cahlen commited on
Commit
1242396
·
verified ·
1 Parent(s): a1e5c94

Add fine-tuned DistilBERT model and card

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +128 -0
  2. all_results.json +16 -0
  3. checkpoint-1010/config.json +73 -0
  4. checkpoint-1010/model.safetensors +3 -0
  5. checkpoint-1010/optimizer.pt +3 -0
  6. checkpoint-1010/rng_state.pth +3 -0
  7. checkpoint-1010/scaler.pt +3 -0
  8. checkpoint-1010/scheduler.pt +3 -0
  9. checkpoint-1010/special_tokens_map.json +7 -0
  10. checkpoint-1010/tokenizer.json +0 -0
  11. checkpoint-1010/tokenizer_config.json +56 -0
  12. checkpoint-1010/trainer_state.json +224 -0
  13. checkpoint-1010/training_args.bin +3 -0
  14. checkpoint-1010/vocab.txt +0 -0
  15. checkpoint-808/config.json +73 -0
  16. checkpoint-808/model.safetensors +3 -0
  17. checkpoint-808/optimizer.pt +3 -0
  18. checkpoint-808/rng_state.pth +3 -0
  19. checkpoint-808/scaler.pt +3 -0
  20. checkpoint-808/scheduler.pt +3 -0
  21. checkpoint-808/special_tokens_map.json +7 -0
  22. checkpoint-808/tokenizer.json +0 -0
  23. checkpoint-808/tokenizer_config.json +56 -0
  24. checkpoint-808/trainer_state.json +186 -0
  25. checkpoint-808/training_args.bin +3 -0
  26. checkpoint-808/vocab.txt +0 -0
  27. config.json +73 -0
  28. model.safetensors +3 -0
  29. runs/Apr15_15-12-43_aigodmode/events.out.tfevents.1744755163.aigodmode.996209.0 +3 -0
  30. runs/Apr15_15-13-03_aigodmode/events.out.tfevents.1744755184.aigodmode.996626.0 +3 -0
  31. runs/Apr15_15-13-03_aigodmode/events.out.tfevents.1744755187.aigodmode.996626.1 +3 -0
  32. runs/Apr15_17-19-20_aigodmode/events.out.tfevents.1744762761.aigodmode.1115972.0 +3 -0
  33. runs/Apr15_17-19-20_aigodmode/events.out.tfevents.1744762765.aigodmode.1115972.1 +3 -0
  34. runs/Apr15_18-20-00_aigodmode/events.out.tfevents.1744766401.aigodmode.1175888.0 +3 -0
  35. runs/Apr15_18-20-00_aigodmode/events.out.tfevents.1744766405.aigodmode.1175888.1 +3 -0
  36. runs/Apr15_18-41-07_aigodmode/events.out.tfevents.1744767667.aigodmode.1200966.0 +3 -0
  37. runs/Apr15_18-41-07_aigodmode/events.out.tfevents.1744767675.aigodmode.1200966.1 +3 -0
  38. runs/Apr15_19-39-18_aigodmode/events.out.tfevents.1744771158.aigodmode.1261440.0 +3 -0
  39. runs/Apr15_19-39-18_aigodmode/events.out.tfevents.1744771170.aigodmode.1261440.1 +3 -0
  40. runs/Apr15_19-41-09_aigodmode/events.out.tfevents.1744771270.aigodmode.1263282.0 +3 -0
  41. runs/Apr15_19-41-09_aigodmode/events.out.tfevents.1744771274.aigodmode.1263282.1 +3 -0
  42. runs/Apr15_20-08-54_aigodmode/events.out.tfevents.1744772934.aigodmode.1292055.0 +3 -0
  43. runs/Apr15_20-08-54_aigodmode/events.out.tfevents.1744772939.aigodmode.1292055.1 +3 -0
  44. runs/Apr15_22-03-10_aigodmode/events.out.tfevents.1744779790.aigodmode.1411307.0 +3 -0
  45. runs/Apr15_22-03-10_aigodmode/events.out.tfevents.1744779797.aigodmode.1411307.1 +3 -0
  46. runs/Apr15_23-20-35_aigodmode/events.out.tfevents.1744784435.aigodmode.1497045.0 +3 -0
  47. runs/Apr15_23-20-35_aigodmode/events.out.tfevents.1744784442.aigodmode.1497045.1 +3 -0
  48. runs/Apr15_23-21-41_aigodmode/events.out.tfevents.1744784502.aigodmode.1498147.0 +3 -0
  49. runs/Apr15_23-21-41_aigodmode/events.out.tfevents.1744784513.aigodmode.1498147.1 +3 -0
  50. runs/Apr15_23-22-43_aigodmode/events.out.tfevents.1744784564.aigodmode.1499184.0 +3 -0
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ library_name: transformers
5
+ tags:
6
+ - distilbert
7
+ - text-classification
8
+ - token-classification
9
+ - intent-classification
10
+ - slot-filling
11
+ - joint-intent-slot
12
+ - smart-home
13
+ - generated:Enfuse.io
14
+ pipeline_tag: token-classification # Or text-classification, often token is used for joint models
15
+ model-index:
16
+ - name: distilbert-joint-intent-slot-smarthome
17
+ results:
18
+ - task:
19
+ type: token-classification # Represents the slot filling part
20
+ name: Slot Filling
21
+ dataset:
22
+ name: enfuse/joint-intent-slot-smarthome
23
+ type: enfuse/joint-intent-slot-smarthome
24
+ config: default
25
+ split: test
26
+ metrics:
27
+ - type: micro_f1
28
+ value: 0.8800
29
+ name: Slot F1 (Micro)
30
+ - type: precision
31
+ value: 0.8800
32
+ name: Slot Precision (Micro)
33
+ - type: recall
34
+ value: 0.8800
35
+ name: Slot Recall (Micro)
36
+ - task:
37
+ type: text-classification # Represents the intent part
38
+ name: Intent Classification
39
+ dataset:
40
+ name: enfuse/joint-intent-slot-smarthome
41
+ type: enfuse/joint-intent-slot-smarthome
42
+ config: default
43
+ split: test
44
+ metrics:
45
+ - type: accuracy
46
+ value: 0.9208
47
+ name: Intent Accuracy
48
+ ---
49
+
50
+ # DistilBERT for Smart Home Joint Intent Classification and Slot Filling
51
+
52
+ ## Model Description
53
+
54
+ **Produced By:** [Enfuse.io](https://enfuse.io/)
55
+
56
+ This model is a fine-tuned version of `distilbert-base-uncased` specifically adapted for **joint intent classification and slot filling** in the **smart home domain**. Given a user command related to controlling smart home devices (like lights or thermostats), the model simultaneously predicts:
57
+
58
+ 1. The user's **intent** (e.g., `set_device_state`, `get_device_state`).
59
+ 2. The relevant **slots** (entities like `device_name`, `location`, `state`, `attribute_value`) within the command, using BIO tagging.
60
+
61
+ ## Intended Use and Limitations
62
+
63
+ **Primary Intended Use:** This model is intended for **hobbyist experimentation and educational purposes** related to Natural Language Understanding (NLU) for smart home applications. It can be used as a baseline or starting point for understanding how to build NLU components for simple device control.
64
+
65
+ **Disclaimer:** **This model is NOT intended for use in production environments.** Enfuse.io takes **no responsibility** for the performance, reliability, security, or any consequences arising from the use of this model in production systems or safety-critical applications. Use in such contexts is entirely at the user's own risk.
66
+
67
+ **Out-of-Scope Use:**
68
+ * The model is not designed for general conversation or tasks outside the specific smart home intents and slots it was trained on.
69
+ * It has **no built-in mechanism for handling out-of-domain requests** (e.g., asking about weather, playing music). It will likely attempt to classify such requests into one of the known smart home intents, potentially leading to incorrect behavior.
70
+ * It has not been evaluated for fairness, bias, or robustness against adversarial inputs.
71
+
72
+ ## Training Data
73
+
74
+ The model was fine-tuned on the `enfuse/joint-intent-slot-smarthome` dataset, specifically the `generated_smarthome_2016_unique.jsonl` version containing 2016 unique synthetic examples.
75
+
76
+ This dataset was generated by Enfuse.io using a combination of `mistralai/Mistral-7B-Instruct-v0.1` and `openai/gpt-4o`, followed by validation and de-duplication. Please refer to the [dataset card](https://huggingface.co/datasets/enfuse/joint-intent-slot-smarthome) for more details on the data generation process and limitations.
77
+
78
+ ## Training Procedure
79
+
80
+ ### Preprocessing
81
+
82
+ The text was tokenized using the `distilbert-base-uncased` tokenizer. Slot labels were converted to a BIO tagging scheme. Input sequences were padded and truncated to a maximum length of 128 tokens.
83
+
84
+ ### Fine-tuning
85
+
86
+ The model was fine-tuned using the Hugging Face `transformers` library Trainer on a single NVIDIA RTX 5090.
87
+
88
+ * **Epochs:** 10
89
+ * **Batch Size:** 16 (per device)
90
+ * **Learning Rate:** 5e-5 (with linear decay)
91
+ * **Optimizer:** AdamW
92
+ * **Precision:** FP16
93
+ * **Dataset Split:** 80% Train (1612), 10% Validation (202), 10% Test (202)
94
+ * **Best Model Selection:** The checkpoint with the highest `eval_intent_accuracy` on the validation set during training was selected for the final model (corresponding to Epoch 8 or 10 in the 10-epoch run).
95
+
96
+ ## Evaluation Results
97
+
98
+ The following results were achieved on the **test set** (202 examples) using the best checkpoint saved during training:
99
+
100
+ * **Intent Accuracy:** 92.08%
101
+ * **Slot F1 Score (Micro):** 88.00%
102
+ * **Slot Precision (Micro):** 88.00%
103
+ * **Slot Recall (Micro):** 88.00%
104
+
105
+ *(Note: These results are specific to this particular training setup and may vary with different hyperparameters or training runs.)*
106
+
107
+ ## How to Use
108
+
109
+ *(You would typically add code examples here showing how to load and use the model with the Transformers pipeline or custom code, similar to the logic in `infer.py`. Since the user requested no code, this section is omitted but would normally be present.)*
110
+
111
+ ## Model Card Contact
112
+
113
+ [Enfuse.io](https://enfuse.io/)
114
+
115
+ ## Citation
116
+
117
+ If you use this model, please cite the dataset:
118
+
119
+ ```bibtex
120
+ @misc{enfuse_smarthome_intent_slot_2024,
121
+ author = {Enfuse.io},
122
+ title = {Enfuse Smart Home Joint Intent and Slot Filling Dataset},
123
+ year = {2024},
124
+ publisher = {Hugging Face},
125
+ journal = {Hugging Face Hub},
126
+ howpublished = {\url{https://huggingface.co/datasets/enfuse/joint-intent-slot-smarthome}}
127
+ }
128
+ ```
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_intent_accuracy": 0.9207920792079208,
4
+ "eval_loss": 0.6127998232841492,
5
+ "eval_runtime": 0.0518,
6
+ "eval_samples_per_second": 3900.241,
7
+ "eval_slot_f1": 0.880019120458891,
8
+ "eval_slot_precision": 0.880019120458891,
9
+ "eval_slot_recall": 0.880019120458891,
10
+ "eval_steps_per_second": 77.233,
11
+ "total_flos": 526646237245440.0,
12
+ "train_loss": 0.5116730279261523,
13
+ "train_runtime": 22.7338,
14
+ "train_samples_per_second": 709.076,
15
+ "train_steps_per_second": 44.427
16
+ }
checkpoint-1010/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForJointIntentSlotFilling"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2intent_label": {
11
+ "0": "get_device_state",
12
+ "1": "set_device_attribute",
13
+ "2": "set_device_state"
14
+ },
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "id2slot_label": {
21
+ "0": "O",
22
+ "1": "B-attribute_type",
23
+ "2": "I-attribute_type",
24
+ "3": "B-attribute_value",
25
+ "4": "I-attribute_value",
26
+ "5": "B-device_name",
27
+ "6": "I-device_name",
28
+ "7": "B-location",
29
+ "8": "I-location",
30
+ "9": "B-state",
31
+ "10": "I-state"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intent_label2id": {
35
+ "get_device_state": 0,
36
+ "set_device_attribute": 1,
37
+ "set_device_state": 2
38
+ },
39
+ "intent_loss_coef": 1.0,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_position_embeddings": 512,
46
+ "model_type": "distilbert",
47
+ "n_heads": 12,
48
+ "n_layers": 6,
49
+ "num_intent_labels": 3,
50
+ "num_slot_labels": 11,
51
+ "pad_token_id": 0,
52
+ "qa_dropout": 0.1,
53
+ "seq_classif_dropout": 0.2,
54
+ "sinusoidal_pos_embds": false,
55
+ "slot_label2id": {
56
+ "B-attribute_type": 1,
57
+ "B-attribute_value": 3,
58
+ "B-device_name": 5,
59
+ "B-location": 7,
60
+ "B-state": 9,
61
+ "I-attribute_type": 2,
62
+ "I-attribute_value": 4,
63
+ "I-device_name": 6,
64
+ "I-location": 8,
65
+ "I-state": 10,
66
+ "O": 0
67
+ },
68
+ "slot_loss_coef": 1.0,
69
+ "tie_weights_": true,
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.51.3",
72
+ "vocab_size": 30522
73
+ }
checkpoint-1010/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93648248aa5f5b2bba475dd45e39523e87d8d476b2b0963e788330c821658952
3
+ size 265507144
checkpoint-1010/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b31a3bf879b8944c1933858eed98b7d0be7bacac83c83f16e99621ad542aa8
3
+ size 531076747
checkpoint-1010/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d82205c82ca0e59cbd17794777700714eabf1c99241e9d6f60a8374a27c5982
3
+ size 14645
checkpoint-1010/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4ab2e42d3da0b44d79c51f9ee188d20a00cf98ef55caa853236c82352c6032
3
+ size 1383
checkpoint-1010/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c670f9ce3c4ad30a56141825dd15a2fa3016bb890950ac61a4a9a65bdbf58199
3
+ size 1465
checkpoint-1010/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-1010/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1010/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-1010/trainer_state.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 808,
3
+ "best_metric": 0.9108910891089109,
4
+ "best_model_checkpoint": "./results_distilbert_custom/checkpoint-808",
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1010,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9900990099009901,
14
+ "grad_norm": 2.6412200927734375,
15
+ "learning_rate": 4.51980198019802e-05,
16
+ "loss": 1.0179,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_intent_accuracy": 0.900990099009901,
22
+ "eval_loss": 0.6627025008201599,
23
+ "eval_runtime": 0.0532,
24
+ "eval_samples_per_second": 3796.158,
25
+ "eval_slot_f1": 0.8583372039015328,
26
+ "eval_slot_precision": 0.8583372039015328,
27
+ "eval_slot_recall": 0.8583372039015328,
28
+ "eval_steps_per_second": 75.171,
29
+ "step": 101
30
+ },
31
+ {
32
+ "epoch": 1.9801980198019802,
33
+ "grad_norm": 1.697471022605896,
34
+ "learning_rate": 4.0247524752475254e-05,
35
+ "loss": 0.5933,
36
+ "step": 200
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_intent_accuracy": 0.8910891089108911,
41
+ "eval_loss": 0.5899206399917603,
42
+ "eval_runtime": 0.0516,
43
+ "eval_samples_per_second": 3912.995,
44
+ "eval_slot_f1": 0.8471899674872271,
45
+ "eval_slot_precision": 0.8471899674872271,
46
+ "eval_slot_recall": 0.8471899674872271,
47
+ "eval_steps_per_second": 77.485,
48
+ "step": 202
49
+ },
50
+ {
51
+ "epoch": 2.9702970297029703,
52
+ "grad_norm": 3.684925079345703,
53
+ "learning_rate": 3.52970297029703e-05,
54
+ "loss": 0.5248,
55
+ "step": 300
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_intent_accuracy": 0.900990099009901,
60
+ "eval_loss": 0.5877912640571594,
61
+ "eval_runtime": 0.0512,
62
+ "eval_samples_per_second": 3945.962,
63
+ "eval_slot_f1": 0.864375290292615,
64
+ "eval_slot_precision": 0.864375290292615,
65
+ "eval_slot_recall": 0.864375290292615,
66
+ "eval_steps_per_second": 78.138,
67
+ "step": 303
68
+ },
69
+ {
70
+ "epoch": 3.9603960396039604,
71
+ "grad_norm": 7.954131126403809,
72
+ "learning_rate": 3.0346534653465347e-05,
73
+ "loss": 0.489,
74
+ "step": 400
75
+ },
76
+ {
77
+ "epoch": 4.0,
78
+ "eval_intent_accuracy": 0.905940594059406,
79
+ "eval_loss": 0.6087009906768799,
80
+ "eval_runtime": 0.0514,
81
+ "eval_samples_per_second": 3928.963,
82
+ "eval_slot_f1": 0.864375290292615,
83
+ "eval_slot_precision": 0.864375290292615,
84
+ "eval_slot_recall": 0.864375290292615,
85
+ "eval_steps_per_second": 77.801,
86
+ "step": 404
87
+ },
88
+ {
89
+ "epoch": 4.9504950495049505,
90
+ "grad_norm": 5.173593044281006,
91
+ "learning_rate": 2.53960396039604e-05,
92
+ "loss": 0.468,
93
+ "step": 500
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "eval_intent_accuracy": 0.8762376237623762,
98
+ "eval_loss": 0.6051058173179626,
99
+ "eval_runtime": 0.052,
100
+ "eval_samples_per_second": 3887.446,
101
+ "eval_slot_f1": 0.8732001857872735,
102
+ "eval_slot_precision": 0.8732001857872735,
103
+ "eval_slot_recall": 0.8732001857872735,
104
+ "eval_steps_per_second": 76.979,
105
+ "step": 505
106
+ },
107
+ {
108
+ "epoch": 5.9405940594059405,
109
+ "grad_norm": 2.602719306945801,
110
+ "learning_rate": 2.0445544554455444e-05,
111
+ "loss": 0.4491,
112
+ "step": 600
113
+ },
114
+ {
115
+ "epoch": 6.0,
116
+ "eval_intent_accuracy": 0.905940594059406,
117
+ "eval_loss": 0.6407473683357239,
118
+ "eval_runtime": 0.0554,
119
+ "eval_samples_per_second": 3647.88,
120
+ "eval_slot_f1": 0.87598699489085,
121
+ "eval_slot_precision": 0.87598699489085,
122
+ "eval_slot_recall": 0.87598699489085,
123
+ "eval_steps_per_second": 72.235,
124
+ "step": 606
125
+ },
126
+ {
127
+ "epoch": 6.930693069306931,
128
+ "grad_norm": 2.991025924682617,
129
+ "learning_rate": 1.5495049504950496e-05,
130
+ "loss": 0.4204,
131
+ "step": 700
132
+ },
133
+ {
134
+ "epoch": 7.0,
135
+ "eval_intent_accuracy": 0.8910891089108911,
136
+ "eval_loss": 0.6234941482543945,
137
+ "eval_runtime": 0.0568,
138
+ "eval_samples_per_second": 3558.795,
139
+ "eval_slot_f1": 0.8773803994426381,
140
+ "eval_slot_precision": 0.8773803994426381,
141
+ "eval_slot_recall": 0.8773803994426381,
142
+ "eval_steps_per_second": 70.471,
143
+ "step": 707
144
+ },
145
+ {
146
+ "epoch": 7.920792079207921,
147
+ "grad_norm": 2.211575746536255,
148
+ "learning_rate": 1.0544554455445545e-05,
149
+ "loss": 0.4028,
150
+ "step": 800
151
+ },
152
+ {
153
+ "epoch": 8.0,
154
+ "eval_intent_accuracy": 0.9108910891089109,
155
+ "eval_loss": 0.65041583776474,
156
+ "eval_runtime": 0.0519,
157
+ "eval_samples_per_second": 3893.86,
158
+ "eval_slot_f1": 0.878309335810497,
159
+ "eval_slot_precision": 0.878309335810497,
160
+ "eval_slot_recall": 0.878309335810497,
161
+ "eval_steps_per_second": 77.106,
162
+ "step": 808
163
+ },
164
+ {
165
+ "epoch": 8.910891089108912,
166
+ "grad_norm": 1.5847089290618896,
167
+ "learning_rate": 5.594059405940594e-06,
168
+ "loss": 0.3929,
169
+ "step": 900
170
+ },
171
+ {
172
+ "epoch": 9.0,
173
+ "eval_intent_accuracy": 0.900990099009901,
174
+ "eval_loss": 0.6379386782646179,
175
+ "eval_runtime": 0.051,
176
+ "eval_samples_per_second": 3959.979,
177
+ "eval_slot_f1": 0.8769159312587088,
178
+ "eval_slot_precision": 0.8769159312587088,
179
+ "eval_slot_recall": 0.8769159312587088,
180
+ "eval_steps_per_second": 78.415,
181
+ "step": 909
182
+ },
183
+ {
184
+ "epoch": 9.900990099009901,
185
+ "grad_norm": 5.904131889343262,
186
+ "learning_rate": 6.435643564356436e-07,
187
+ "loss": 0.3679,
188
+ "step": 1000
189
+ },
190
+ {
191
+ "epoch": 10.0,
192
+ "eval_intent_accuracy": 0.9108910891089109,
193
+ "eval_loss": 0.6317320466041565,
194
+ "eval_runtime": 0.0518,
195
+ "eval_samples_per_second": 3899.99,
196
+ "eval_slot_f1": 0.8797027403622851,
197
+ "eval_slot_precision": 0.8797027403622851,
198
+ "eval_slot_recall": 0.8797027403622851,
199
+ "eval_steps_per_second": 77.228,
200
+ "step": 1010
201
+ }
202
+ ],
203
+ "logging_steps": 100,
204
+ "max_steps": 1010,
205
+ "num_input_tokens_seen": 0,
206
+ "num_train_epochs": 10,
207
+ "save_steps": 500,
208
+ "stateful_callbacks": {
209
+ "TrainerControl": {
210
+ "args": {
211
+ "should_epoch_stop": false,
212
+ "should_evaluate": false,
213
+ "should_log": false,
214
+ "should_save": true,
215
+ "should_training_stop": true
216
+ },
217
+ "attributes": {}
218
+ }
219
+ },
220
+ "total_flos": 526646237245440.0,
221
+ "train_batch_size": 16,
222
+ "trial_name": null,
223
+ "trial_params": null
224
+ }
checkpoint-1010/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5460ae7fb569e4afe080919a3302f4475b1c884a06713458cae27af7d9e6a9cf
3
+ size 5777
checkpoint-1010/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-808/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForJointIntentSlotFilling"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2intent_label": {
11
+ "0": "get_device_state",
12
+ "1": "set_device_attribute",
13
+ "2": "set_device_state"
14
+ },
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "id2slot_label": {
21
+ "0": "O",
22
+ "1": "B-attribute_type",
23
+ "2": "I-attribute_type",
24
+ "3": "B-attribute_value",
25
+ "4": "I-attribute_value",
26
+ "5": "B-device_name",
27
+ "6": "I-device_name",
28
+ "7": "B-location",
29
+ "8": "I-location",
30
+ "9": "B-state",
31
+ "10": "I-state"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intent_label2id": {
35
+ "get_device_state": 0,
36
+ "set_device_attribute": 1,
37
+ "set_device_state": 2
38
+ },
39
+ "intent_loss_coef": 1.0,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_position_embeddings": 512,
46
+ "model_type": "distilbert",
47
+ "n_heads": 12,
48
+ "n_layers": 6,
49
+ "num_intent_labels": 3,
50
+ "num_slot_labels": 11,
51
+ "pad_token_id": 0,
52
+ "qa_dropout": 0.1,
53
+ "seq_classif_dropout": 0.2,
54
+ "sinusoidal_pos_embds": false,
55
+ "slot_label2id": {
56
+ "B-attribute_type": 1,
57
+ "B-attribute_value": 3,
58
+ "B-device_name": 5,
59
+ "B-location": 7,
60
+ "B-state": 9,
61
+ "I-attribute_type": 2,
62
+ "I-attribute_value": 4,
63
+ "I-device_name": 6,
64
+ "I-location": 8,
65
+ "I-state": 10,
66
+ "O": 0
67
+ },
68
+ "slot_loss_coef": 1.0,
69
+ "tie_weights_": true,
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.51.3",
72
+ "vocab_size": 30522
73
+ }
checkpoint-808/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c31f1badc5c6e7b3bc137d8f9e31d51672a8f47fe10c383ffc5a60cff77e961
3
+ size 265507144
checkpoint-808/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d01715dea30e8e3316263b4112055a23d620f3992a717339486141fe5802689
3
+ size 531076747
checkpoint-808/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d3c6c5729df1c06893524eebca8d445a73ee949ab0f5b8968bfde1fff2dd5e
3
+ size 14645
checkpoint-808/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2309eb914966d75cf8e4e0e7271c74191a61b3d57d0e33e440d8ca2990543d8
3
+ size 1383
checkpoint-808/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e624932d18ec9c281888584c8ffdcc866ed10ee6365627cd55003a9eeb6e9fc7
3
+ size 1465
checkpoint-808/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-808/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-808/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-808/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 808,
3
+ "best_metric": 0.9108910891089109,
4
+ "best_model_checkpoint": "./results_distilbert_custom/checkpoint-808",
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 808,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9900990099009901,
14
+ "grad_norm": 2.6412200927734375,
15
+ "learning_rate": 4.51980198019802e-05,
16
+ "loss": 1.0179,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_intent_accuracy": 0.900990099009901,
22
+ "eval_loss": 0.6627025008201599,
23
+ "eval_runtime": 0.0532,
24
+ "eval_samples_per_second": 3796.158,
25
+ "eval_slot_f1": 0.8583372039015328,
26
+ "eval_slot_precision": 0.8583372039015328,
27
+ "eval_slot_recall": 0.8583372039015328,
28
+ "eval_steps_per_second": 75.171,
29
+ "step": 101
30
+ },
31
+ {
32
+ "epoch": 1.9801980198019802,
33
+ "grad_norm": 1.697471022605896,
34
+ "learning_rate": 4.0247524752475254e-05,
35
+ "loss": 0.5933,
36
+ "step": 200
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_intent_accuracy": 0.8910891089108911,
41
+ "eval_loss": 0.5899206399917603,
42
+ "eval_runtime": 0.0516,
43
+ "eval_samples_per_second": 3912.995,
44
+ "eval_slot_f1": 0.8471899674872271,
45
+ "eval_slot_precision": 0.8471899674872271,
46
+ "eval_slot_recall": 0.8471899674872271,
47
+ "eval_steps_per_second": 77.485,
48
+ "step": 202
49
+ },
50
+ {
51
+ "epoch": 2.9702970297029703,
52
+ "grad_norm": 3.684925079345703,
53
+ "learning_rate": 3.52970297029703e-05,
54
+ "loss": 0.5248,
55
+ "step": 300
56
+ },
57
+ {
58
+ "epoch": 3.0,
59
+ "eval_intent_accuracy": 0.900990099009901,
60
+ "eval_loss": 0.5877912640571594,
61
+ "eval_runtime": 0.0512,
62
+ "eval_samples_per_second": 3945.962,
63
+ "eval_slot_f1": 0.864375290292615,
64
+ "eval_slot_precision": 0.864375290292615,
65
+ "eval_slot_recall": 0.864375290292615,
66
+ "eval_steps_per_second": 78.138,
67
+ "step": 303
68
+ },
69
+ {
70
+ "epoch": 3.9603960396039604,
71
+ "grad_norm": 7.954131126403809,
72
+ "learning_rate": 3.0346534653465347e-05,
73
+ "loss": 0.489,
74
+ "step": 400
75
+ },
76
+ {
77
+ "epoch": 4.0,
78
+ "eval_intent_accuracy": 0.905940594059406,
79
+ "eval_loss": 0.6087009906768799,
80
+ "eval_runtime": 0.0514,
81
+ "eval_samples_per_second": 3928.963,
82
+ "eval_slot_f1": 0.864375290292615,
83
+ "eval_slot_precision": 0.864375290292615,
84
+ "eval_slot_recall": 0.864375290292615,
85
+ "eval_steps_per_second": 77.801,
86
+ "step": 404
87
+ },
88
+ {
89
+ "epoch": 4.9504950495049505,
90
+ "grad_norm": 5.173593044281006,
91
+ "learning_rate": 2.53960396039604e-05,
92
+ "loss": 0.468,
93
+ "step": 500
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "eval_intent_accuracy": 0.8762376237623762,
98
+ "eval_loss": 0.6051058173179626,
99
+ "eval_runtime": 0.052,
100
+ "eval_samples_per_second": 3887.446,
101
+ "eval_slot_f1": 0.8732001857872735,
102
+ "eval_slot_precision": 0.8732001857872735,
103
+ "eval_slot_recall": 0.8732001857872735,
104
+ "eval_steps_per_second": 76.979,
105
+ "step": 505
106
+ },
107
+ {
108
+ "epoch": 5.9405940594059405,
109
+ "grad_norm": 2.602719306945801,
110
+ "learning_rate": 2.0445544554455444e-05,
111
+ "loss": 0.4491,
112
+ "step": 600
113
+ },
114
+ {
115
+ "epoch": 6.0,
116
+ "eval_intent_accuracy": 0.905940594059406,
117
+ "eval_loss": 0.6407473683357239,
118
+ "eval_runtime": 0.0554,
119
+ "eval_samples_per_second": 3647.88,
120
+ "eval_slot_f1": 0.87598699489085,
121
+ "eval_slot_precision": 0.87598699489085,
122
+ "eval_slot_recall": 0.87598699489085,
123
+ "eval_steps_per_second": 72.235,
124
+ "step": 606
125
+ },
126
+ {
127
+ "epoch": 6.930693069306931,
128
+ "grad_norm": 2.991025924682617,
129
+ "learning_rate": 1.5495049504950496e-05,
130
+ "loss": 0.4204,
131
+ "step": 700
132
+ },
133
+ {
134
+ "epoch": 7.0,
135
+ "eval_intent_accuracy": 0.8910891089108911,
136
+ "eval_loss": 0.6234941482543945,
137
+ "eval_runtime": 0.0568,
138
+ "eval_samples_per_second": 3558.795,
139
+ "eval_slot_f1": 0.8773803994426381,
140
+ "eval_slot_precision": 0.8773803994426381,
141
+ "eval_slot_recall": 0.8773803994426381,
142
+ "eval_steps_per_second": 70.471,
143
+ "step": 707
144
+ },
145
+ {
146
+ "epoch": 7.920792079207921,
147
+ "grad_norm": 2.211575746536255,
148
+ "learning_rate": 1.0544554455445545e-05,
149
+ "loss": 0.4028,
150
+ "step": 800
151
+ },
152
+ {
153
+ "epoch": 8.0,
154
+ "eval_intent_accuracy": 0.9108910891089109,
155
+ "eval_loss": 0.65041583776474,
156
+ "eval_runtime": 0.0519,
157
+ "eval_samples_per_second": 3893.86,
158
+ "eval_slot_f1": 0.878309335810497,
159
+ "eval_slot_precision": 0.878309335810497,
160
+ "eval_slot_recall": 0.878309335810497,
161
+ "eval_steps_per_second": 77.106,
162
+ "step": 808
163
+ }
164
+ ],
165
+ "logging_steps": 100,
166
+ "max_steps": 1010,
167
+ "num_input_tokens_seen": 0,
168
+ "num_train_epochs": 10,
169
+ "save_steps": 500,
170
+ "stateful_callbacks": {
171
+ "TrainerControl": {
172
+ "args": {
173
+ "should_epoch_stop": false,
174
+ "should_evaluate": false,
175
+ "should_log": false,
176
+ "should_save": true,
177
+ "should_training_stop": false
178
+ },
179
+ "attributes": {}
180
+ }
181
+ },
182
+ "total_flos": 421316989796352.0,
183
+ "train_batch_size": 16,
184
+ "trial_name": null,
185
+ "trial_params": null
186
+ }
checkpoint-808/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5460ae7fb569e4afe080919a3302f4475b1c884a06713458cae27af7d9e6a9cf
3
+ size 5777
checkpoint-808/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForJointIntentSlotFilling"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2intent_label": {
11
+ "0": "get_device_state",
12
+ "1": "set_device_attribute",
13
+ "2": "set_device_state"
14
+ },
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "id2slot_label": {
21
+ "0": "O",
22
+ "1": "B-attribute_type",
23
+ "2": "I-attribute_type",
24
+ "3": "B-attribute_value",
25
+ "4": "I-attribute_value",
26
+ "5": "B-device_name",
27
+ "6": "I-device_name",
28
+ "7": "B-location",
29
+ "8": "I-location",
30
+ "9": "B-state",
31
+ "10": "I-state"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intent_label2id": {
35
+ "get_device_state": 0,
36
+ "set_device_attribute": 1,
37
+ "set_device_state": 2
38
+ },
39
+ "intent_loss_coef": 1.0,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_position_embeddings": 512,
46
+ "model_type": "distilbert",
47
+ "n_heads": 12,
48
+ "n_layers": 6,
49
+ "num_intent_labels": 3,
50
+ "num_slot_labels": 11,
51
+ "pad_token_id": 0,
52
+ "qa_dropout": 0.1,
53
+ "seq_classif_dropout": 0.2,
54
+ "sinusoidal_pos_embds": false,
55
+ "slot_label2id": {
56
+ "B-attribute_type": 1,
57
+ "B-attribute_value": 3,
58
+ "B-device_name": 5,
59
+ "B-location": 7,
60
+ "B-state": 9,
61
+ "I-attribute_type": 2,
62
+ "I-attribute_value": 4,
63
+ "I-device_name": 6,
64
+ "I-location": 8,
65
+ "I-state": 10,
66
+ "O": 0
67
+ },
68
+ "slot_loss_coef": 1.0,
69
+ "tie_weights_": true,
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.51.3",
72
+ "vocab_size": 30522
73
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c31f1badc5c6e7b3bc137d8f9e31d51672a8f47fe10c383ffc5a60cff77e961
3
+ size 265507144
runs/Apr15_15-12-43_aigodmode/events.out.tfevents.1744755163.aigodmode.996209.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35b0c3307c8edce30c0e71cb9c3ead35b3fe25a0332f9781be0a689438b6182
3
+ size 5938
runs/Apr15_15-13-03_aigodmode/events.out.tfevents.1744755184.aigodmode.996626.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c22901362b8d9f274dce0f236ea66c22cac503e44622e32bb092e7b73bb8ca
3
+ size 7740
runs/Apr15_15-13-03_aigodmode/events.out.tfevents.1744755187.aigodmode.996626.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff2e00c56c39064e4852c9e87175f4bbd0bc89dc24ed3606106eb3b0d4c21ae1
3
+ size 573
runs/Apr15_17-19-20_aigodmode/events.out.tfevents.1744762761.aigodmode.1115972.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50df85af1b5d0a3f06e567d52910b8be7c9f801e431725a3b5d01710f55082e
3
+ size 7962
runs/Apr15_17-19-20_aigodmode/events.out.tfevents.1744762765.aigodmode.1115972.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399ecf3dc37daf2dd0923162f5c0e3147dd7bc437b82162a14643109544776f3
3
+ size 582
runs/Apr15_18-20-00_aigodmode/events.out.tfevents.1744766401.aigodmode.1175888.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce186316ae6eb1fc9acdb21cbdf157926cb80e74093de0f1194d7745f855c07
3
+ size 7962
runs/Apr15_18-20-00_aigodmode/events.out.tfevents.1744766405.aigodmode.1175888.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8503cfe44841a0fb1e6e276c964e55d9584a406d86d89e646bbc9026d4eec916
3
+ size 582
runs/Apr15_18-41-07_aigodmode/events.out.tfevents.1744767667.aigodmode.1200966.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f5508d3cac29164527cf1bfda59632f225f685b58a503c84e2c384ba15143c
3
+ size 8393
runs/Apr15_18-41-07_aigodmode/events.out.tfevents.1744767675.aigodmode.1200966.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4af9c5c60777f79dac5ec4bdf01168be4fa51925c7e771776a460d2fa17397f
3
+ size 582
runs/Apr15_19-39-18_aigodmode/events.out.tfevents.1744771158.aigodmode.1261440.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf00a06717da11a4159c820fe56c91fe07a278da445f5cfe8e173ea9aac7aea
3
+ size 9035
runs/Apr15_19-39-18_aigodmode/events.out.tfevents.1744771170.aigodmode.1261440.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a131f7bf860686603c5a621154634d8b823293703fb9c4d5e9a300de23e67e9
3
+ size 582
runs/Apr15_19-41-09_aigodmode/events.out.tfevents.1744771270.aigodmode.1263282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43492f9f7312018fa2d91feda6fdfc71d54df79c61ba9c71722b4ccb0a786cc0
3
+ size 7962
runs/Apr15_19-41-09_aigodmode/events.out.tfevents.1744771274.aigodmode.1263282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0328a70b832431662157df678c2669601f975d5c7640d0f41ceedd753470e9
3
+ size 582
runs/Apr15_20-08-54_aigodmode/events.out.tfevents.1744772934.aigodmode.1292055.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b67a926bafbf632bccd8d5b8f9fa3decfcd16dd13b0b0c1cc19bc9182f3272
3
+ size 7962
runs/Apr15_20-08-54_aigodmode/events.out.tfevents.1744772939.aigodmode.1292055.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28519c868715aca438a32fa2a9607390d9c12ed964f671b2e2818f1e3a3cc7b1
3
+ size 582
runs/Apr15_22-03-10_aigodmode/events.out.tfevents.1744779790.aigodmode.1411307.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6baddd8e8f1fe4a3177de09a0de4b5d7c051eda63b0d572d0ecc14b73fc3c6
3
+ size 8182
runs/Apr15_22-03-10_aigodmode/events.out.tfevents.1744779797.aigodmode.1411307.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3f3f15bd5aa8ffe18a4f4a9fe299ce211a8efcd994ad6578dc0a90a7cf296c
3
+ size 582
runs/Apr15_23-20-35_aigodmode/events.out.tfevents.1744784435.aigodmode.1497045.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aff3b782064c46c9073ee0c584e2d8c78c7d74ab1290a28f77322853a2828a
3
+ size 8393
runs/Apr15_23-20-35_aigodmode/events.out.tfevents.1744784442.aigodmode.1497045.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5056c63e5751b899ff0eb8db8ea3c6cc113dc812cd2033a7f1922a6449f4b8c
3
+ size 582
runs/Apr15_23-21-41_aigodmode/events.out.tfevents.1744784502.aigodmode.1498147.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44198eda7e8f8942f947fe63aaeedc680e6100dccb2caa9c5b53ea2f144e52aa
3
+ size 9803
runs/Apr15_23-21-41_aigodmode/events.out.tfevents.1744784513.aigodmode.1498147.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30fbfd74417bed3ed6c0462bc78c7604635f922db61eb06b80cde1fdf063463
3
+ size 582
runs/Apr15_23-22-43_aigodmode/events.out.tfevents.1744784564.aigodmode.1499184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630efb1b5574425843d6f147f63b66edd4ac7d9c654093d43667c97f0c0640ca
3
+ size 13329