Upload folder using huggingface_hub
Browse files- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer_reference.txt +1 -0
- trainer_state.json +1243 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "phueb/BabyBERTa-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 3,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 4,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 256,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 1024,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 130,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 8,
|
| 20 |
+
"num_hidden_layers": 8,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.46.3",
|
| 25 |
+
"type_vocab_size": 2,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 8192
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ade9f0a6408d9d443f6f358408bab44404bd94b73172863d87c9c44d1cb2650a
|
| 3 |
+
size 34112288
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef1b9e66a36daf090a8132f3d47570f28809c663e135f1ee1112861b733fee83
|
| 3 |
+
size 68307834
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eef62f1726f7816d16b679bcd0fa5d5e094f95e050cda7edab9ab319cfc28693
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16810444873b484fc4539f7c992208849486053bc0e4c6d3fd5f116f0345171f
|
| 3 |
+
size 1064
|
tokenizer_reference.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Tokenizer available at: msharma95/babyberta-tokenizer
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7811457624923088,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 55000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016192234204475534,
|
| 13 |
+
"grad_norm": 2.899235963821411,
|
| 14 |
+
"learning_rate": 4.9919038828977625e-05,
|
| 15 |
+
"loss": 7.6546,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03238446840895107,
|
| 20 |
+
"grad_norm": 3.1383473873138428,
|
| 21 |
+
"learning_rate": 4.983807765795525e-05,
|
| 22 |
+
"loss": 7.0771,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03238446840895107,
|
| 27 |
+
"eval_loss": 10.114262580871582,
|
| 28 |
+
"eval_runtime": 20.3013,
|
| 29 |
+
"eval_samples_per_second": 2704.02,
|
| 30 |
+
"eval_steps_per_second": 169.004,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0485767026134266,
|
| 35 |
+
"grad_norm": 3.265001058578491,
|
| 36 |
+
"learning_rate": 4.975711648693287e-05,
|
| 37 |
+
"loss": 6.9745,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06476893681790213,
|
| 42 |
+
"grad_norm": 4.482234477996826,
|
| 43 |
+
"learning_rate": 4.967615531591049e-05,
|
| 44 |
+
"loss": 6.8578,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06476893681790213,
|
| 49 |
+
"eval_loss": 10.50239086151123,
|
| 50 |
+
"eval_runtime": 20.2747,
|
| 51 |
+
"eval_samples_per_second": 2707.566,
|
| 52 |
+
"eval_steps_per_second": 169.226,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.08096117102237767,
|
| 57 |
+
"grad_norm": 3.455843925476074,
|
| 58 |
+
"learning_rate": 4.9595194144888116e-05,
|
| 59 |
+
"loss": 6.8529,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0971534052268532,
|
| 64 |
+
"grad_norm": 4.888940811157227,
|
| 65 |
+
"learning_rate": 4.951423297386574e-05,
|
| 66 |
+
"loss": 6.7865,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.0971534052268532,
|
| 71 |
+
"eval_loss": 11.206120491027832,
|
| 72 |
+
"eval_runtime": 20.2787,
|
| 73 |
+
"eval_samples_per_second": 2707.023,
|
| 74 |
+
"eval_steps_per_second": 169.192,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11334563943132873,
|
| 79 |
+
"grad_norm": 2.9272000789642334,
|
| 80 |
+
"learning_rate": 4.9433271802843354e-05,
|
| 81 |
+
"loss": 6.7582,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.12953787363580427,
|
| 86 |
+
"grad_norm": 3.68345046043396,
|
| 87 |
+
"learning_rate": 4.9352310631820984e-05,
|
| 88 |
+
"loss": 6.6886,
|
| 89 |
+
"step": 4000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.12953787363580427,
|
| 93 |
+
"eval_loss": 11.919740676879883,
|
| 94 |
+
"eval_runtime": 20.2985,
|
| 95 |
+
"eval_samples_per_second": 2704.382,
|
| 96 |
+
"eval_steps_per_second": 169.027,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.14573010784027982,
|
| 101 |
+
"grad_norm": 3.9165866374969482,
|
| 102 |
+
"learning_rate": 4.927151138314065e-05,
|
| 103 |
+
"loss": 6.657,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.16192234204475534,
|
| 108 |
+
"grad_norm": 4.2097015380859375,
|
| 109 |
+
"learning_rate": 4.9190550212118266e-05,
|
| 110 |
+
"loss": 6.6567,
|
| 111 |
+
"step": 5000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16192234204475534,
|
| 115 |
+
"eval_loss": 11.381248474121094,
|
| 116 |
+
"eval_runtime": 20.3121,
|
| 117 |
+
"eval_samples_per_second": 2702.582,
|
| 118 |
+
"eval_steps_per_second": 168.914,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.17811457624923088,
|
| 123 |
+
"grad_norm": 3.525871753692627,
|
| 124 |
+
"learning_rate": 4.9109589041095895e-05,
|
| 125 |
+
"loss": 6.6297,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.1943068104537064,
|
| 130 |
+
"grad_norm": 5.512066841125488,
|
| 131 |
+
"learning_rate": 4.902862787007351e-05,
|
| 132 |
+
"loss": 6.6049,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.1943068104537064,
|
| 137 |
+
"eval_loss": 11.815380096435547,
|
| 138 |
+
"eval_runtime": 20.3269,
|
| 139 |
+
"eval_samples_per_second": 2700.605,
|
| 140 |
+
"eval_steps_per_second": 168.791,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.21049904465818195,
|
| 145 |
+
"grad_norm": 6.878340244293213,
|
| 146 |
+
"learning_rate": 4.8947828621393185e-05,
|
| 147 |
+
"loss": 6.5587,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.22669127886265747,
|
| 152 |
+
"grad_norm": 3.512578248977661,
|
| 153 |
+
"learning_rate": 4.886686745037081e-05,
|
| 154 |
+
"loss": 6.5451,
|
| 155 |
+
"step": 7000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.22669127886265747,
|
| 159 |
+
"eval_loss": 11.993084907531738,
|
| 160 |
+
"eval_runtime": 20.3217,
|
| 161 |
+
"eval_samples_per_second": 2701.3,
|
| 162 |
+
"eval_steps_per_second": 168.834,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.24288351306713302,
|
| 167 |
+
"grad_norm": 4.394603729248047,
|
| 168 |
+
"learning_rate": 4.8786068201690474e-05,
|
| 169 |
+
"loss": 6.5283,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.25907574727160854,
|
| 174 |
+
"grad_norm": 3.8106327056884766,
|
| 175 |
+
"learning_rate": 4.8705107030668096e-05,
|
| 176 |
+
"loss": 6.5246,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.25907574727160854,
|
| 181 |
+
"eval_loss": 12.192233085632324,
|
| 182 |
+
"eval_runtime": 20.3069,
|
| 183 |
+
"eval_samples_per_second": 2703.263,
|
| 184 |
+
"eval_steps_per_second": 168.957,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.27526798147608406,
|
| 189 |
+
"grad_norm": 4.158311367034912,
|
| 190 |
+
"learning_rate": 4.862414585964571e-05,
|
| 191 |
+
"loss": 6.4727,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.29146021568055963,
|
| 196 |
+
"grad_norm": 3.797197103500366,
|
| 197 |
+
"learning_rate": 4.854318468862334e-05,
|
| 198 |
+
"loss": 6.4594,
|
| 199 |
+
"step": 9000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.29146021568055963,
|
| 203 |
+
"eval_loss": 12.250760078430176,
|
| 204 |
+
"eval_runtime": 20.2943,
|
| 205 |
+
"eval_samples_per_second": 2704.945,
|
| 206 |
+
"eval_steps_per_second": 169.062,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.30765244988503515,
|
| 211 |
+
"grad_norm": 4.4851908683776855,
|
| 212 |
+
"learning_rate": 4.8462223517600964e-05,
|
| 213 |
+
"loss": 6.4441,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.32384468408951067,
|
| 218 |
+
"grad_norm": 5.158078670501709,
|
| 219 |
+
"learning_rate": 4.838142426892063e-05,
|
| 220 |
+
"loss": 6.4537,
|
| 221 |
+
"step": 10000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.32384468408951067,
|
| 225 |
+
"eval_loss": 12.235699653625488,
|
| 226 |
+
"eval_runtime": 20.3426,
|
| 227 |
+
"eval_samples_per_second": 2698.522,
|
| 228 |
+
"eval_steps_per_second": 168.661,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.3400369182939862,
|
| 233 |
+
"grad_norm": 4.838212966918945,
|
| 234 |
+
"learning_rate": 4.8300463097898254e-05,
|
| 235 |
+
"loss": 6.4313,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.35622915249846177,
|
| 240 |
+
"grad_norm": 4.873743534088135,
|
| 241 |
+
"learning_rate": 4.821950192687587e-05,
|
| 242 |
+
"loss": 6.4375,
|
| 243 |
+
"step": 11000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.35622915249846177,
|
| 247 |
+
"eval_loss": 13.167688369750977,
|
| 248 |
+
"eval_runtime": 20.3858,
|
| 249 |
+
"eval_samples_per_second": 2692.805,
|
| 250 |
+
"eval_steps_per_second": 168.303,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.3724213867029373,
|
| 255 |
+
"grad_norm": 5.022457122802734,
|
| 256 |
+
"learning_rate": 4.813854075585349e-05,
|
| 257 |
+
"loss": 6.4249,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3886136209074128,
|
| 262 |
+
"grad_norm": 4.3410964012146,
|
| 263 |
+
"learning_rate": 4.805774150717316e-05,
|
| 264 |
+
"loss": 6.3944,
|
| 265 |
+
"step": 12000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3886136209074128,
|
| 269 |
+
"eval_loss": 12.753792762756348,
|
| 270 |
+
"eval_runtime": 20.3234,
|
| 271 |
+
"eval_samples_per_second": 2701.08,
|
| 272 |
+
"eval_steps_per_second": 168.821,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.4048058551118883,
|
| 277 |
+
"grad_norm": 4.282736301422119,
|
| 278 |
+
"learning_rate": 4.797678033615078e-05,
|
| 279 |
+
"loss": 6.3343,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.4209980893163639,
|
| 284 |
+
"grad_norm": 4.2941484451293945,
|
| 285 |
+
"learning_rate": 4.789581916512841e-05,
|
| 286 |
+
"loss": 6.3576,
|
| 287 |
+
"step": 13000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.4209980893163639,
|
| 291 |
+
"eval_loss": 14.182137489318848,
|
| 292 |
+
"eval_runtime": 20.2915,
|
| 293 |
+
"eval_samples_per_second": 2705.322,
|
| 294 |
+
"eval_steps_per_second": 169.086,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.4371903235208394,
|
| 299 |
+
"grad_norm": 4.584780693054199,
|
| 300 |
+
"learning_rate": 4.7814857994106027e-05,
|
| 301 |
+
"loss": 6.3133,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.45338255772531494,
|
| 306 |
+
"grad_norm": 6.5496134757995605,
|
| 307 |
+
"learning_rate": 4.77340587454257e-05,
|
| 308 |
+
"loss": 6.3042,
|
| 309 |
+
"step": 14000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.45338255772531494,
|
| 313 |
+
"eval_loss": 13.6593656539917,
|
| 314 |
+
"eval_runtime": 20.2751,
|
| 315 |
+
"eval_samples_per_second": 2707.503,
|
| 316 |
+
"eval_steps_per_second": 169.222,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.46957479192979046,
|
| 321 |
+
"grad_norm": 4.188933849334717,
|
| 322 |
+
"learning_rate": 4.7653097574403316e-05,
|
| 323 |
+
"loss": 6.2764,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.48576702613426603,
|
| 328 |
+
"grad_norm": 4.540693283081055,
|
| 329 |
+
"learning_rate": 4.757213640338094e-05,
|
| 330 |
+
"loss": 6.261,
|
| 331 |
+
"step": 15000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.48576702613426603,
|
| 335 |
+
"eval_loss": 13.340327262878418,
|
| 336 |
+
"eval_runtime": 20.2957,
|
| 337 |
+
"eval_samples_per_second": 2704.755,
|
| 338 |
+
"eval_steps_per_second": 169.05,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5019592603387415,
|
| 343 |
+
"grad_norm": 4.090181827545166,
|
| 344 |
+
"learning_rate": 4.749117523235857e-05,
|
| 345 |
+
"loss": 6.2382,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5181514945432171,
|
| 350 |
+
"grad_norm": 5.604825973510742,
|
| 351 |
+
"learning_rate": 4.7410214061336184e-05,
|
| 352 |
+
"loss": 6.2225,
|
| 353 |
+
"step": 16000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5181514945432171,
|
| 357 |
+
"eval_loss": 14.243009567260742,
|
| 358 |
+
"eval_runtime": 20.3274,
|
| 359 |
+
"eval_samples_per_second": 2700.537,
|
| 360 |
+
"eval_steps_per_second": 168.787,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.5343437287476926,
|
| 365 |
+
"grad_norm": 5.334819316864014,
|
| 366 |
+
"learning_rate": 4.732941481265585e-05,
|
| 367 |
+
"loss": 6.2051,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.5505359629521681,
|
| 372 |
+
"grad_norm": 5.907509803771973,
|
| 373 |
+
"learning_rate": 4.724845364163347e-05,
|
| 374 |
+
"loss": 6.1475,
|
| 375 |
+
"step": 17000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.5505359629521681,
|
| 379 |
+
"eval_loss": 14.208978652954102,
|
| 380 |
+
"eval_runtime": 20.3636,
|
| 381 |
+
"eval_samples_per_second": 2695.742,
|
| 382 |
+
"eval_steps_per_second": 168.487,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.5667281971566437,
|
| 387 |
+
"grad_norm": 5.113221645355225,
|
| 388 |
+
"learning_rate": 4.7167492470611096e-05,
|
| 389 |
+
"loss": 6.1765,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.5829204313611193,
|
| 394 |
+
"grad_norm": 5.8240461349487305,
|
| 395 |
+
"learning_rate": 4.708653129958872e-05,
|
| 396 |
+
"loss": 6.1567,
|
| 397 |
+
"step": 18000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.5829204313611193,
|
| 401 |
+
"eval_loss": 14.480341911315918,
|
| 402 |
+
"eval_runtime": 20.3098,
|
| 403 |
+
"eval_samples_per_second": 2702.888,
|
| 404 |
+
"eval_steps_per_second": 168.934,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.5991126655655947,
|
| 409 |
+
"grad_norm": 4.948818683624268,
|
| 410 |
+
"learning_rate": 4.7005732050908385e-05,
|
| 411 |
+
"loss": 6.1198,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.6153048997700703,
|
| 416 |
+
"grad_norm": 5.95670223236084,
|
| 417 |
+
"learning_rate": 4.692477087988601e-05,
|
| 418 |
+
"loss": 6.1038,
|
| 419 |
+
"step": 19000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.6153048997700703,
|
| 423 |
+
"eval_loss": 14.150490760803223,
|
| 424 |
+
"eval_runtime": 20.2957,
|
| 425 |
+
"eval_samples_per_second": 2704.759,
|
| 426 |
+
"eval_steps_per_second": 169.051,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.6314971339745458,
|
| 431 |
+
"grad_norm": 7.957947731018066,
|
| 432 |
+
"learning_rate": 4.684380970886363e-05,
|
| 433 |
+
"loss": 6.0658,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.6476893681790213,
|
| 438 |
+
"grad_norm": 6.398547649383545,
|
| 439 |
+
"learning_rate": 4.676284853784125e-05,
|
| 440 |
+
"loss": 6.007,
|
| 441 |
+
"step": 20000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.6476893681790213,
|
| 445 |
+
"eval_loss": 13.682233810424805,
|
| 446 |
+
"eval_runtime": 20.2919,
|
| 447 |
+
"eval_samples_per_second": 2705.271,
|
| 448 |
+
"eval_steps_per_second": 169.083,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.6638816023834969,
|
| 453 |
+
"grad_norm": 7.564326763153076,
|
| 454 |
+
"learning_rate": 4.6681887366818875e-05,
|
| 455 |
+
"loss": 6.0063,
|
| 456 |
+
"step": 20500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.6800738365879724,
|
| 460 |
+
"grad_norm": 6.847624778747559,
|
| 461 |
+
"learning_rate": 4.66009261957965e-05,
|
| 462 |
+
"loss": 5.9528,
|
| 463 |
+
"step": 21000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.6800738365879724,
|
| 467 |
+
"eval_loss": 13.830253601074219,
|
| 468 |
+
"eval_runtime": 20.3183,
|
| 469 |
+
"eval_samples_per_second": 2701.748,
|
| 470 |
+
"eval_steps_per_second": 168.862,
|
| 471 |
+
"step": 21000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.696266070792448,
|
| 475 |
+
"grad_norm": 6.5545125007629395,
|
| 476 |
+
"learning_rate": 4.651996502477412e-05,
|
| 477 |
+
"loss": 5.9257,
|
| 478 |
+
"step": 21500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7124583049969235,
|
| 482 |
+
"grad_norm": 8.006608009338379,
|
| 483 |
+
"learning_rate": 4.643900385375174e-05,
|
| 484 |
+
"loss": 5.9066,
|
| 485 |
+
"step": 22000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7124583049969235,
|
| 489 |
+
"eval_loss": 14.178547859191895,
|
| 490 |
+
"eval_runtime": 20.3334,
|
| 491 |
+
"eval_samples_per_second": 2699.748,
|
| 492 |
+
"eval_steps_per_second": 168.737,
|
| 493 |
+
"step": 22000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.728650539201399,
|
| 497 |
+
"grad_norm": 6.9318766593933105,
|
| 498 |
+
"learning_rate": 4.635820460507141e-05,
|
| 499 |
+
"loss": 5.8562,
|
| 500 |
+
"step": 22500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7448427734058746,
|
| 504 |
+
"grad_norm": 6.815021991729736,
|
| 505 |
+
"learning_rate": 4.627724343404903e-05,
|
| 506 |
+
"loss": 5.7984,
|
| 507 |
+
"step": 23000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7448427734058746,
|
| 511 |
+
"eval_loss": 14.005717277526855,
|
| 512 |
+
"eval_runtime": 20.3208,
|
| 513 |
+
"eval_samples_per_second": 2701.413,
|
| 514 |
+
"eval_steps_per_second": 168.841,
|
| 515 |
+
"step": 23000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.76103500761035,
|
| 519 |
+
"grad_norm": 7.4206976890563965,
|
| 520 |
+
"learning_rate": 4.6196282263026655e-05,
|
| 521 |
+
"loss": 5.7574,
|
| 522 |
+
"step": 23500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.7772272418148256,
|
| 526 |
+
"grad_norm": 7.273144721984863,
|
| 527 |
+
"learning_rate": 4.611532109200428e-05,
|
| 528 |
+
"loss": 5.7247,
|
| 529 |
+
"step": 24000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.7772272418148256,
|
| 533 |
+
"eval_loss": 13.36209774017334,
|
| 534 |
+
"eval_runtime": 20.3187,
|
| 535 |
+
"eval_samples_per_second": 2701.693,
|
| 536 |
+
"eval_steps_per_second": 168.859,
|
| 537 |
+
"step": 24000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.7934194760193012,
|
| 541 |
+
"grad_norm": 8.667037963867188,
|
| 542 |
+
"learning_rate": 4.6034521843323944e-05,
|
| 543 |
+
"loss": 5.682,
|
| 544 |
+
"step": 24500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.8096117102237766,
|
| 548 |
+
"grad_norm": 9.467761039733887,
|
| 549 |
+
"learning_rate": 4.595356067230157e-05,
|
| 550 |
+
"loss": 5.6262,
|
| 551 |
+
"step": 25000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.8096117102237766,
|
| 555 |
+
"eval_loss": 14.30241584777832,
|
| 556 |
+
"eval_runtime": 20.3265,
|
| 557 |
+
"eval_samples_per_second": 2700.664,
|
| 558 |
+
"eval_steps_per_second": 168.795,
|
| 559 |
+
"step": 25000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.8258039444282522,
|
| 563 |
+
"grad_norm": 7.378128528594971,
|
| 564 |
+
"learning_rate": 4.587259950127919e-05,
|
| 565 |
+
"loss": 5.5776,
|
| 566 |
+
"step": 25500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.8419961786327278,
|
| 570 |
+
"grad_norm": 8.246053695678711,
|
| 571 |
+
"learning_rate": 4.5791638330256806e-05,
|
| 572 |
+
"loss": 5.5251,
|
| 573 |
+
"step": 26000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.8419961786327278,
|
| 577 |
+
"eval_loss": 14.098834037780762,
|
| 578 |
+
"eval_runtime": 20.3189,
|
| 579 |
+
"eval_samples_per_second": 2701.67,
|
| 580 |
+
"eval_steps_per_second": 168.857,
|
| 581 |
+
"step": 26000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.8581884128372033,
|
| 585 |
+
"grad_norm": 6.545131206512451,
|
| 586 |
+
"learning_rate": 4.571083908157648e-05,
|
| 587 |
+
"loss": 5.4848,
|
| 588 |
+
"step": 26500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.8743806470416788,
|
| 592 |
+
"grad_norm": 7.735929489135742,
|
| 593 |
+
"learning_rate": 4.56298779105541e-05,
|
| 594 |
+
"loss": 5.4504,
|
| 595 |
+
"step": 27000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.8743806470416788,
|
| 599 |
+
"eval_loss": 13.383395195007324,
|
| 600 |
+
"eval_runtime": 20.3058,
|
| 601 |
+
"eval_samples_per_second": 2703.417,
|
| 602 |
+
"eval_steps_per_second": 168.967,
|
| 603 |
+
"step": 27000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.8905728812461543,
|
| 607 |
+
"grad_norm": 7.53142786026001,
|
| 608 |
+
"learning_rate": 4.5548916739531724e-05,
|
| 609 |
+
"loss": 5.4094,
|
| 610 |
+
"step": 27500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.9067651154506299,
|
| 614 |
+
"grad_norm": 6.753902912139893,
|
| 615 |
+
"learning_rate": 4.546795556850935e-05,
|
| 616 |
+
"loss": 5.382,
|
| 617 |
+
"step": 28000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.9067651154506299,
|
| 621 |
+
"eval_loss": 13.9662446975708,
|
| 622 |
+
"eval_runtime": 20.3511,
|
| 623 |
+
"eval_samples_per_second": 2697.397,
|
| 624 |
+
"eval_steps_per_second": 168.59,
|
| 625 |
+
"step": 28000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9229573496551055,
|
| 629 |
+
"grad_norm": 7.170286655426025,
|
| 630 |
+
"learning_rate": 4.538715631982901e-05,
|
| 631 |
+
"loss": 5.3786,
|
| 632 |
+
"step": 28500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9391495838595809,
|
| 636 |
+
"grad_norm": 7.388674736022949,
|
| 637 |
+
"learning_rate": 4.5306195148806636e-05,
|
| 638 |
+
"loss": 5.3468,
|
| 639 |
+
"step": 29000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9391495838595809,
|
| 643 |
+
"eval_loss": 14.00700855255127,
|
| 644 |
+
"eval_runtime": 20.2945,
|
| 645 |
+
"eval_samples_per_second": 2704.924,
|
| 646 |
+
"eval_steps_per_second": 169.061,
|
| 647 |
+
"step": 29000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9553418180640565,
|
| 651 |
+
"grad_norm": 8.680002212524414,
|
| 652 |
+
"learning_rate": 4.522523397778426e-05,
|
| 653 |
+
"loss": 5.3159,
|
| 654 |
+
"step": 29500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9715340522685321,
|
| 658 |
+
"grad_norm": 6.966347694396973,
|
| 659 |
+
"learning_rate": 4.514427280676188e-05,
|
| 660 |
+
"loss": 5.3321,
|
| 661 |
+
"step": 30000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9715340522685321,
|
| 665 |
+
"eval_loss": 13.2510986328125,
|
| 666 |
+
"eval_runtime": 20.2734,
|
| 667 |
+
"eval_samples_per_second": 2707.742,
|
| 668 |
+
"eval_steps_per_second": 169.237,
|
| 669 |
+
"step": 30000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.9877262864730075,
|
| 673 |
+
"grad_norm": 7.675726413726807,
|
| 674 |
+
"learning_rate": 4.506347355808155e-05,
|
| 675 |
+
"loss": 5.2547,
|
| 676 |
+
"step": 30500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.003918520677483,
|
| 680 |
+
"grad_norm": 9.16435432434082,
|
| 681 |
+
"learning_rate": 4.4982512387059164e-05,
|
| 682 |
+
"loss": 5.2597,
|
| 683 |
+
"step": 31000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.003918520677483,
|
| 687 |
+
"eval_loss": 13.722345352172852,
|
| 688 |
+
"eval_runtime": 20.3123,
|
| 689 |
+
"eval_samples_per_second": 2702.549,
|
| 690 |
+
"eval_steps_per_second": 168.912,
|
| 691 |
+
"step": 31000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.0201107548819586,
|
| 695 |
+
"grad_norm": 8.053180694580078,
|
| 696 |
+
"learning_rate": 4.490155121603679e-05,
|
| 697 |
+
"loss": 5.2168,
|
| 698 |
+
"step": 31500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.0363029890864341,
|
| 702 |
+
"grad_norm": 7.8324432373046875,
|
| 703 |
+
"learning_rate": 4.4820590045014416e-05,
|
| 704 |
+
"loss": 5.2229,
|
| 705 |
+
"step": 32000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.0363029890864341,
|
| 709 |
+
"eval_loss": 13.410867691040039,
|
| 710 |
+
"eval_runtime": 20.3235,
|
| 711 |
+
"eval_samples_per_second": 2701.057,
|
| 712 |
+
"eval_steps_per_second": 168.819,
|
| 713 |
+
"step": 32000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.0524952232909097,
|
| 717 |
+
"grad_norm": 6.322490692138672,
|
| 718 |
+
"learning_rate": 4.473979079633408e-05,
|
| 719 |
+
"loss": 5.1849,
|
| 720 |
+
"step": 32500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.0686874574953853,
|
| 724 |
+
"grad_norm": 7.511089324951172,
|
| 725 |
+
"learning_rate": 4.4658829625311705e-05,
|
| 726 |
+
"loss": 5.1838,
|
| 727 |
+
"step": 33000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.0686874574953853,
|
| 731 |
+
"eval_loss": 13.21849250793457,
|
| 732 |
+
"eval_runtime": 20.3207,
|
| 733 |
+
"eval_samples_per_second": 2701.433,
|
| 734 |
+
"eval_steps_per_second": 168.843,
|
| 735 |
+
"step": 33000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.0848796916998606,
|
| 739 |
+
"grad_norm": 7.725784778594971,
|
| 740 |
+
"learning_rate": 4.457786845428932e-05,
|
| 741 |
+
"loss": 5.1687,
|
| 742 |
+
"step": 33500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.1010719259043362,
|
| 746 |
+
"grad_norm": 7.167893886566162,
|
| 747 |
+
"learning_rate": 4.449690728326695e-05,
|
| 748 |
+
"loss": 5.157,
|
| 749 |
+
"step": 34000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.1010719259043362,
|
| 753 |
+
"eval_loss": 13.764806747436523,
|
| 754 |
+
"eval_runtime": 20.3095,
|
| 755 |
+
"eval_samples_per_second": 2702.924,
|
| 756 |
+
"eval_steps_per_second": 168.936,
|
| 757 |
+
"step": 34000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.1172641601088118,
|
| 761 |
+
"grad_norm": 9.298649787902832,
|
| 762 |
+
"learning_rate": 4.441610803458661e-05,
|
| 763 |
+
"loss": 5.1152,
|
| 764 |
+
"step": 34500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.1334563943132874,
|
| 768 |
+
"grad_norm": 7.694969654083252,
|
| 769 |
+
"learning_rate": 4.433514686356424e-05,
|
| 770 |
+
"loss": 5.0736,
|
| 771 |
+
"step": 35000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.1334563943132874,
|
| 775 |
+
"eval_loss": 13.989611625671387,
|
| 776 |
+
"eval_runtime": 20.324,
|
| 777 |
+
"eval_samples_per_second": 2700.988,
|
| 778 |
+
"eval_steps_per_second": 168.815,
|
| 779 |
+
"step": 35000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.149648628517763,
|
| 783 |
+
"grad_norm": 7.617096424102783,
|
| 784 |
+
"learning_rate": 4.425418569254186e-05,
|
| 785 |
+
"loss": 5.0596,
|
| 786 |
+
"step": 35500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.1658408627222383,
|
| 790 |
+
"grad_norm": 6.822023391723633,
|
| 791 |
+
"learning_rate": 4.417322452151948e-05,
|
| 792 |
+
"loss": 5.0544,
|
| 793 |
+
"step": 36000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.1658408627222383,
|
| 797 |
+
"eval_loss": 14.167996406555176,
|
| 798 |
+
"eval_runtime": 20.2953,
|
| 799 |
+
"eval_samples_per_second": 2704.815,
|
| 800 |
+
"eval_steps_per_second": 169.054,
|
| 801 |
+
"step": 36000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.1820330969267139,
|
| 805 |
+
"grad_norm": 6.709229946136475,
|
| 806 |
+
"learning_rate": 4.40922633504971e-05,
|
| 807 |
+
"loss": 5.0675,
|
| 808 |
+
"step": 36500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.1982253311311895,
|
| 812 |
+
"grad_norm": 8.224237442016602,
|
| 813 |
+
"learning_rate": 4.401162602415881e-05,
|
| 814 |
+
"loss": 4.9965,
|
| 815 |
+
"step": 37000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.1982253311311895,
|
| 819 |
+
"eval_loss": 14.570647239685059,
|
| 820 |
+
"eval_runtime": 20.3304,
|
| 821 |
+
"eval_samples_per_second": 2700.144,
|
| 822 |
+
"eval_steps_per_second": 168.762,
|
| 823 |
+
"step": 37000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.214417565335665,
|
| 827 |
+
"grad_norm": 8.49647045135498,
|
| 828 |
+
"learning_rate": 4.393066485313644e-05,
|
| 829 |
+
"loss": 4.9891,
|
| 830 |
+
"step": 37500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.2306097995401406,
|
| 834 |
+
"grad_norm": 6.622528553009033,
|
| 835 |
+
"learning_rate": 4.384970368211406e-05,
|
| 836 |
+
"loss": 4.9896,
|
| 837 |
+
"step": 38000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.2306097995401406,
|
| 841 |
+
"eval_loss": 14.330415725708008,
|
| 842 |
+
"eval_runtime": 20.3174,
|
| 843 |
+
"eval_samples_per_second": 2701.865,
|
| 844 |
+
"eval_steps_per_second": 168.87,
|
| 845 |
+
"step": 38000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.2468020337446162,
|
| 849 |
+
"grad_norm": 7.867303371429443,
|
| 850 |
+
"learning_rate": 4.376874251109168e-05,
|
| 851 |
+
"loss": 4.9851,
|
| 852 |
+
"step": 38500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.2629942679490918,
|
| 856 |
+
"grad_norm": 7.329415321350098,
|
| 857 |
+
"learning_rate": 4.368778134006931e-05,
|
| 858 |
+
"loss": 4.969,
|
| 859 |
+
"step": 39000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.2629942679490918,
|
| 863 |
+
"eval_loss": 14.989124298095703,
|
| 864 |
+
"eval_runtime": 20.3265,
|
| 865 |
+
"eval_samples_per_second": 2700.663,
|
| 866 |
+
"eval_steps_per_second": 168.795,
|
| 867 |
+
"step": 39000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.279186502153567,
|
| 871 |
+
"grad_norm": 8.647744178771973,
|
| 872 |
+
"learning_rate": 4.3606820169046924e-05,
|
| 873 |
+
"loss": 4.9547,
|
| 874 |
+
"step": 39500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.2953787363580427,
|
| 878 |
+
"grad_norm": 8.578520774841309,
|
| 879 |
+
"learning_rate": 4.352585899802455e-05,
|
| 880 |
+
"loss": 4.9569,
|
| 881 |
+
"step": 40000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.2953787363580427,
|
| 885 |
+
"eval_loss": 14.283174514770508,
|
| 886 |
+
"eval_runtime": 20.3168,
|
| 887 |
+
"eval_samples_per_second": 2701.954,
|
| 888 |
+
"eval_steps_per_second": 168.875,
|
| 889 |
+
"step": 40000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.3115709705625183,
|
| 893 |
+
"grad_norm": 8.312915802001953,
|
| 894 |
+
"learning_rate": 4.3444897827002176e-05,
|
| 895 |
+
"loss": 4.9647,
|
| 896 |
+
"step": 40500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.3277632047669938,
|
| 900 |
+
"grad_norm": 9.59231185913086,
|
| 901 |
+
"learning_rate": 4.3364098578321836e-05,
|
| 902 |
+
"loss": 4.9462,
|
| 903 |
+
"step": 41000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.3277632047669938,
|
| 907 |
+
"eval_loss": 14.299793243408203,
|
| 908 |
+
"eval_runtime": 20.2951,
|
| 909 |
+
"eval_samples_per_second": 2704.839,
|
| 910 |
+
"eval_steps_per_second": 169.055,
|
| 911 |
+
"step": 41000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.3439554389714692,
|
| 915 |
+
"grad_norm": 7.844625949859619,
|
| 916 |
+
"learning_rate": 4.328313740729946e-05,
|
| 917 |
+
"loss": 4.9147,
|
| 918 |
+
"step": 41500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.3601476731759448,
|
| 922 |
+
"grad_norm": 6.845381736755371,
|
| 923 |
+
"learning_rate": 4.320217623627708e-05,
|
| 924 |
+
"loss": 4.914,
|
| 925 |
+
"step": 42000
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.3601476731759448,
|
| 929 |
+
"eval_loss": 14.049765586853027,
|
| 930 |
+
"eval_runtime": 20.2836,
|
| 931 |
+
"eval_samples_per_second": 2706.371,
|
| 932 |
+
"eval_steps_per_second": 169.151,
|
| 933 |
+
"step": 42000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.3763399073804203,
|
| 937 |
+
"grad_norm": 7.644216537475586,
|
| 938 |
+
"learning_rate": 4.3121215065254704e-05,
|
| 939 |
+
"loss": 4.9066,
|
| 940 |
+
"step": 42500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.392532141584896,
|
| 944 |
+
"grad_norm": 7.950870513916016,
|
| 945 |
+
"learning_rate": 4.304041581657438e-05,
|
| 946 |
+
"loss": 4.8716,
|
| 947 |
+
"step": 43000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.392532141584896,
|
| 951 |
+
"eval_loss": 14.33547306060791,
|
| 952 |
+
"eval_runtime": 20.3142,
|
| 953 |
+
"eval_samples_per_second": 2702.295,
|
| 954 |
+
"eval_steps_per_second": 168.897,
|
| 955 |
+
"step": 43000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.4087243757893715,
|
| 959 |
+
"grad_norm": 7.638858318328857,
|
| 960 |
+
"learning_rate": 4.295945464555199e-05,
|
| 961 |
+
"loss": 4.8557,
|
| 962 |
+
"step": 43500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.424916609993847,
|
| 966 |
+
"grad_norm": 9.173840522766113,
|
| 967 |
+
"learning_rate": 4.2878493474529616e-05,
|
| 968 |
+
"loss": 4.8394,
|
| 969 |
+
"step": 44000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.424916609993847,
|
| 973 |
+
"eval_loss": 13.498611450195312,
|
| 974 |
+
"eval_runtime": 20.3548,
|
| 975 |
+
"eval_samples_per_second": 2696.904,
|
| 976 |
+
"eval_steps_per_second": 168.56,
|
| 977 |
+
"step": 44000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.4411088441983224,
|
| 981 |
+
"grad_norm": 8.224470138549805,
|
| 982 |
+
"learning_rate": 4.279753230350724e-05,
|
| 983 |
+
"loss": 4.8216,
|
| 984 |
+
"step": 44500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.457301078402798,
|
| 988 |
+
"grad_norm": 7.497710704803467,
|
| 989 |
+
"learning_rate": 4.2716733054826905e-05,
|
| 990 |
+
"loss": 4.8237,
|
| 991 |
+
"step": 45000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.457301078402798,
|
| 995 |
+
"eval_loss": 13.823565483093262,
|
| 996 |
+
"eval_runtime": 20.2695,
|
| 997 |
+
"eval_samples_per_second": 2708.257,
|
| 998 |
+
"eval_steps_per_second": 169.269,
|
| 999 |
+
"step": 45000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.4734933126072736,
|
| 1003 |
+
"grad_norm": 6.961141586303711,
|
| 1004 |
+
"learning_rate": 4.2635771883804535e-05,
|
| 1005 |
+
"loss": 4.8119,
|
| 1006 |
+
"step": 45500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.4896855468117491,
|
| 1010 |
+
"grad_norm": 6.934360504150391,
|
| 1011 |
+
"learning_rate": 4.255481071278215e-05,
|
| 1012 |
+
"loss": 4.7972,
|
| 1013 |
+
"step": 46000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.4896855468117491,
|
| 1017 |
+
"eval_loss": 14.0670804977417,
|
| 1018 |
+
"eval_runtime": 20.2732,
|
| 1019 |
+
"eval_samples_per_second": 2707.759,
|
| 1020 |
+
"eval_steps_per_second": 169.238,
|
| 1021 |
+
"step": 46000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.5058777810162245,
|
| 1025 |
+
"grad_norm": 7.600714206695557,
|
| 1026 |
+
"learning_rate": 4.247384954175977e-05,
|
| 1027 |
+
"loss": 4.8131,
|
| 1028 |
+
"step": 46500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.5220700152207,
|
| 1032 |
+
"grad_norm": 8.766816139221191,
|
| 1033 |
+
"learning_rate": 4.239305029307944e-05,
|
| 1034 |
+
"loss": 4.778,
|
| 1035 |
+
"step": 47000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.5220700152207,
|
| 1039 |
+
"eval_loss": 13.546905517578125,
|
| 1040 |
+
"eval_runtime": 20.3029,
|
| 1041 |
+
"eval_samples_per_second": 2703.795,
|
| 1042 |
+
"eval_steps_per_second": 168.99,
|
| 1043 |
+
"step": 47000
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.5382622494251756,
|
| 1047 |
+
"grad_norm": 8.299079895019531,
|
| 1048 |
+
"learning_rate": 4.231208912205706e-05,
|
| 1049 |
+
"loss": 4.7336,
|
| 1050 |
+
"step": 47500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.5544544836296512,
|
| 1054 |
+
"grad_norm": 8.333426475524902,
|
| 1055 |
+
"learning_rate": 4.2231127951034685e-05,
|
| 1056 |
+
"loss": 4.7541,
|
| 1057 |
+
"step": 48000
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.5544544836296512,
|
| 1061 |
+
"eval_loss": 13.711235046386719,
|
| 1062 |
+
"eval_runtime": 20.3064,
|
| 1063 |
+
"eval_samples_per_second": 2703.338,
|
| 1064 |
+
"eval_steps_per_second": 168.962,
|
| 1065 |
+
"step": 48000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.5706467178341268,
|
| 1069 |
+
"grad_norm": 7.705515384674072,
|
| 1070 |
+
"learning_rate": 4.215016678001231e-05,
|
| 1071 |
+
"loss": 4.7901,
|
| 1072 |
+
"step": 48500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.5868389520386024,
|
| 1076 |
+
"grad_norm": 6.669991493225098,
|
| 1077 |
+
"learning_rate": 4.206920560898993e-05,
|
| 1078 |
+
"loss": 4.7544,
|
| 1079 |
+
"step": 49000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.5868389520386024,
|
| 1083 |
+
"eval_loss": 13.069415092468262,
|
| 1084 |
+
"eval_runtime": 20.3123,
|
| 1085 |
+
"eval_samples_per_second": 2702.548,
|
| 1086 |
+
"eval_steps_per_second": 168.912,
|
| 1087 |
+
"step": 49000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.603031186243078,
|
| 1091 |
+
"grad_norm": 6.958492279052734,
|
| 1092 |
+
"learning_rate": 4.19884063603096e-05,
|
| 1093 |
+
"loss": 4.7175,
|
| 1094 |
+
"step": 49500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.6192234204475535,
|
| 1098 |
+
"grad_norm": 9.244942665100098,
|
| 1099 |
+
"learning_rate": 4.190744518928722e-05,
|
| 1100 |
+
"loss": 4.7092,
|
| 1101 |
+
"step": 50000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.6192234204475535,
|
| 1105 |
+
"eval_loss": 13.0497465133667,
|
| 1106 |
+
"eval_runtime": 20.3211,
|
| 1107 |
+
"eval_samples_per_second": 2701.382,
|
| 1108 |
+
"eval_steps_per_second": 168.839,
|
| 1109 |
+
"step": 50000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.6354156546520289,
|
| 1113 |
+
"grad_norm": 8.372320175170898,
|
| 1114 |
+
"learning_rate": 4.182648401826484e-05,
|
| 1115 |
+
"loss": 4.7401,
|
| 1116 |
+
"step": 50500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.6516078888565044,
|
| 1120 |
+
"grad_norm": 7.373213768005371,
|
| 1121 |
+
"learning_rate": 4.1745522847242465e-05,
|
| 1122 |
+
"loss": 4.7252,
|
| 1123 |
+
"step": 51000
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.6516078888565044,
|
| 1127 |
+
"eval_loss": 13.589052200317383,
|
| 1128 |
+
"eval_runtime": 20.3142,
|
| 1129 |
+
"eval_samples_per_second": 2702.302,
|
| 1130 |
+
"eval_steps_per_second": 168.897,
|
| 1131 |
+
"step": 51000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.6678001230609798,
|
| 1135 |
+
"grad_norm": 9.22149658203125,
|
| 1136 |
+
"learning_rate": 4.166472359856213e-05,
|
| 1137 |
+
"loss": 4.6795,
|
| 1138 |
+
"step": 51500
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.6839923572654554,
|
| 1142 |
+
"grad_norm": 5.994777202606201,
|
| 1143 |
+
"learning_rate": 4.1583762427539754e-05,
|
| 1144 |
+
"loss": 4.7021,
|
| 1145 |
+
"step": 52000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.6839923572654554,
|
| 1149 |
+
"eval_loss": 13.31000804901123,
|
| 1150 |
+
"eval_runtime": 20.2902,
|
| 1151 |
+
"eval_samples_per_second": 2705.498,
|
| 1152 |
+
"eval_steps_per_second": 169.097,
|
| 1153 |
+
"step": 52000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 1.700184591469931,
|
| 1157 |
+
"grad_norm": 8.134748458862305,
|
| 1158 |
+
"learning_rate": 4.150280125651738e-05,
|
| 1159 |
+
"loss": 4.7013,
|
| 1160 |
+
"step": 52500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.7163768256744065,
|
| 1164 |
+
"grad_norm": 8.395650863647461,
|
| 1165 |
+
"learning_rate": 4.1421840085495e-05,
|
| 1166 |
+
"loss": 4.6976,
|
| 1167 |
+
"step": 53000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.7163768256744065,
|
| 1171 |
+
"eval_loss": 13.707457542419434,
|
| 1172 |
+
"eval_runtime": 20.3052,
|
| 1173 |
+
"eval_samples_per_second": 2703.49,
|
| 1174 |
+
"eval_steps_per_second": 168.971,
|
| 1175 |
+
"step": 53000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.732569059878882,
|
| 1179 |
+
"grad_norm": 9.668176651000977,
|
| 1180 |
+
"learning_rate": 4.1341040836814666e-05,
|
| 1181 |
+
"loss": 4.6889,
|
| 1182 |
+
"step": 53500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.7487612940833577,
|
| 1186 |
+
"grad_norm": 7.348442554473877,
|
| 1187 |
+
"learning_rate": 4.126007966579229e-05,
|
| 1188 |
+
"loss": 4.6465,
|
| 1189 |
+
"step": 54000
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.7487612940833577,
|
| 1193 |
+
"eval_loss": 13.285728454589844,
|
| 1194 |
+
"eval_runtime": 20.3053,
|
| 1195 |
+
"eval_samples_per_second": 2703.483,
|
| 1196 |
+
"eval_steps_per_second": 168.971,
|
| 1197 |
+
"step": 54000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.7649535282878333,
|
| 1201 |
+
"grad_norm": 7.7653889656066895,
|
| 1202 |
+
"learning_rate": 4.117911849476991e-05,
|
| 1203 |
+
"loss": 4.6537,
|
| 1204 |
+
"step": 54500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.7811457624923088,
|
| 1208 |
+
"grad_norm": 8.290285110473633,
|
| 1209 |
+
"learning_rate": 4.1098157323747534e-05,
|
| 1210 |
+
"loss": 4.6468,
|
| 1211 |
+
"step": 55000
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.7811457624923088,
|
| 1215 |
+
"eval_loss": 13.134732246398926,
|
| 1216 |
+
"eval_runtime": 20.3013,
|
| 1217 |
+
"eval_samples_per_second": 2704.018,
|
| 1218 |
+
"eval_steps_per_second": 169.004,
|
| 1219 |
+
"step": 55000
|
| 1220 |
+
}
|
| 1221 |
+
],
|
| 1222 |
+
"logging_steps": 500,
|
| 1223 |
+
"max_steps": 308790,
|
| 1224 |
+
"num_input_tokens_seen": 0,
|
| 1225 |
+
"num_train_epochs": 10,
|
| 1226 |
+
"save_steps": 5000,
|
| 1227 |
+
"stateful_callbacks": {
|
| 1228 |
+
"TrainerControl": {
|
| 1229 |
+
"args": {
|
| 1230 |
+
"should_epoch_stop": false,
|
| 1231 |
+
"should_evaluate": false,
|
| 1232 |
+
"should_log": false,
|
| 1233 |
+
"should_save": true,
|
| 1234 |
+
"should_training_stop": false
|
| 1235 |
+
},
|
| 1236 |
+
"attributes": {}
|
| 1237 |
+
}
|
| 1238 |
+
},
|
| 1239 |
+
"total_flos": 4320645675220992.0,
|
| 1240 |
+
"train_batch_size": 16,
|
| 1241 |
+
"trial_name": null,
|
| 1242 |
+
"trial_params": null
|
| 1243 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:944a39203183756575dda434a2ab60e2e05d73559e20ed8b7c45f952dee1c16d
|
| 3 |
+
size 5304
|