592883,
727
+ "grad_norm": 1.2494316975005797,
728
+ "learning_rate": 9.011988712651295e-06,
729
+ "loss": 0.2254,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.41106719367588934,
734
+ "grad_norm": 1.164269222531622,
735
+ "learning_rate": 8.993385122822364e-06,
736
+ "loss": 0.196,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.4150197628458498,
741
+ "grad_norm": 1.2168120947010408,
742
+ "learning_rate": 8.974627597590693e-06,
743
+ "loss": 0.1871,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.4189723320158103,
748
+ "grad_norm": 1.2068782855519822,
749
+ "learning_rate": 8.955716860013812e-06,
750
+ "loss": 0.2061,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.42292490118577075,
755
+ "grad_norm": 1.217200175520014,
756
+ "learning_rate": 8.936653639055225e-06,
757
+ "loss": 0.2128,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.4268774703557312,
762
+ "grad_norm": 1.1978052117951064,
763
+ "learning_rate": 8.917438669556307e-06,
764
+ "loss": 0.2154,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.4308300395256917,
769
+ "grad_norm": 1.2353347282860097,
770
+ "learning_rate": 8.898072692207964e-06,
771
+ "loss": 0.2166,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.43478260869565216,
776
+ "grad_norm": 1.2843635498058075,
777
+ "learning_rate": 8.8785564535221e-06,
778
+ "loss": 0.222,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.43873517786561267,
783
+ "grad_norm": 1.2399015935864328,
784
+ "learning_rate": 8.85889070580283e-06,
785
+ "loss": 0.2106,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.4426877470355731,
790
+ "grad_norm": 1.2553929591861368,
791
+ "learning_rate": 8.839076207117485e-06,
792
+ "loss": 0.2428,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.44664031620553357,
797
+ "grad_norm": 1.344840565207265,
798
+ "learning_rate": 8.819113721267385e-06,
799
+ "loss": 0.231,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.4505928853754941,
804
+ "grad_norm": 1.1925173566212948,
805
+ "learning_rate": 8.7990040177584e-06,
806
+ "loss": 0.1862,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.45454545454545453,
811
+ "grad_norm": 1.2960852273499728,
812
+ "learning_rate": 8.778747871771293e-06,
813
+ "loss": 0.2015,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.45849802371541504,
818
+ "grad_norm": 1.222878498466299,
819
+ "learning_rate": 8.758346064131824e-06,
820
+ "loss": 0.2153,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.4624505928853755,
825
+ "grad_norm": 1.274954724070636,
826
+ "learning_rate": 8.737799381280667e-06,
827
+ "loss": 0.2027,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.466403162055336,
832
+ "grad_norm": 1.387737355454323,
833
+ "learning_rate": 8.717108615243081e-06,
834
+ "loss": 0.2221,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.47035573122529645,
839
+ "grad_norm": 1.3426117595660954,
840
+ "learning_rate": 8.696274563598395e-06,
841
+ "loss": 0.2255,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.4743083003952569,
846
+ "grad_norm": 1.119139769942221,
847
+ "learning_rate": 8.675298029449241e-06,
848
+ "loss": 0.18,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.4782608695652174,
853
+ "grad_norm": 1.2709986698183513,
854
+ "learning_rate": 8.65417982139062e-06,
855
+ "loss": 0.2204,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.48221343873517786,
860
+ "grad_norm": 1.3155178470853532,
861
+ "learning_rate": 8.63292075347872e-06,
862
+ "loss": 0.2098,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.48616600790513836,
867
+ "grad_norm": 1.1164093498148737,
868
+ "learning_rate": 8.611521645199532e-06,
869
+ "loss": 0.1699,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.4901185770750988,
874
+ "grad_norm": 1.2232423322705634,
875
+ "learning_rate": 8.589983321437271e-06,
876
+ "loss": 0.2048,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.49407114624505927,
881
+ "grad_norm": 1.19896747867504,
882
+ "learning_rate": 8.568306612442579e-06,
883
+ "loss": 0.1818,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.4980237154150198,
888
+ "grad_norm": 1.1935132661062275,
889
+ "learning_rate": 8.546492353800504e-06,
890
+ "loss": 0.1905,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5019762845849802,
895
+ "grad_norm": 1.3129073388913475,
896
+ "learning_rate": 8.524541386398318e-06,
897
+ "loss": 0.2249,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5059288537549407,
902
+ "grad_norm": 1.128105255244932,
903
+ "learning_rate": 8.502454556393071e-06,
904
+ "loss": 0.1853,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5098814229249012,
909
+ "grad_norm": 1.275277474434624,
910
+ "learning_rate": 8.480232715179004e-06,
911
+ "loss": 0.2268,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5138339920948617,
916
+ "grad_norm": 1.199574317058949,
917
+ "learning_rate": 8.457876719354708e-06,
918
+ "loss": 0.2159,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.5177865612648221,
923
+ "grad_norm": 1.333440075825727,
924
+ "learning_rate": 8.435387430690114e-06,
925
+ "loss": 0.2071,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.5217391304347826,
930
+ "grad_norm": 1.2298826627346486,
931
+ "learning_rate": 8.412765716093273e-06,
932
+ "loss": 0.1978,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.525691699604743,
937
+ "grad_norm": 1.1487447920512157,
938
+ "learning_rate": 8.390012447576931e-06,
939
+ "loss": 0.1681,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5296442687747036,
944
+ "grad_norm": 1.1422378679889824,
945
+ "learning_rate": 8.367128502224931e-06,
946
+ "loss": 0.1799,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5335968379446641,
951
+ "grad_norm": 1.1642741860659866,
952
+ "learning_rate": 8.344114762158391e-06,
953
+ "loss": 0.1945,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.5375494071146245,
958
+ "grad_norm": 1.3124275732270296,
959
+ "learning_rate": 8.320972114501698e-06,
960
+ "loss": 0.1994,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.541501976284585,
965
+ "grad_norm": 1.1914086199917326,
966
+ "learning_rate": 8.297701451348324e-06,
967
+ "loss": 0.1982,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.5454545454545454,
972
+ "grad_norm": 1.251119288035372,
973
+ "learning_rate": 8.274303669726427e-06,
974
+ "loss": 0.1961,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.549407114624506,
979
+ "grad_norm": 1.1421929686539185,
980
+ "learning_rate": 8.250779671564277e-06,
981
+ "loss": 0.205,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.5533596837944664,
986
+ "grad_norm": 1.26120508447205,
987
+ "learning_rate": 8.22713036365549e-06,
988
+ "loss": 0.2056,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.5573122529644269,
993
+ "grad_norm": 1.1982016744926482,
994
+ "learning_rate": 8.20335665762407e-06,
995
+ "loss": 0.2152,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.5612648221343873,
1000
+ "grad_norm": 1.2176314854159234,
1001
+ "learning_rate": 8.179459469889269e-06,
1002
+ "loss": 0.2154,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.5652173913043478,
1007
+ "grad_norm": 1.2473624074495893,
1008
+ "learning_rate": 8.155439721630265e-06,
1009
+ "loss": 0.2175,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.5691699604743083,
1014
+ "grad_norm": 1.1267383357984246,
1015
+ "learning_rate": 8.131298338750648e-06,
1016
+ "loss": 0.1892,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.5731225296442688,
1021
+ "grad_norm": 1.182358551787801,
1022
+ "learning_rate": 8.10703625184273e-06,
1023
+ "loss": 0.1972,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.5770750988142292,
1028
+ "grad_norm": 1.2568983709583992,
1029
+ "learning_rate": 8.082654396151676e-06,
1030
+ "loss": 0.2156,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.5810276679841897,
1035
+ "grad_norm": 1.3251313569923084,
1036
+ "learning_rate": 8.058153711539444e-06,
1037
+ "loss": 0.2089,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.5849802371541502,
1042
+ "grad_norm": 1.0726734543721594,
1043
+ "learning_rate": 8.03353514244857e-06,
1044
+ "loss": 0.1809,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.5889328063241107,
1049
+ "grad_norm": 1.217655834438009,
1050
+ "learning_rate": 8.008799637865741e-06,
1051
+ "loss": 0.2023,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.5928853754940712,
1056
+ "grad_norm": 1.0772407801697832,
1057
+ "learning_rate": 7.983948151285242e-06,
1058
+ "loss": 0.1796,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.5968379446640316,
1063
+ "grad_norm": 1.2413074180785202,
1064
+ "learning_rate": 7.958981640672173e-06,
1065
+ "loss": 0.1977,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6007905138339921,
1070
+ "grad_norm": 1.0852808186316445,
1071
+ "learning_rate": 7.933901068425539e-06,
1072
+ "loss": 0.1731,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6047430830039525,
1077
+ "grad_norm": 1.299528282255904,
1078
+ "learning_rate": 7.908707401341146e-06,
1079
+ "loss": 0.2216,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.6086956521739131,
1084
+ "grad_norm": 1.185556918204072,
1085
+ "learning_rate": 7.883401610574338e-06,
1086
+ "loss": 0.1908,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6126482213438735,
1091
+ "grad_norm": 1.304948505750968,
1092
+ "learning_rate": 7.857984671602547e-06,
1093
+ "loss": 0.2008,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.616600790513834,
1098
+ "grad_norm": 1.1900402122684852,
1099
+ "learning_rate": 7.832457564187715e-06,
1100
+ "loss": 0.1706,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6205533596837944,
1105
+ "grad_norm": 1.210872241558616,
1106
+ "learning_rate": 7.806821272338504e-06,
1107
+ "loss": 0.2054,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.6245059288537549,
1112
+ "grad_norm": 1.1791680850500765,
1113
+ "learning_rate": 7.781076784272377e-06,
1114
+ "loss": 0.1911,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.6284584980237155,
1119
+ "grad_norm": 1.2064915376432837,
1120
+ "learning_rate": 7.755225092377498e-06,
1121
+ "loss": 0.2123,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.6324110671936759,
1126
+ "grad_norm": 1.1788766410507692,
1127
+ "learning_rate": 7.729267193174483e-06,
1128
+ "loss": 0.2166,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.6363636363636364,
1133
+ "grad_norm": 1.2252698894797731,
1134
+ "learning_rate": 7.703204087277989e-06,
1135
+ "loss": 0.1919,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.6403162055335968,
1140
+ "grad_norm": 1.349649897365813,
1141
+ "learning_rate": 7.67703677935813e-06,
1142
+ "loss": 0.2178,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.6442687747035574,
1147
+ "grad_norm": 1.1345917440027748,
1148
+ "learning_rate": 7.650766278101762e-06,
1149
+ "loss": 0.197,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.6482213438735178,
1154
+ "grad_norm": 1.287989390837344,
1155
+ "learning_rate": 7.624393596173598e-06,
1156
+ "loss": 0.2381,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.6521739130434783,
1161
+ "grad_norm": 1.1299739332721368,
1162
+ "learning_rate": 7.597919750177168e-06,
1163
+ "loss": 0.1808,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.6561264822134387,
1168
+ "grad_norm": 1.2891189521599526,
1169
+ "learning_rate": 7.5713457606156335e-06,
1170
+ "loss": 0.219,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.6600790513833992,
1175
+ "grad_norm": 1.2643945396009584,
1176
+ "learning_rate": 7.5446726518524505e-06,
1177
+ "loss": 0.2049,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.6640316205533597,
1182
+ "grad_norm": 1.2293140206996043,
1183
+ "learning_rate": 7.51790145207188e-06,
1184
+ "loss": 0.2103,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.6679841897233202,
1189
+ "grad_norm": 1.178935960357507,
1190
+ "learning_rate": 7.4910331932393634e-06,
1191
+ "loss": 0.199,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.6719367588932806,
1196
+ "grad_norm": 1.2052463331102627,
1197
+ "learning_rate": 7.464068911061726e-06,
1198
+ "loss": 0.2096,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.6758893280632411,
1203
+ "grad_norm": 1.1862206001747997,
1204
+ "learning_rate": 7.437009644947268e-06,
1205
+ "loss": 0.1987,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.6798418972332015,
1210
+ "grad_norm": 1.256150663623612,
1211
+ "learning_rate": 7.40985643796569e-06,
1212
+ "loss": 0.2198,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.6837944664031621,
1217
+ "grad_norm": 1.1442878472683295,
1218
+ "learning_rate": 7.382610336807887e-06,
1219
+ "loss": 0.1735,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.6877470355731226,
1224
+ "grad_norm": 1.21934881533331,
1225
+ "learning_rate": 7.355272391745605e-06,
1226
+ "loss": 0.201,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.691699604743083,
1231
+ "grad_norm": 1.2085810780811668,
1232
+ "learning_rate": 7.327843656590948e-06,
1233
+ "loss": 0.1997,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.6956521739130435,
1238
+ "grad_norm": 1.1706763346917641,
1239
+ "learning_rate": 7.300325188655762e-06,
1240
+ "loss": 0.175,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.6996047430830039,
1245
+ "grad_norm": 1.3103080637398228,
1246
+ "learning_rate": 7.2727180487108725e-06,
1247
+ "loss": 0.2316,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.7035573122529645,
1252
+ "grad_norm": 1.2414175503064024,
1253
+ "learning_rate": 7.245023300945203e-06,
1254
+ "loss": 0.2086,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7075098814229249,
1259
+ "grad_norm": 1.1028313396028102,
1260
+ "learning_rate": 7.217242012924747e-06,
1261
+ "loss": 0.1614,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.7114624505928854,
1266
+ "grad_norm": 1.2545708120381063,
1267
+ "learning_rate": 7.189375255551413e-06,
1268
+ "loss": 0.2129,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.7154150197628458,
1273
+ "grad_norm": 1.2208082871634096,
1274
+ "learning_rate": 7.161424103021752e-06,
1275
+ "loss": 0.186,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.7193675889328063,
1280
+ "grad_norm": 1.1856323959588346,
1281
+ "learning_rate": 7.133389632785543e-06,
1282
+ "loss": 0.18,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.7233201581027668,
1287
+ "grad_norm": 1.0491684795158043,
1288
+ "learning_rate": 7.1052729255042645e-06,
1289
+ "loss": 0.1738,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.7272727272727273,
1294
+ "grad_norm": 1.1602063012667307,
1295
+ "learning_rate": 7.0770750650094335e-06,
1296
+ "loss": 0.1888,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.7312252964426877,
1301
+ "grad_norm": 1.168233348357676,
1302
+ "learning_rate": 7.048797138260829e-06,
1303
+ "loss": 0.1938,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.7351778656126482,
1308
+ "grad_norm": 1.0998419207012584,
1309
+ "learning_rate": 7.020440235304593e-06,
1310
+ "loss": 0.1541,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.7391304347826086,
1315
+ "grad_norm": 1.2094474362406284,
1316
+ "learning_rate": 6.9920054492312086e-06,
1317
+ "loss": 0.1863,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.7430830039525692,
1322
+ "grad_norm": 1.1862926984636035,
1323
+ "learning_rate": 6.963493876133367e-06,
1324
+ "loss": 0.1991,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.7470355731225297,
1329
+ "grad_norm": 1.309657217121461,
1330
+ "learning_rate": 6.934906615063716e-06,
1331
+ "loss": 0.2202,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.7509881422924901,
1336
+ "grad_norm": 1.1164109935733424,
1337
+ "learning_rate": 6.90624476799249e-06,
1338
+ "loss": 0.1755,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.7549407114624506,
1343
+ "grad_norm": 1.0725104657393945,
1344
+ "learning_rate": 6.8775094397650375e-06,
1345
+ "loss": 0.1669,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.758893280632411,
1350
+ "grad_norm": 1.2352816410215464,
1351
+ "learning_rate": 6.8487017380592266e-06,
1352
+ "loss": 0.1962,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.7628458498023716,
1357
+ "grad_norm": 1.145478161105048,
1358
+ "learning_rate": 6.81982277334275e-06,
1359
+ "loss": 0.1864,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.766798418972332,
1364
+ "grad_norm": 1.2512415214036399,
1365
+ "learning_rate": 6.790873658830321e-06,
1366
+ "loss": 0.1972,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.7707509881422925,
1371
+ "grad_norm": 1.2466180949277024,
1372
+ "learning_rate": 6.761855510440752e-06,
1373
+ "loss": 0.1817,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.7747035573122529,
1378
+ "grad_norm": 1.181804911384916,
1379
+ "learning_rate": 6.732769446753954e-06,
1380
+ "loss": 0.175,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.7786561264822134,
1385
+ "grad_norm": 1.2910997699602191,
1386
+ "learning_rate": 6.703616588967804e-06,
1387
+ "loss": 0.2146,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.782608695652174,
1392
+ "grad_norm": 1.2156034432115361,
1393
+ "learning_rate": 6.674398060854931e-06,
1394
+ "loss": 0.2065,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.7865612648221344,
1399
+ "grad_norm": 1.2324700294150777,
1400
+ "learning_rate": 6.645114988719401e-06,
1401
+ "loss": 0.218,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.7905138339920948,
1406
+ "grad_norm": 1.1788814940788603,
1407
+ "learning_rate": 6.615768501353297e-06,
1408
+ "loss": 0.1911,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.7944664031620553,
1413
+ "grad_norm": 1.239782727484998,
1414
+ "learning_rate": 6.5863597299932e-06,
1415
+ "loss": 0.2033,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.7984189723320159,
1420
+ "grad_norm": 1.2328166491787746,
1421
+ "learning_rate": 6.5568898082765945e-06,
1422
+ "loss": 0.1885,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.8023715415019763,
1427
+ "grad_norm": 1.2257569520585552,
1428
+ "learning_rate": 6.527359872198166e-06,
1429
+ "loss": 0.2087,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.8063241106719368,
1434
+ "grad_norm": 1.090893060994598,
1435
+ "learning_rate": 6.497771060066008e-06,
1436
+ "loss": 0.1673,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.8102766798418972,
1441
+ "grad_norm": 1.262115835491651,
1442
+ "learning_rate": 6.468124512457743e-06,
1443
+ "loss": 0.2173,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.8142292490118577,
1448
+ "grad_norm": 1.1404830620435313,
1449
+ "learning_rate": 6.4384213721765565e-06,
1450
+ "loss": 0.1821,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.8181818181818182,
1455
+ "grad_norm": 1.0789980915654802,
1456
+ "learning_rate": 6.408662784207149e-06,
1457
+ "loss": 0.1809,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.8221343873517787,
1462
+ "grad_norm": 1.1275632208098325,
1463
+ "learning_rate": 6.378849895671594e-06,
1464
+ "loss": 0.1807,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.8260869565217391,
1469
+ "grad_norm": 1.1869280328722958,
1470
+ "learning_rate": 6.348983855785122e-06,
1471
+ "loss": 0.193,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.8300395256916996,
1476
+ "grad_norm": 1.1369831660790293,
1477
+ "learning_rate": 6.3190658158118205e-06,
1478
+ "loss": 0.1736,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.83399209486166,
1483
+ "grad_norm": 1.099689140622585,
1484
+ "learning_rate": 6.289096929020254e-06,
1485
+ "loss": 0.1737,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.8379446640316206,
1490
+ "grad_norm": 1.1149596155598573,
1491
+ "learning_rate": 6.25907835063901e-06,
1492
+ "loss": 0.185,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.841897233201581,
1497
+ "grad_norm": 1.2181136196244295,
1498
+ "learning_rate": 6.229011237812172e-06,
1499
+ "loss": 0.2183,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.8458498023715415,
1504
+ "grad_norm": 1.1288870761802783,
1505
+ "learning_rate": 6.1988967495547016e-06,
1506
+ "loss": 0.1705,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.849802371541502,
1511
+ "grad_norm": 1.2184909621033004,
1512
+ "learning_rate": 6.168736046707777e-06,
1513
+ "loss": 0.2087,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.8537549407114624,
1518
+ "grad_norm": 1.0707635750160447,
1519
+ "learning_rate": 6.138530291894033e-06,
1520
+ "loss": 0.1599,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.857707509881423,
1525
+ "grad_norm": 1.15244187620798,
1526
+ "learning_rate": 6.108280649472751e-06,
1527
+ "loss": 0.1977,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.8616600790513834,
1532
+ "grad_norm": 1.140414407474285,
1533
+ "learning_rate": 6.0779882854949745e-06,
1534
+ "loss": 0.1916,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.8656126482213439,
1539
+ "grad_norm": 1.168184854563085,
1540
+ "learning_rate": 6.047654367658563e-06,
1541
+ "loss": 0.1877,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.8695652173913043,
1546
+ "grad_norm": 1.095382559762059,
1547
+ "learning_rate": 6.0172800652631706e-06,
1548
+ "loss": 0.1941,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.8735177865612648,
1553
+ "grad_norm": 1.170558717112789,
1554
+ "learning_rate": 5.986866549165185e-06,
1555
+ "loss": 0.1841,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.8774703557312253,
1560
+ "grad_norm": 1.1273692690940986,
1561
+ "learning_rate": 5.9564149917325845e-06,
1562
+ "loss": 0.1776,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.8814229249011858,
1567
+ "grad_norm": 1.1615247705497285,
1568
+ "learning_rate": 5.925926566799754e-06,
1569
+ "loss": 0.1923,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.8853754940711462,
1574
+ "grad_norm": 1.1310915029362631,
1575
+ "learning_rate": 5.895402449622226e-06,
1576
+ "loss": 0.1772,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.8893280632411067,
1581
+ "grad_norm": 1.168875863428828,
1582
+ "learning_rate": 5.864843816831388e-06,
1583
+ "loss": 0.1844,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.8932806324110671,
1588
+ "grad_norm": 1.1674668972919495,
1589
+ "learning_rate": 5.8342518463891195e-06,
1590
+ "loss": 0.1632,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.8972332015810277,
1595
+ "grad_norm": 1.2880944650610078,
1596
+ "learning_rate": 5.803627717542386e-06,
1597
+ "loss": 0.1961,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.9011857707509882,
1602
+ "grad_norm": 1.224311023303702,
1603
+ "learning_rate": 5.7729726107777855e-06,
1604
+ "loss": 0.1884,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.9051383399209486,
1609
+ "grad_norm": 1.1555445601349188,
1610
+ "learning_rate": 5.742287707776034e-06,
1611
+ "loss": 0.1746,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.9090909090909091,
1616
+ "grad_norm": 1.137507280031818,
1617
+ "learning_rate": 5.711574191366427e-06,
1618
+ "loss": 0.1767,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.9130434782608695,
1623
+ "grad_norm": 1.1300350500871745,
1624
+ "learning_rate": 5.680833245481234e-06,
1625
+ "loss": 0.1748,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.9169960474308301,
1630
+ "grad_norm": 1.061749424236297,
1631
+ "learning_rate": 5.650066055110067e-06,
1632
+ "loss": 0.1682,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.9209486166007905,
1637
+ "grad_norm": 1.270168772191801,
1638
+ "learning_rate": 5.6192738062542e-06,
1639
+ "loss": 0.1883,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.924901185770751,
1644
+ "grad_norm": 1.0546305674656924,
1645
+ "learning_rate": 5.588457685880851e-06,
1646
+ "loss": 0.1634,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.9288537549407114,
1651
+ "grad_norm": 1.1513270673921783,
1652
+ "learning_rate": 5.557618881877428e-06,
1653
+ "loss": 0.1745,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.932806324110672,
1658
+ "grad_norm": 1.4466685740671457,
1659
+ "learning_rate": 5.526758583005736e-06,
1660
+ "loss": 0.2153,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.9367588932806324,
1665
+ "grad_norm": 1.2211664220988006,
1666
+ "learning_rate": 5.495877978856159e-06,
1667
+ "loss": 0.1962,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.9407114624505929,
1672
+ "grad_norm": 1.1382037688163558,
1673
+ "learning_rate": 5.464978259801797e-06,
1674
+ "loss": 0.1765,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.9446640316205533,
1679
+ "grad_norm": 1.1600221011599767,
1680
+ "learning_rate": 5.4340606169525915e-06,
1681
+ "loss": 0.1948,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.9486166007905138,
1686
+ "grad_norm": 1.2329095686972222,
1687
+ "learning_rate": 5.40312624210939e-06,
1688
+ "loss": 0.1958,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.9525691699604744,
1693
+ "grad_norm": 1.1077759614799594,
1694
+ "learning_rate": 5.372176327718029e-06,
1695
+ "loss": 0.1772,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.9565217391304348,
1700
+ "grad_norm": 1.3525530316416365,
1701
+ "learning_rate": 5.341212066823356e-06,
1702
+ "loss": 0.2068,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.9604743083003953,
1707
+ "grad_norm": 1.1641895345672653,
1708
+ "learning_rate": 5.3102346530232365e-06,
1709
+ "loss": 0.1983,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.9644268774703557,
1714
+ "grad_norm": 1.210471873881558,
1715
+ "learning_rate": 5.2792452804225535e-06,
1716
+ "loss": 0.203,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.9683794466403162,
1721
+ "grad_norm": 1.1895101061042292,
1722
+ "learning_rate": 5.248245143587172e-06,
1723
+ "loss": 0.1838,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.9723320158102767,
1728
+ "grad_norm": 1.132321900931639,
1729
+ "learning_rate": 5.2172354374978905e-06,
1730
+ "loss": 0.1843,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.9762845849802372,
1735
+ "grad_norm": 1.2024875975928633,
1736
+ "learning_rate": 5.186217357504382e-06,
1737
+ "loss": 0.1971,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.9802371541501976,
1742
+ "grad_norm": 1.1385111787681224,
1743
+ "learning_rate": 5.155192099279113e-06,
1744
+ "loss": 0.1581,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.9841897233201581,
1749
+ "grad_norm": 1.1812364752105893,
1750
+ "learning_rate": 5.124160858771252e-06,
1751
+ "loss": 0.1868,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.9881422924901185,
1756
+ "grad_norm": 1.0663746142171262,
1757
+ "learning_rate": 5.093124832160569e-06,
1758
+ "loss": 0.1702,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.9920948616600791,
1763
+ "grad_norm": 1.0637107177598129,
1764
+ "learning_rate": 5.06208521581133e-06,
1765
+ "loss": 0.1758,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.9960474308300395,
1770
+ "grad_norm": 1.082027772728129,
1771
+ "learning_rate": 5.0310432062261764e-06,
1772
+ "loss": 0.1718,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.0,
1777
+ "grad_norm": 1.2004136292445025,
1778
+ "learning_rate": 5e-06,
1779
+ "loss": 0.18,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.0039525691699605,
1784
+ "grad_norm": 1.1438358979908518,
1785
+ "learning_rate": 4.968956793773825e-06,
1786
+ "loss": 0.128,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.007905138339921,
1791
+ "grad_norm": 1.0815724819973256,
1792
+ "learning_rate": 4.9379147841886715e-06,
1793
+ "loss": 0.1374,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.0118577075098814,
1798
+ "grad_norm": 0.9971041298616835,
1799
+ "learning_rate": 4.906875167839433e-06,
1800
+ "loss": 0.1295,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.0158102766798418,
1805
+ "grad_norm": 1.0834575346736253,
1806
+ "learning_rate": 4.875839141228751e-06,
1807
+ "loss": 0.1435,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.0197628458498025,
1812
+ "grad_norm": 1.068216857230524,
1813
+ "learning_rate": 4.844807900720888e-06,
1814
+ "loss": 0.1369,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.023715415019763,
1819
+ "grad_norm": 1.1436718795229075,
1820
+ "learning_rate": 4.813782642495618e-06,
1821
+ "loss": 0.1299,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.0276679841897234,
1826
+ "grad_norm": 1.2041205262898764,
1827
+ "learning_rate": 4.78276456250211e-06,
1828
+ "loss": 0.1393,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.0316205533596838,
1833
+ "grad_norm": 1.3153176210311313,
1834
+ "learning_rate": 4.75175485641283e-06,
1835
+ "loss": 0.1587,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.0355731225296443,
1840
+ "grad_norm": 1.2818237661945875,
1841
+ "learning_rate": 4.720754719577448e-06,
1842
+ "loss": 0.1417,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.0395256916996047,
1847
+ "grad_norm": 1.346590041013075,
1848
+ "learning_rate": 4.689765346976765e-06,
1849
+ "loss": 0.1414,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.0434782608695652,
1854
+ "grad_norm": 1.396103108426267,
1855
+ "learning_rate": 4.6587879331766465e-06,
1856
+ "loss": 0.1541,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.0474308300395256,
1861
+ "grad_norm": 1.3369506628795504,
1862
+ "learning_rate": 4.627823672281972e-06,
1863
+ "loss": 0.1566,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.051383399209486,
1868
+ "grad_norm": 1.2097827541662982,
1869
+ "learning_rate": 4.596873757890612e-06,
1870
+ "loss": 0.1381,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.0553359683794465,
1875
+ "grad_norm": 1.1170762868644442,
1876
+ "learning_rate": 4.565939383047411e-06,
1877
+ "loss": 0.1135,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.0592885375494072,
1882
+ "grad_norm": 1.2233155007588437,
1883
+ "learning_rate": 4.535021740198202e-06,
1884
+ "loss": 0.1609,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.0632411067193677,
1889
+ "grad_norm": 1.2914900494723907,
1890
+ "learning_rate": 4.504122021143842e-06,
1891
+ "loss": 0.1454,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.0671936758893281,
1896
+ "grad_norm": 1.0833968374959027,
1897
+ "learning_rate": 4.473241416994265e-06,
1898
+ "loss": 0.1374,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.0711462450592886,
1903
+ "grad_norm": 1.130910587654628,
1904
+ "learning_rate": 4.442381118122573e-06,
1905
+ "loss": 0.1249,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.075098814229249,
1910
+ "grad_norm": 1.0290406864536354,
1911
+ "learning_rate": 4.41154231411915e-06,
1912
+ "loss": 0.1179,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.0790513833992095,
1917
+ "grad_norm": 1.1351038290482456,
1918
+ "learning_rate": 4.3807261937458005e-06,
1919
+ "loss": 0.1446,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.08300395256917,
1924
+ "grad_norm": 0.9979191858289315,
1925
+ "learning_rate": 4.349933944889934e-06,
1926
+ "loss": 0.1085,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.0869565217391304,
1931
+ "grad_norm": 1.0703887978514581,
1932
+ "learning_rate": 4.319166754518768e-06,
1933
+ "loss": 0.1277,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.0909090909090908,
1938
+ "grad_norm": 1.1475934247053179,
1939
+ "learning_rate": 4.2884258086335755e-06,
1940
+ "loss": 0.1394,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.0948616600790513,
1945
+ "grad_norm": 1.1836305673827001,
1946
+ "learning_rate": 4.257712292223967e-06,
1947
+ "loss": 0.1342,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.098814229249012,
1952
+ "grad_norm": 1.2046134166270397,
1953
+ "learning_rate": 4.227027389222215e-06,
1954
+ "loss": 0.1344,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.1027667984189724,
1959
+ "grad_norm": 1.035753316225185,
1960
+ "learning_rate": 4.196372282457614e-06,
1961
+ "loss": 0.1127,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.1067193675889329,
1966
+ "grad_norm": 1.1282169817707273,
1967
+ "learning_rate": 4.165748153610881e-06,
1968
+ "loss": 0.1293,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.1106719367588933,
1973
+ "grad_norm": 1.1372474070307015,
1974
+ "learning_rate": 4.1351561831686136e-06,
1975
+ "loss": 0.1332,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.1146245059288538,
1980
+ "grad_norm": 1.1594526273221435,
1981
+ "learning_rate": 4.104597550377776e-06,
1982
+ "loss": 0.1263,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.1185770750988142,
1987
+ "grad_norm": 1.15152490259451,
1988
+ "learning_rate": 4.074073433200249e-06,
1989
+ "loss": 0.1285,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.1225296442687747,
1994
+ "grad_norm": 1.1540429682296736,
1995
+ "learning_rate": 4.043585008267418e-06,
1996
+ "loss": 0.118,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.1264822134387351,
2001
+ "grad_norm": 1.2879322008831273,
2002
+ "learning_rate": 4.013133450834818e-06,
2003
+ "loss": 0.1532,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.1304347826086956,
2008
+ "grad_norm": 1.021378919711874,
2009
+ "learning_rate": 3.982719934736832e-06,
2010
+ "loss": 0.0988,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.1343873517786562,
2015
+ "grad_norm": 1.1026842967832002,
2016
+ "learning_rate": 3.95234563234144e-06,
2017
+ "loss": 0.1148,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.1383399209486167,
2022
+ "grad_norm": 1.1221443001758493,
2023
+ "learning_rate": 3.9220117145050254e-06,
2024
+ "loss": 0.1346,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.1422924901185771,
2029
+ "grad_norm": 1.179825748135588,
2030
+ "learning_rate": 3.89171935052725e-06,
2031
+ "loss": 0.132,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.1462450592885376,
2036
+ "grad_norm": 1.1145447568885478,
2037
+ "learning_rate": 3.861469708105969e-06,
2038
+ "loss": 0.1262,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.150197628458498,
2043
+ "grad_norm": 1.1805243512710089,
2044
+ "learning_rate": 3.831263953292225e-06,
2045
+ "loss": 0.1464,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.1541501976284585,
2050
+ "grad_norm": 1.1752099012387707,
2051
+ "learning_rate": 3.8011032504453e-06,
2052
+ "loss": 0.1303,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.158102766798419,
2057
+ "grad_norm": 1.1724153479966961,
2058
+ "learning_rate": 3.7709887621878305e-06,
2059
+ "loss": 0.1237,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.1620553359683794,
2064
+ "grad_norm": 1.1312088107686393,
2065
+ "learning_rate": 3.740921649360991e-06,
2066
+ "loss": 0.1329,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.1660079051383399,
2071
+ "grad_norm": 1.2140114398756852,
2072
+ "learning_rate": 3.710903070979749e-06,
2073
+ "loss": 0.146,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.1699604743083003,
2078
+ "grad_norm": 1.177316021638641,
2079
+ "learning_rate": 3.680934184188182e-06,
2080
+ "loss": 0.1369,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.1739130434782608,
2085
+ "grad_norm": 1.0958487706218825,
2086
+ "learning_rate": 3.6510161442148783e-06,
2087
+ "loss": 0.1224,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 1.1778656126482214,
2092
+ "grad_norm": 1.0391815446060055,
2093
+ "learning_rate": 3.621150104328407e-06,
2094
+ "loss": 0.1248,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 1.1818181818181819,
2099
+ "grad_norm": 1.0701427010593552,
2100
+ "learning_rate": 3.5913372157928515e-06,
2101
+ "loss": 0.1224,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 1.1857707509881423,
2106
+ "grad_norm": 1.1848224795154656,
2107
+ "learning_rate": 3.5615786278234443e-06,
2108
+ "loss": 0.1491,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 1.1897233201581028,
2113
+ "grad_norm": 1.1762535991099512,
2114
+ "learning_rate": 3.5318754875422588e-06,
2115
+ "loss": 0.1347,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 1.1936758893280632,
2120
+ "grad_norm": 1.0206443853029172,
2121
+ "learning_rate": 3.5022289399339933e-06,
2122
+ "loss": 0.1022,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 1.1976284584980237,
2127
+ "grad_norm": 1.0357149112196293,
2128
+ "learning_rate": 3.4726401278018353e-06,
2129
+ "loss": 0.1134,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 1.2015810276679841,
2134
+ "grad_norm": 1.156607546118926,
2135
+ "learning_rate": 3.443110191723407e-06,
2136
+ "loss": 0.127,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 1.2055335968379446,
2141
+ "grad_norm": 1.1452610773145862,
2142
+ "learning_rate": 3.4136402700068034e-06,
2143
+ "loss": 0.1242,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 1.2094861660079053,
2148
+ "grad_norm": 1.137660713683979,
2149
+ "learning_rate": 3.384231498646706e-06,
2150
+ "loss": 0.1302,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 1.2134387351778657,
2155
+ "grad_norm": 1.3751968299311201,
2156
+ "learning_rate": 3.3548850112805985e-06,
2157
+ "loss": 0.1345,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 1.2173913043478262,
2162
+ "grad_norm": 1.1820163169421647,
2163
+ "learning_rate": 3.3256019391450696e-06,
2164
+ "loss": 0.124,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 1.2213438735177866,
2169
+ "grad_norm": 1.254836523224082,
2170
+ "learning_rate": 3.296383411032198e-06,
2171
+ "loss": 0.1592,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 1.225296442687747,
2176
+ "grad_norm": 1.2092831479934754,
2177
+ "learning_rate": 3.267230553246047e-06,
2178
+ "loss": 0.1374,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 1.2292490118577075,
2183
+ "grad_norm": 1.3298953359466184,
2184
+ "learning_rate": 3.2381444895592483e-06,
2185
+ "loss": 0.1599,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 1.233201581027668,
2190
+ "grad_norm": 1.15714090782168,
2191
+ "learning_rate": 3.209126341169681e-06,
2192
+ "loss": 0.1178,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 1.2371541501976284,
2197
+ "grad_norm": 1.1321197195627186,
2198
+ "learning_rate": 3.180177226657251e-06,
2199
+ "loss": 0.1324,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 1.2411067193675889,
2204
+ "grad_norm": 1.1427780558349572,
2205
+ "learning_rate": 3.151298261940775e-06,
2206
+ "loss": 0.1354,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 1.2450592885375493,
2211
+ "grad_norm": 1.1792578676088221,
2212
+ "learning_rate": 3.122490560234964e-06,
2213
+ "loss": 0.1316,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 1.2490118577075098,
2218
+ "grad_norm": 1.173771729377104,
2219
+ "learning_rate": 3.0937552320075116e-06,
2220
+ "loss": 0.1237,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 1.2529644268774702,
2225
+ "grad_norm": 1.2142503247487184,
2226
+ "learning_rate": 3.065093384936285e-06,
2227
+ "loss": 0.1385,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 1.256916996047431,
2232
+ "grad_norm": 1.2169127173091283,
2233
+ "learning_rate": 3.0365061238666336e-06,
2234
+ "loss": 0.1442,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 1.2608695652173914,
2239
+ "grad_norm": 1.3055869261396447,
2240
+ "learning_rate": 3.007994550768793e-06,
2241
+ "loss": 0.136,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 1.2648221343873518,
2246
+ "grad_norm": 1.2043193143210125,
2247
+ "learning_rate": 2.979559764695409e-06,
2248
+ "loss": 0.1447,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 1.2687747035573123,
2253
+ "grad_norm": 1.1233412613298097,
2254
+ "learning_rate": 2.951202861739173e-06,
2255
+ "loss": 0.1282,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 1.2727272727272727,
2260
+ "grad_norm": 1.0606810788891305,
2261
+ "learning_rate": 2.9229249349905686e-06,
2262
+ "loss": 0.1212,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 1.2766798418972332,
2267
+ "grad_norm": 1.0460756961226252,
2268
+ "learning_rate": 2.8947270744957385e-06,
2269
+ "loss": 0.1173,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 1.2806324110671936,
2274
+ "grad_norm": 1.1897624975044134,
2275
+ "learning_rate": 2.8666103672144597e-06,
2276
+ "loss": 0.1407,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 1.2845849802371543,
2281
+ "grad_norm": 1.1942264596916479,
2282
+ "learning_rate": 2.8385758969782507e-06,
2283
+ "loss": 0.1286,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 1.2885375494071147,
2288
+ "grad_norm": 1.1341245622744474,
2289
+ "learning_rate": 2.810624744448588e-06,
2290
+ "loss": 0.128,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 1.2924901185770752,
2295
+ "grad_norm": 1.165964008709128,
2296
+ "learning_rate": 2.7827579870752542e-06,
2297
+ "loss": 0.136,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 1.2964426877470356,
2302
+ "grad_norm": 1.1358629236681395,
2303
+ "learning_rate": 2.7549766990547973e-06,
2304
+ "loss": 0.1238,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 1.300395256916996,
2309
+ "grad_norm": 1.144473644830131,
2310
+ "learning_rate": 2.727281951289128e-06,
2311
+ "loss": 0.1333,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 1.3043478260869565,
2316
+ "grad_norm": 1.1761434599454856,
2317
+ "learning_rate": 2.6996748113442397e-06,
2318
+ "loss": 0.1223,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 1.308300395256917,
2323
+ "grad_norm": 1.1788613585620644,
2324
+ "learning_rate": 2.672156343409053e-06,
2325
+ "loss": 0.1349,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 1.3122529644268774,
2330
+ "grad_norm": 1.1047408820558797,
2331
+ "learning_rate": 2.644727608254396e-06,
2332
+ "loss": 0.1215,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 1.316205533596838,
2337
+ "grad_norm": 1.1915355492120698,
2338
+ "learning_rate": 2.6173896631921134e-06,
2339
+ "loss": 0.1405,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 1.3201581027667983,
2344
+ "grad_norm": 1.1396002338772575,
2345
+ "learning_rate": 2.590143562034312e-06,
2346
+ "loss": 0.1297,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 1.3241106719367588,
2351
+ "grad_norm": 0.9928956463128177,
2352
+ "learning_rate": 2.5629903550527343e-06,
2353
+ "loss": 0.1032,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 1.3280632411067192,
2358
+ "grad_norm": 1.1497535091692899,
2359
+ "learning_rate": 2.535931088938274e-06,
2360
+ "loss": 0.1342,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 1.33201581027668,
2365
+ "grad_norm": 1.1209952848082338,
2366
+ "learning_rate": 2.5089668067606365e-06,
2367
+ "loss": 0.1185,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 1.3359683794466404,
2372
+ "grad_norm": 1.0839706555945572,
2373
+ "learning_rate": 2.4820985479281184e-06,
2374
+ "loss": 0.1139,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 1.3399209486166008,
2379
+ "grad_norm": 1.1440761155145645,
2380
+ "learning_rate": 2.45532734814755e-06,
2381
+ "loss": 0.134,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 1.3438735177865613,
2386
+ "grad_norm": 1.082616882918915,
2387
+ "learning_rate": 2.4286542393843665e-06,
2388
+ "loss": 0.1281,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 1.3478260869565217,
2393
+ "grad_norm": 1.17500675790559,
2394
+ "learning_rate": 2.4020802498228333e-06,
2395
+ "loss": 0.1432,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 1.3517786561264822,
2400
+ "grad_norm": 1.1182114019109513,
2401
+ "learning_rate": 2.3756064038264033e-06,
2402
+ "loss": 0.134,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 1.3557312252964426,
2407
+ "grad_norm": 1.1566712806713801,
2408
+ "learning_rate": 2.3492337218982396e-06,
2409
+ "loss": 0.1285,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 1.359683794466403,
2414
+ "grad_norm": 1.0164245424014764,
2415
+ "learning_rate": 2.3229632206418727e-06,
2416
+ "loss": 0.1055,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 1.3636363636363638,
2421
+ "grad_norm": 1.1202273103032814,
2422
+ "learning_rate": 2.296795912722014e-06,
2423
+ "loss": 0.1164,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 1.3675889328063242,
2428
+ "grad_norm": 1.2025482829810825,
2429
+ "learning_rate": 2.270732806825517e-06,
2430
+ "loss": 0.1413,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 1.3715415019762847,
2435
+ "grad_norm": 1.1369886395664646,
2436
+ "learning_rate": 2.244774907622504e-06,
2437
+ "loss": 0.1312,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 1.3754940711462451,
2442
+ "grad_norm": 1.1150013437618065,
2443
+ "learning_rate": 2.2189232157276247e-06,
2444
+ "loss": 0.1379,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 1.3794466403162056,
2449
+ "grad_norm": 1.086272977870767,
2450
+ "learning_rate": 2.1931787276614968e-06,
2451
+ "loss": 0.1178,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 1.383399209486166,
2456
+ "grad_norm": 1.1640308203458913,
2457
+ "learning_rate": 2.167542435812286e-06,
2458
+ "loss": 0.1356,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 1.3873517786561265,
2463
+ "grad_norm": 1.1121490307629227,
2464
+ "learning_rate": 2.142015328397454e-06,
2465
+ "loss": 0.1237,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 1.391304347826087,
2470
+ "grad_norm": 1.1574528436812335,
2471
+ "learning_rate": 2.1165983894256647e-06,
2472
+ "loss": 0.1255,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 1.3952569169960474,
2477
+ "grad_norm": 1.361980674009939,
2478
+ "learning_rate": 2.0912925986588547e-06,
2479
+ "loss": 0.1389,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 1.3992094861660078,
2484
+ "grad_norm": 1.051150691395027,
2485
+ "learning_rate": 2.0660989315744624e-06,
2486
+ "loss": 0.1168,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 1.4031620553359683,
2491
+ "grad_norm": 1.1382181091816,
2492
+ "learning_rate": 2.0410183593278287e-06,
2493
+ "loss": 0.1367,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 1.4071146245059287,
2498
+ "grad_norm": 1.127194102052322,
2499
+ "learning_rate": 2.016051848714758e-06,
2500
+ "loss": 0.131,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 1.4110671936758894,
2505
+ "grad_norm": 1.3646197569162608,
2506
+ "learning_rate": 1.991200362134258e-06,
2507
+ "loss": 0.1668,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 1.4150197628458498,
2512
+ "grad_norm": 1.179231150635698,
2513
+ "learning_rate": 1.9664648575514316e-06,
2514
+ "loss": 0.1309,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 1.4189723320158103,
2519
+ "grad_norm": 1.1478284079295227,
2520
+ "learning_rate": 1.9418462884605555e-06,
2521
+ "loss": 0.1407,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 1.4229249011857708,
2526
+ "grad_norm": 0.966600715786351,
2527
+ "learning_rate": 1.9173456038483244e-06,
2528
+ "loss": 0.0989,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 1.4268774703557312,
2533
+ "grad_norm": 1.089318761705495,
2534
+ "learning_rate": 1.8929637481572715e-06,
2535
+ "loss": 0.1233,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 1.4308300395256917,
2540
+ "grad_norm": 1.1956595892466026,
2541
+ "learning_rate": 1.8687016612493542e-06,
2542
+ "loss": 0.1266,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 1.434782608695652,
2547
+ "grad_norm": 1.199815800783593,
2548
+ "learning_rate": 1.8445602783697375e-06,
2549
+ "loss": 0.1383,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 1.4387351778656128,
2554
+ "grad_norm": 1.0596031990819328,
2555
+ "learning_rate": 1.8205405301107343e-06,
2556
+ "loss": 0.1183,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 1.4426877470355732,
2561
+ "grad_norm": 1.1937639817958505,
2562
+ "learning_rate": 1.7966433423759327e-06,
2563
+ "loss": 0.1452,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 1.4466403162055337,
2568
+ "grad_norm": 1.0906265845240057,
2569
+ "learning_rate": 1.772869636344512e-06,
2570
+ "loss": 0.111,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 1.4505928853754941,
2575
+ "grad_norm": 1.2231633736793504,
2576
+ "learning_rate": 1.7492203284357245e-06,
2577
+ "loss": 0.1362,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 1.4545454545454546,
2582
+ "grad_norm": 1.0619383271235998,
2583
+ "learning_rate": 1.7256963302735752e-06,
2584
+ "loss": 0.1202,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 1.458498023715415,
2589
+ "grad_norm": 1.0900241430901978,
2590
+ "learning_rate": 1.702298548651678e-06,
2591
+ "loss": 0.1162,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 1.4624505928853755,
2596
+ "grad_norm": 1.1512284006660594,
2597
+ "learning_rate": 1.6790278854983033e-06,
2598
+ "loss": 0.1322,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 1.466403162055336,
2603
+ "grad_norm": 1.1329200558876649,
2604
+ "learning_rate": 1.6558852378416113e-06,
2605
+ "loss": 0.1362,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 1.4703557312252964,
2610
+ "grad_norm": 1.0410869979854105,
2611
+ "learning_rate": 1.6328714977750698e-06,
2612
+ "loss": 0.1239,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 1.4743083003952568,
2617
+ "grad_norm": 1.2545052203915814,
2618
+ "learning_rate": 1.6099875524230707e-06,
2619
+ "loss": 0.1476,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 1.4782608695652173,
2624
+ "grad_norm": 1.2003692839751088,
2625
+ "learning_rate": 1.5872342839067305e-06,
2626
+ "loss": 0.1381,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 1.4822134387351777,
2631
+ "grad_norm": 1.1739098836348705,
2632
+ "learning_rate": 1.5646125693098863e-06,
2633
+ "loss": 0.1295,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 1.4861660079051384,
2638
+ "grad_norm": 1.1535530949440382,
2639
+ "learning_rate": 1.542123280645292e-06,
2640
+ "loss": 0.1234,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 1.4901185770750989,
2645
+ "grad_norm": 1.1168208484387032,
2646
+ "learning_rate": 1.519767284820996e-06,
2647
+ "loss": 0.1152,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 1.4940711462450593,
2652
+ "grad_norm": 1.0340813124452886,
2653
+ "learning_rate": 1.4975454436069292e-06,
2654
+ "loss": 0.1114,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 1.4980237154150198,
2659
+ "grad_norm": 1.117157676559404,
2660
+ "learning_rate": 1.4754586136016841e-06,
2661
+ "loss": 0.127,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 1.5019762845849802,
2666
+ "grad_norm": 1.1411823176863023,
2667
+ "learning_rate": 1.4535076461994974e-06,
2668
+ "loss": 0.1243,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 1.5059288537549407,
2673
+ "grad_norm": 1.0074369184939824,
2674
+ "learning_rate": 1.431693387557424e-06,
2675
+ "loss": 0.1007,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 1.5098814229249014,
2680
+ "grad_norm": 1.1674952879116636,
2681
+ "learning_rate": 1.4100166785627301e-06,
2682
+ "loss": 0.1201,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 1.5138339920948618,
2687
+ "grad_norm": 1.0610397050784564,
2688
+ "learning_rate": 1.3884783548004704e-06,
2689
+ "loss": 0.1208,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 1.5177865612648223,
2694
+ "grad_norm": 1.1703142856070294,
2695
+ "learning_rate": 1.3670792465212828e-06,
2696
+ "loss": 0.131,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 1.5217391304347827,
2701
+ "grad_norm": 1.24844816636085,
2702
+ "learning_rate": 1.3458201786093795e-06,
2703
+ "loss": 0.1426,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 1.5256916996047432,
2708
+ "grad_norm": 1.0289708643260822,
2709
+ "learning_rate": 1.3247019705507596e-06,
2710
+ "loss": 0.107,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 1.5296442687747036,
2715
+ "grad_norm": 1.0411982481948332,
2716
+ "learning_rate": 1.3037254364016068e-06,
2717
+ "loss": 0.1106,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 1.533596837944664,
2722
+ "grad_norm": 1.0887512215886415,
2723
+ "learning_rate": 1.2828913847569185e-06,
2724
+ "loss": 0.126,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 1.5375494071146245,
2729
+ "grad_norm": 1.1038917846986824,
2730
+ "learning_rate": 1.2622006187193348e-06,
2731
+ "loss": 0.1169,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 1.541501976284585,
2736
+ "grad_norm": 1.1650275815326414,
2737
+ "learning_rate": 1.2416539358681772e-06,
2738
+ "loss": 0.1243,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 1.5454545454545454,
2743
+ "grad_norm": 1.126326384634314,
2744
+ "learning_rate": 1.2212521282287093e-06,
2745
+ "loss": 0.129,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 1.5494071146245059,
2750
+ "grad_norm": 1.129180074421009,
2751
+ "learning_rate": 1.2009959822416012e-06,
2752
+ "loss": 0.1382,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 1.5533596837944663,
2757
+ "grad_norm": 1.164913976767265,
2758
+ "learning_rate": 1.1808862787326176e-06,
2759
+ "loss": 0.1217,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 1.5573122529644268,
2764
+ "grad_norm": 1.1842645447436517,
2765
+ "learning_rate": 1.1609237928825174e-06,
2766
+ "loss": 0.1392,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 1.5612648221343872,
2771
+ "grad_norm": 1.127758214888184,
2772
+ "learning_rate": 1.1411092941971702e-06,
2773
+ "loss": 0.1334,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 1.5652173913043477,
2778
+ "grad_norm": 1.0268028668010976,
2779
+ "learning_rate": 1.1214435464779006e-06,
2780
+ "loss": 0.1092,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 1.5691699604743083,
2785
+ "grad_norm": 1.1298748698800432,
2786
+ "learning_rate": 1.1019273077920366e-06,
2787
+ "loss": 0.1199,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 1.5731225296442688,
2792
+ "grad_norm": 1.151983299642192,
2793
+ "learning_rate": 1.0825613304436938e-06,
2794
+ "loss": 0.1214,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 1.5770750988142292,
2799
+ "grad_norm": 1.056563475272345,
2800
+ "learning_rate": 1.0633463609447753e-06,
2801
+ "loss": 0.1137,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 1.5810276679841897,
2806
+ "grad_norm": 1.0401127604187286,
2807
+ "learning_rate": 1.0442831399861903e-06,
2808
+ "loss": 0.1116,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 1.5849802371541502,
2813
+ "grad_norm": 1.137297843112467,
2814
+ "learning_rate": 1.0253724024093103e-06,
2815
+ "loss": 0.1259,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 1.5889328063241108,
2820
+ "grad_norm": 1.2731646482391143,
2821
+ "learning_rate": 1.006614877177638e-06,
2822
+ "loss": 0.1398,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 1.5928853754940713,
2827
+ "grad_norm": 1.2031755255565708,
2828
+ "learning_rate": 9.880112873487068e-07,
2829
+ "loss": 0.1435,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 1.5968379446640317,
2834
+ "grad_norm": 1.0673733506453118,
2835
+ "learning_rate": 9.695623500462114e-07,
2836
+ "loss": 0.1213,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 1.6007905138339922,
2841
+ "grad_norm": 1.1540390417696156,
2842
+ "learning_rate": 9.512687764323647e-07,
2843
+ "loss": 0.1309,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 1.6047430830039526,
2848
+ "grad_norm": 1.1719558092176683,
2849
+ "learning_rate": 9.331312716804791e-07,
2850
+ "loss": 0.1353,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 1.608695652173913,
2855
+ "grad_norm": 1.1328079202728492,
2856
+ "learning_rate": 9.151505349477901e-07,
2857
+ "loss": 0.1126,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 1.6126482213438735,
2862
+ "grad_norm": 1.1668524122475088,
2863
+ "learning_rate": 8.973272593485011e-07,
2864
+ "loss": 0.1232,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 1.616600790513834,
2869
+ "grad_norm": 1.1765999211223719,
2870
+ "learning_rate": 8.796621319270676e-07,
2871
+ "loss": 0.1381,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 1.6205533596837944,
2876
+ "grad_norm": 1.1580704897137293,
2877
+ "learning_rate": 8.621558336317132e-07,
2878
+ "loss": 0.125,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 1.6245059288537549,
2883
+ "grad_norm": 1.2221405236185294,
2884
+ "learning_rate": 8.448090392881797e-07,
2885
+ "loss": 0.1434,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 1.6284584980237153,
2890
+ "grad_norm": 1.1484711907465028,
2891
+ "learning_rate": 8.276224175737152e-07,
2892
+ "loss": 0.1341,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 1.6324110671936758,
2897
+ "grad_norm": 1.0668615052922243,
2898
+ "learning_rate": 8.105966309912966e-07,
2899
+ "loss": 0.119,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 1.6363636363636362,
2904
+ "grad_norm": 1.1708621908812695,
2905
+ "learning_rate": 7.937323358440935e-07,
2906
+ "loss": 0.1365,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 1.6403162055335967,
2911
+ "grad_norm": 1.0037003731577279,
2912
+ "learning_rate": 7.770301822101712e-07,
2913
+ "loss": 0.1056,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 1.6442687747035574,
2918
+ "grad_norm": 1.0648681490157104,
2919
+ "learning_rate": 7.604908139174255e-07,
2920
+ "loss": 0.1098,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 1.6482213438735178,
2925
+ "grad_norm": 1.1995736066849585,
2926
+ "learning_rate": 7.441148685187694e-07,
2927
+ "loss": 0.1341,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 1.6521739130434783,
2932
+ "grad_norm": 1.1848136469443982,
2933
+ "learning_rate": 7.279029772675572e-07,
2934
+ "loss": 0.1336,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 1.6561264822134387,
2939
+ "grad_norm": 1.1795612477078212,
2940
+ "learning_rate": 7.11855765093249e-07,
2941
+ "loss": 0.1379,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 1.6600790513833992,
2946
+ "grad_norm": 1.244369267153096,
2947
+ "learning_rate": 6.959738505773211e-07,
2948
+ "loss": 0.1373,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 1.6640316205533598,
2953
+ "grad_norm": 1.148156272898155,
2954
+ "learning_rate": 6.802578459294235e-07,
2955
+ "loss": 0.1274,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 1.6679841897233203,
2960
+ "grad_norm": 1.1618407598954121,
2961
+ "learning_rate": 6.647083569637797e-07,
2962
+ "loss": 0.1208,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 1.6719367588932808,
2967
+ "grad_norm": 1.1228370521334565,
2968
+ "learning_rate": 6.493259830758325e-07,
2969
+ "loss": 0.1181,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 1.6758893280632412,
2974
+ "grad_norm": 1.1659039027502425,
2975
+ "learning_rate": 6.341113172191399e-07,
2976
+ "loss": 0.1251,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 1.6798418972332017,
2981
+ "grad_norm": 1.1667891678872329,
2982
+ "learning_rate": 6.190649458825204e-07,
2983
+ "loss": 0.1373,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 1.683794466403162,
2988
+ "grad_norm": 1.1054656728972119,
2989
+ "learning_rate": 6.041874490674416e-07,
2990
+ "loss": 0.1183,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 1.6877470355731226,
2995
+ "grad_norm": 1.1318157363661536,
2996
+ "learning_rate": 5.894794002656628e-07,
2997
+ "loss": 0.1276,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 1.691699604743083,
3002
+ "grad_norm": 1.1427617467212088,
3003
+ "learning_rate": 5.749413664371312e-07,
3004
+ "loss": 0.1314,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 1.6956521739130435,
3009
+ "grad_norm": 1.123370168432176,
3010
+ "learning_rate": 5.60573907988124e-07,
3011
+ "loss": 0.1172,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 1.699604743083004,
3016
+ "grad_norm": 1.2640707026191205,
3017
+ "learning_rate": 5.463775787496484e-07,
3018
+ "loss": 0.1345,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 1.7035573122529644,
3023
+ "grad_norm": 1.2270465900901621,
3024
+ "learning_rate": 5.323529259560911e-07,
3025
+ "loss": 0.1337,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 1.7075098814229248,
3030
+ "grad_norm": 1.0714382150531283,
3031
+ "learning_rate": 5.185004902241241e-07,
3032
+ "loss": 0.1125,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 1.7114624505928853,
3037
+ "grad_norm": 1.0825327963083162,
3038
+ "learning_rate": 5.04820805531866e-07,
3039
+ "loss": 0.1059,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 1.7154150197628457,
3044
+ "grad_norm": 1.0596003222945678,
3045
+ "learning_rate": 4.91314399198296e-07,
3046
+ "loss": 0.0999,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 1.7193675889328062,
3051
+ "grad_norm": 1.1990608827420846,
3052
+ "learning_rate": 4.779817918629326e-07,
3053
+ "loss": 0.1257,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 1.7233201581027668,
3058
+ "grad_norm": 1.0887979080170394,
3059
+ "learning_rate": 4.6482349746575783e-07,
3060
+ "loss": 0.1236,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 1.7272727272727273,
3065
+ "grad_norm": 1.0412689170684666,
3066
+ "learning_rate": 4.5184002322740784e-07,
3067
+ "loss": 0.1066,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 1.7312252964426877,
3072
+ "grad_norm": 1.0802724381125226,
3073
+ "learning_rate": 4.390318696296247e-07,
3074
+ "loss": 0.1149,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 1.7351778656126482,
3079
+ "grad_norm": 1.1551936194230803,
3080
+ "learning_rate": 4.2639953039595725e-07,
3081
+ "loss": 0.135,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 1.7391304347826086,
3086
+ "grad_norm": 1.2135177448970054,
3087
+ "learning_rate": 4.139434924727359e-07,
3088
+ "loss": 0.1349,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 1.7430830039525693,
3093
+ "grad_norm": 1.0507122616854452,
3094
+ "learning_rate": 4.0166423601029735e-07,
3095
+ "loss": 0.1157,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 1.7470355731225298,
3100
+ "grad_norm": 1.1753401932840621,
3101
+ "learning_rate": 3.8956223434447936e-07,
3102
+ "loss": 0.136,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 1.7509881422924902,
3107
+ "grad_norm": 1.1404040824302084,
3108
+ "learning_rate": 3.776379539783709e-07,
3109
+ "loss": 0.1223,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 1.7549407114624507,
3114
+ "grad_norm": 1.2777386537799145,
3115
+ "learning_rate": 3.658918545643353e-07,
3116
+ "loss": 0.1485,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 1.7588932806324111,
3121
+ "grad_norm": 1.1413712412237624,
3122
+ "learning_rate": 3.543243888862841e-07,
3123
+ "loss": 0.1212,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 1.7628458498023716,
3128
+ "grad_norm": 1.0872960731651602,
3129
+ "learning_rate": 3.429360028422307e-07,
3130
+ "loss": 0.1193,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 1.766798418972332,
3135
+ "grad_norm": 1.0637737003753145,
3136
+ "learning_rate": 3.317271354270968e-07,
3137
+ "loss": 0.1133,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 1.7707509881422925,
3142
+ "grad_norm": 1.1840091720746755,
3143
+ "learning_rate": 3.2069821871579255e-07,
3144
+ "loss": 0.1333,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 1.774703557312253,
3149
+ "grad_norm": 1.1255230443713273,
3150
+ "learning_rate": 3.098496778465621e-07,
3151
+ "loss": 0.1181,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 1.7786561264822134,
3156
+ "grad_norm": 1.0775241906777941,
3157
+ "learning_rate": 2.991819310045929e-07,
3158
+ "loss": 0.1189,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 1.7826086956521738,
3163
+ "grad_norm": 1.0583221665971685,
3164
+ "learning_rate": 2.88695389405898e-07,
3165
+ "loss": 0.1103,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 1.7865612648221343,
3170
+ "grad_norm": 1.1242814725320212,
3171
+ "learning_rate": 2.783904572814622e-07,
3172
+ "loss": 0.1285,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 1.7905138339920947,
3177
+ "grad_norm": 1.1779401797110727,
3178
+ "learning_rate": 2.682675318616618e-07,
3179
+ "loss": 0.1294,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 1.7944664031620552,
3184
+ "grad_norm": 1.0859491545785036,
3185
+ "learning_rate": 2.583270033609536e-07,
3186
+ "loss": 0.1123,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 1.7984189723320159,
3191
+ "grad_norm": 1.0763948870282039,
3192
+ "learning_rate": 2.4856925496283045e-07,
3193
+ "loss": 0.1104,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 1.8023715415019763,
3198
+ "grad_norm": 1.0887108595666282,
3199
+ "learning_rate": 2.3899466280504936e-07,
3200
+ "loss": 0.1126,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 1.8063241106719368,
3205
+ "grad_norm": 1.1717149496208563,
3206
+ "learning_rate": 2.2960359596513714e-07,
3207
+ "loss": 0.1351,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 1.8102766798418972,
3212
+ "grad_norm": 1.229561030964994,
3213
+ "learning_rate": 2.203964164461597e-07,
3214
+ "loss": 0.1369,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 1.8142292490118577,
3219
+ "grad_norm": 1.1633472228135062,
3220
+ "learning_rate": 2.113734791627664e-07,
3221
+ "loss": 0.1291,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 1.8181818181818183,
3226
+ "grad_norm": 1.2035274009151151,
3227
+ "learning_rate": 2.0253513192751374e-07,
3228
+ "loss": 0.1469,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 1.8221343873517788,
3233
+ "grad_norm": 1.1836270092696015,
3234
+ "learning_rate": 1.9388171543745394e-07,
3235
+ "loss": 0.1379,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 1.8260869565217392,
3240
+ "grad_norm": 1.0758870256725546,
3241
+ "learning_rate": 1.8541356326100436e-07,
3242
+ "loss": 0.1117,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 1.8300395256916997,
3247
+ "grad_norm": 1.1793736035903457,
3248
+ "learning_rate": 1.7713100182508604e-07,
3249
+ "loss": 0.1398,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 1.8339920948616601,
3254
+ "grad_norm": 1.0801974661120426,
3255
+ "learning_rate": 1.6903435040254545e-07,
3256
+ "loss": 0.1128,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 1.8379446640316206,
3261
+ "grad_norm": 1.07339663507577,
3262
+ "learning_rate": 1.6112392109984386e-07,
3263
+ "loss": 0.1099,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 1.841897233201581,
3268
+ "grad_norm": 1.1120046775263792,
3269
+ "learning_rate": 1.5340001884502577e-07,
3270
+ "loss": 0.1262,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 1.8458498023715415,
3275
+ "grad_norm": 1.0831243721534856,
3276
+ "learning_rate": 1.4586294137596768e-07,
3277
+ "loss": 0.1193,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 1.849802371541502,
3282
+ "grad_norm": 1.0472977237699574,
3283
+ "learning_rate": 1.385129792288986e-07,
3284
+ "loss": 0.1041,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 1.8537549407114624,
3289
+ "grad_norm": 1.1482729228107225,
3290
+ "learning_rate": 1.313504157272022e-07,
3291
+ "loss": 0.1301,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 1.8577075098814229,
3296
+ "grad_norm": 1.1397420372115987,
3297
+ "learning_rate": 1.2437552697049327e-07,
3298
+ "loss": 0.1289,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 1.8616600790513833,
3303
+ "grad_norm": 1.1569650321244938,
3304
+ "learning_rate": 1.1758858182397692e-07,
3305
+ "loss": 0.1283,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 1.8656126482213438,
3310
+ "grad_norm": 1.1694788716855629,
3311
+ "learning_rate": 1.1098984190808403e-07,
3312
+ "loss": 0.1335,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 1.8695652173913042,
3317
+ "grad_norm": 1.0086960578539177,
3318
+ "learning_rate": 1.0457956158838545e-07,
3319
+ "loss": 0.0996,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 1.8735177865612647,
3324
+ "grad_norm": 1.0308075869001883,
3325
+ "learning_rate": 9.835798796578755e-08,
3326
+ "loss": 0.1153,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 1.8774703557312253,
3331
+ "grad_norm": 1.170279753009744,
3332
+ "learning_rate": 9.232536086700605e-08,
3333
+ "loss": 0.1304,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 1.8814229249011858,
3338
+ "grad_norm": 1.0870287190560486,
3339
+ "learning_rate": 8.648191283532337e-08,
3340
+ "loss": 0.1213,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 1.8853754940711462,
3345
+ "grad_norm": 1.1165962048020976,
3346
+ "learning_rate": 8.082786912162243e-08,
3347
+ "loss": 0.1161,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 1.8893280632411067,
3352
+ "grad_norm": 1.1494916541958282,
3353
+ "learning_rate": 7.536344767570536e-08,
3354
+ "loss": 0.1141,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 1.8932806324110671,
3359
+ "grad_norm": 1.0640073229737435,
3360
+ "learning_rate": 7.008885913789066e-08,
3361
+ "loss": 0.1228,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 1.8972332015810278,
3366
+ "grad_norm": 1.1870546140040668,
3367
+ "learning_rate": 6.500430683089532e-08,
3368
+ "loss": 0.1303,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 1.9011857707509883,
3373
+ "grad_norm": 1.173615256902204,
3374
+ "learning_rate": 6.010998675199554e-08,
3375
+ "loss": 0.1338,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 1.9051383399209487,
3380
+ "grad_norm": 1.1958445869792897,
3381
+ "learning_rate": 5.5406087565471054e-08,
3382
+ "loss": 0.1405,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 1.9090909090909092,
3387
+ "grad_norm": 1.1122683154170514,
3388
+ "learning_rate": 5.089279059533658e-08,
3389
+ "loss": 0.1281,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 1.9130434782608696,
3394
+ "grad_norm": 1.0958024070105987,
3395
+ "learning_rate": 4.657026981834623e-08,
3396
+ "loss": 0.12,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 1.91699604743083,
3401
+ "grad_norm": 1.1024888588089012,
3402
+ "learning_rate": 4.2438691857292215e-08,
3403
+ "loss": 0.1144,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 1.9209486166007905,
3408
+ "grad_norm": 1.123264444499075,
3409
+ "learning_rate": 3.849821597457892e-08,
3410
+ "loss": 0.1347,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 1.924901185770751,
3415
+ "grad_norm": 1.0765658056683685,
3416
+ "learning_rate": 3.474899406608501e-08,
3417
+ "loss": 0.1129,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 1.9288537549407114,
3422
+ "grad_norm": 1.148979953908725,
3423
+ "learning_rate": 3.119117065530808e-08,
3424
+ "loss": 0.123,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 1.9328063241106719,
3429
+ "grad_norm": 1.2501363554379483,
3430
+ "learning_rate": 2.7824882887793058e-08,
3431
+ "loss": 0.1538,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 1.9367588932806323,
3436
+ "grad_norm": 1.196112067372065,
3437
+ "learning_rate": 2.4650260525846404e-08,
3438
+ "loss": 0.1416,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 1.9407114624505928,
3443
+ "grad_norm": 1.1128332896345188,
3444
+ "learning_rate": 2.1667425943532884e-08,
3445
+ "loss": 0.1147,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 1.9446640316205532,
3450
+ "grad_norm": 1.1016376226716715,
3451
+ "learning_rate": 1.8876494121959908e-08,
3452
+ "loss": 0.1289,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 1.9486166007905137,
3457
+ "grad_norm": 1.135611367054567,
3458
+ "learning_rate": 1.627757264484442e-08,
3459
+ "loss": 0.1294,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 1.9525691699604744,
3464
+ "grad_norm": 1.1398251434326172,
3465
+ "learning_rate": 1.387076169436563e-08,
3466
+ "loss": 0.1262,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 1.9565217391304348,
3471
+ "grad_norm": 1.0846986101599616,
3472
+ "learning_rate": 1.1656154047303691e-08,
3473
+ "loss": 0.1126,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 1.9604743083003953,
3478
+ "grad_norm": 1.2370763808268233,
3479
+ "learning_rate": 9.633835071463094e-09,
3480
+ "loss": 0.1485,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 1.9644268774703557,
3485
+ "grad_norm": 1.1863239612132057,
3486
+ "learning_rate": 7.803882722381417e-09,
3487
+ "loss": 0.1293,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 1.9683794466403162,
3492
+ "grad_norm": 1.2282535432480546,
3493
+ "learning_rate": 6.166367540325624e-09,
3494
+ "loss": 0.1428,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 1.9723320158102768,
3499
+ "grad_norm": 1.0276030484998475,
3500
+ "learning_rate": 4.721352647572564e-09,
3501
+ "loss": 0.1129,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 1.9762845849802373,
3506
+ "grad_norm": 1.2463780542335487,
3507
+ "learning_rate": 3.4688937459737004e-09,
3508
+ "loss": 0.1394,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 1.9762845849802373,
3513
+ "eval_loss": 0.16894643008708954,
3514
+ "eval_runtime": 3.7534,
3515
+ "eval_samples_per_second": 5.595,
3516
+ "eval_steps_per_second": 1.599,
3517
+ "step": 500
3518
+ },
3519
+ {
3520
+ "epoch": 1.9802371541501977,
3521
+ "grad_norm": 1.149104137588847,
3522
+ "learning_rate": 2.4090391148112734e-09,
3523
+ "loss": 0.126,
3524
+ "step": 501
3525
+ },
3526
+ {
3527
+ "epoch": 1.9841897233201582,
3528
+ "grad_norm": 1.0644722994856588,
3529
+ "learning_rate": 1.5418296089358964e-09,
3530
+ "loss": 0.1161,
3531
+ "step": 502
3532
+ },
3533
+ {
3534
+ "epoch": 1.9881422924901186,
3535
+ "grad_norm": 1.1078146584096278,
3536
+ "learning_rate": 8.672986571894859e-10,
3537
+ "loss": 0.1159,
3538
+ "step": 503
3539
+ },
3540
+ {
3541
+ "epoch": 1.992094861660079,
3542
+ "grad_norm": 1.0306240076981967,
3543
+ "learning_rate": 3.854722611201789e-10,
3544
+ "loss": 0.1143,
3545
+ "step": 504
3546
+ },
3547
+ {
3548
+ "epoch": 1.9960474308300395,
3549
+ "grad_norm": 1.150741799871838,
3550
+ "learning_rate": 9.636899397813537e-11,
3551
+ "loss": 0.1237,
3552
+ "step": 505
3553
+ },
3554
+ {
3555
+ "epoch": 2.0,
3556
+ "grad_norm": 1.0328104166457073,
3557
+ "learning_rate": 0.0,
3558
+ "loss": 0.1028,
3559
+ "step": 506
3560
+ },
3561
+ {
3562
+ "epoch": 2.0,
3563
+ "step": 506,
3564
+ "total_flos": 6736634707968.0,
3565
+ "train_loss": 0.1787011340083812,
3566
+ "train_runtime": 1032.8943,
3567
+ "train_samples_per_second": 3.913,
3568
+ "train_steps_per_second": 0.49
3569
+ }
3570
+ ],
3571
+ "logging_steps": 1,
3572
+ "max_steps": 506,
3573
+ "num_input_tokens_seen": 0,
3574
+ "num_train_epochs": 2,
3575
+ "save_steps": 70000,
3576
+ "stateful_callbacks": {
3577
+ "TrainerControl": {
3578
+ "args": {
3579
+ "should_epoch_stop": false,
3580
+ "should_evaluate": false,
3581
+ "should_log": false,
3582
+ "should_save": true,
3583
+ "should_training_stop": true
3584
+ },
3585
+ "attributes": {}
3586
+ }
3587
+ },
3588
+ "total_flos": 6736634707968.0,
3589
+ "train_batch_size": 2,
3590
+ "trial_name": null,
3591
+ "trial_params": null
3592
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb6bc2aa7dcee835f77748889389450ff97f23cccd754542788c127b2a702aa
3
+ size 7480
training_eval_loss.png ADDED
training_loss.png ADDED