Upload folder using huggingface_hub
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +775 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "intfloat/e5-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.43.0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864d50e4126e45f39f26e7b21405955edb547e8d8d4b1a1d3a833b044e240078
|
| 3 |
+
size 871297978
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e715e1af5cd5cc6baafc2f28a200a9f068b4fb59458acc6255a2518dc5b2b59b
|
| 3 |
+
size 437996134
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:038235e47710842766eec88106fd85eccb3c65e3759cd8a2b2471421a7d95501
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c3a4cacee02650c99cba1547310e127667d610f1d02da2c6f1f883440f9445
|
| 3 |
+
size 1064
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,775 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 26.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1066,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24390243902439024,
|
| 13 |
+
"grad_norm": 153.20391845703125,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 14.3989,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4878048780487805,
|
| 20 |
+
"grad_norm": 98.0101318359375,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 9.4888,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7317073170731707,
|
| 27 |
+
"grad_norm": 66.21862030029297,
|
| 28 |
+
"learning_rate": 1e-05,
|
| 29 |
+
"loss": 7.1045,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.975609756097561,
|
| 34 |
+
"grad_norm": 51.25503921508789,
|
| 35 |
+
"learning_rate": 1e-05,
|
| 36 |
+
"loss": 6.0752,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.2195121951219512,
|
| 41 |
+
"grad_norm": 42.94609451293945,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 5.4784,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4634146341463414,
|
| 48 |
+
"grad_norm": 23.749080657958984,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 5.0407,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.7073170731707317,
|
| 55 |
+
"grad_norm": 21.82228660583496,
|
| 56 |
+
"learning_rate": 1e-05,
|
| 57 |
+
"loss": 4.7377,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.951219512195122,
|
| 62 |
+
"grad_norm": 16.767141342163086,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 4.6813,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.1951219512195124,
|
| 69 |
+
"grad_norm": 15.738419532775879,
|
| 70 |
+
"learning_rate": 1e-05,
|
| 71 |
+
"loss": 4.5301,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.4390243902439024,
|
| 76 |
+
"grad_norm": 15.758868217468262,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 4.4416,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.682926829268293,
|
| 83 |
+
"grad_norm": 14.666833877563477,
|
| 84 |
+
"learning_rate": 1e-05,
|
| 85 |
+
"loss": 4.324,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.926829268292683,
|
| 90 |
+
"grad_norm": 14.121631622314453,
|
| 91 |
+
"learning_rate": 1e-05,
|
| 92 |
+
"loss": 4.2509,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.1707317073170733,
|
| 97 |
+
"grad_norm": 13.137129783630371,
|
| 98 |
+
"learning_rate": 1e-05,
|
| 99 |
+
"loss": 4.2184,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.4146341463414633,
|
| 104 |
+
"grad_norm": 13.16901683807373,
|
| 105 |
+
"learning_rate": 1e-05,
|
| 106 |
+
"loss": 4.2392,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.658536585365854,
|
| 111 |
+
"grad_norm": 12.6273193359375,
|
| 112 |
+
"learning_rate": 1e-05,
|
| 113 |
+
"loss": 4.2731,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.902439024390244,
|
| 118 |
+
"grad_norm": 12.8707275390625,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 4.1833,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.146341463414634,
|
| 125 |
+
"grad_norm": 12.259010314941406,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 4.1131,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.390243902439025,
|
| 132 |
+
"grad_norm": 13.05242919921875,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 4.0821,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.634146341463414,
|
| 139 |
+
"grad_norm": 12.534492492675781,
|
| 140 |
+
"learning_rate": 1e-05,
|
| 141 |
+
"loss": 4.1202,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.878048780487805,
|
| 146 |
+
"grad_norm": 11.910691261291504,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 4.0793,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.121951219512195,
|
| 153 |
+
"grad_norm": 13.948406219482422,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 3.9298,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.365853658536586,
|
| 160 |
+
"grad_norm": 15.066719055175781,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 4.1399,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.609756097560975,
|
| 167 |
+
"grad_norm": 12.302136421203613,
|
| 168 |
+
"learning_rate": 1e-05,
|
| 169 |
+
"loss": 3.9993,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.853658536585366,
|
| 174 |
+
"grad_norm": 12.577598571777344,
|
| 175 |
+
"learning_rate": 1e-05,
|
| 176 |
+
"loss": 3.9465,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.097560975609756,
|
| 181 |
+
"grad_norm": 12.180274963378906,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 3.8803,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.341463414634147,
|
| 188 |
+
"grad_norm": 14.182092666625977,
|
| 189 |
+
"learning_rate": 1e-05,
|
| 190 |
+
"loss": 3.9006,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.585365853658536,
|
| 195 |
+
"grad_norm": 15.906909942626953,
|
| 196 |
+
"learning_rate": 1e-05,
|
| 197 |
+
"loss": 3.8925,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.829268292682927,
|
| 202 |
+
"grad_norm": 11.003096580505371,
|
| 203 |
+
"learning_rate": 1e-05,
|
| 204 |
+
"loss": 3.9061,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.073170731707317,
|
| 209 |
+
"grad_norm": 12.84813404083252,
|
| 210 |
+
"learning_rate": 1e-05,
|
| 211 |
+
"loss": 3.8672,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.317073170731708,
|
| 216 |
+
"grad_norm": 13.7793607711792,
|
| 217 |
+
"learning_rate": 1e-05,
|
| 218 |
+
"loss": 3.8265,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.560975609756097,
|
| 223 |
+
"grad_norm": 15.24905776977539,
|
| 224 |
+
"learning_rate": 1e-05,
|
| 225 |
+
"loss": 3.7881,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.804878048780488,
|
| 230 |
+
"grad_norm": 13.246805191040039,
|
| 231 |
+
"learning_rate": 1e-05,
|
| 232 |
+
"loss": 3.7045,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.048780487804878,
|
| 237 |
+
"grad_norm": 13.150066375732422,
|
| 238 |
+
"learning_rate": 1e-05,
|
| 239 |
+
"loss": 3.6827,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.292682926829269,
|
| 244 |
+
"grad_norm": 16.51359748840332,
|
| 245 |
+
"learning_rate": 1e-05,
|
| 246 |
+
"loss": 3.7162,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.536585365853659,
|
| 251 |
+
"grad_norm": 12.987756729125977,
|
| 252 |
+
"learning_rate": 1e-05,
|
| 253 |
+
"loss": 3.8721,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.78048780487805,
|
| 258 |
+
"grad_norm": 12.487648010253906,
|
| 259 |
+
"learning_rate": 1e-05,
|
| 260 |
+
"loss": 3.7642,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.024390243902438,
|
| 265 |
+
"grad_norm": 13.399900436401367,
|
| 266 |
+
"learning_rate": 1e-05,
|
| 267 |
+
"loss": 3.5614,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.268292682926829,
|
| 272 |
+
"grad_norm": 12.230491638183594,
|
| 273 |
+
"learning_rate": 1e-05,
|
| 274 |
+
"loss": 3.6516,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.512195121951219,
|
| 279 |
+
"grad_norm": 12.481654167175293,
|
| 280 |
+
"learning_rate": 1e-05,
|
| 281 |
+
"loss": 3.5442,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.75609756097561,
|
| 286 |
+
"grad_norm": 12.716032028198242,
|
| 287 |
+
"learning_rate": 1e-05,
|
| 288 |
+
"loss": 3.7811,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 10.0,
|
| 293 |
+
"grad_norm": 16.65569305419922,
|
| 294 |
+
"learning_rate": 1e-05,
|
| 295 |
+
"loss": 3.6132,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 10.24390243902439,
|
| 300 |
+
"grad_norm": 12.62430477142334,
|
| 301 |
+
"learning_rate": 1e-05,
|
| 302 |
+
"loss": 3.6959,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 10.487804878048781,
|
| 307 |
+
"grad_norm": 12.553898811340332,
|
| 308 |
+
"learning_rate": 1e-05,
|
| 309 |
+
"loss": 3.6677,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 10.731707317073171,
|
| 314 |
+
"grad_norm": 14.134100914001465,
|
| 315 |
+
"learning_rate": 1e-05,
|
| 316 |
+
"loss": 3.678,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 10.975609756097562,
|
| 321 |
+
"grad_norm": 12.144598960876465,
|
| 322 |
+
"learning_rate": 1e-05,
|
| 323 |
+
"loss": 3.6878,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.21951219512195,
|
| 328 |
+
"grad_norm": 13.102901458740234,
|
| 329 |
+
"learning_rate": 1e-05,
|
| 330 |
+
"loss": 3.4404,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.463414634146341,
|
| 335 |
+
"grad_norm": 12.662181854248047,
|
| 336 |
+
"learning_rate": 1e-05,
|
| 337 |
+
"loss": 3.5925,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 11.707317073170731,
|
| 342 |
+
"grad_norm": 12.018118858337402,
|
| 343 |
+
"learning_rate": 1e-05,
|
| 344 |
+
"loss": 3.5211,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.951219512195122,
|
| 349 |
+
"grad_norm": 13.634488105773926,
|
| 350 |
+
"learning_rate": 1e-05,
|
| 351 |
+
"loss": 3.6878,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 12.195121951219512,
|
| 356 |
+
"grad_norm": 13.962358474731445,
|
| 357 |
+
"learning_rate": 1e-05,
|
| 358 |
+
"loss": 3.4749,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 12.439024390243903,
|
| 363 |
+
"grad_norm": 13.360703468322754,
|
| 364 |
+
"learning_rate": 1e-05,
|
| 365 |
+
"loss": 3.3638,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 12.682926829268293,
|
| 370 |
+
"grad_norm": 12.813912391662598,
|
| 371 |
+
"learning_rate": 1e-05,
|
| 372 |
+
"loss": 3.6672,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 12.926829268292684,
|
| 377 |
+
"grad_norm": 12.291671752929688,
|
| 378 |
+
"learning_rate": 1e-05,
|
| 379 |
+
"loss": 3.5141,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 13.170731707317072,
|
| 384 |
+
"grad_norm": 13.497099876403809,
|
| 385 |
+
"learning_rate": 1e-05,
|
| 386 |
+
"loss": 3.4268,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 13.414634146341463,
|
| 391 |
+
"grad_norm": 11.689033508300781,
|
| 392 |
+
"learning_rate": 1e-05,
|
| 393 |
+
"loss": 3.4772,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 13.658536585365853,
|
| 398 |
+
"grad_norm": 13.340636253356934,
|
| 399 |
+
"learning_rate": 1e-05,
|
| 400 |
+
"loss": 3.3453,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 13.902439024390244,
|
| 405 |
+
"grad_norm": 14.993213653564453,
|
| 406 |
+
"learning_rate": 1e-05,
|
| 407 |
+
"loss": 3.6322,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.146341463414634,
|
| 412 |
+
"grad_norm": 15.0778169631958,
|
| 413 |
+
"learning_rate": 1e-05,
|
| 414 |
+
"loss": 3.3216,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.390243902439025,
|
| 419 |
+
"grad_norm": 13.393571853637695,
|
| 420 |
+
"learning_rate": 1e-05,
|
| 421 |
+
"loss": 3.2652,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 14.634146341463415,
|
| 426 |
+
"grad_norm": 13.353214263916016,
|
| 427 |
+
"learning_rate": 1e-05,
|
| 428 |
+
"loss": 3.3916,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.878048780487806,
|
| 433 |
+
"grad_norm": 13.477783203125,
|
| 434 |
+
"learning_rate": 1e-05,
|
| 435 |
+
"loss": 3.5582,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 15.121951219512194,
|
| 440 |
+
"grad_norm": 13.947030067443848,
|
| 441 |
+
"learning_rate": 1e-05,
|
| 442 |
+
"loss": 3.1888,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 15.365853658536585,
|
| 447 |
+
"grad_norm": 13.27822208404541,
|
| 448 |
+
"learning_rate": 1e-05,
|
| 449 |
+
"loss": 3.3959,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 15.609756097560975,
|
| 454 |
+
"grad_norm": 12.724740982055664,
|
| 455 |
+
"learning_rate": 1e-05,
|
| 456 |
+
"loss": 3.4102,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 15.853658536585366,
|
| 461 |
+
"grad_norm": 12.53013801574707,
|
| 462 |
+
"learning_rate": 1e-05,
|
| 463 |
+
"loss": 3.3826,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 16.097560975609756,
|
| 468 |
+
"grad_norm": 12.549883842468262,
|
| 469 |
+
"learning_rate": 1e-05,
|
| 470 |
+
"loss": 3.1557,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 16.341463414634145,
|
| 475 |
+
"grad_norm": 14.903629302978516,
|
| 476 |
+
"learning_rate": 1e-05,
|
| 477 |
+
"loss": 3.215,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 16.585365853658537,
|
| 482 |
+
"grad_norm": 13.426742553710938,
|
| 483 |
+
"learning_rate": 1e-05,
|
| 484 |
+
"loss": 3.2223,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 16.829268292682926,
|
| 489 |
+
"grad_norm": 12.214171409606934,
|
| 490 |
+
"learning_rate": 1e-05,
|
| 491 |
+
"loss": 3.3669,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 17.073170731707318,
|
| 496 |
+
"grad_norm": 13.474701881408691,
|
| 497 |
+
"learning_rate": 1e-05,
|
| 498 |
+
"loss": 3.1725,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 17.317073170731707,
|
| 503 |
+
"grad_norm": 13.971524238586426,
|
| 504 |
+
"learning_rate": 1e-05,
|
| 505 |
+
"loss": 3.3139,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 17.5609756097561,
|
| 510 |
+
"grad_norm": 13.29129695892334,
|
| 511 |
+
"learning_rate": 1e-05,
|
| 512 |
+
"loss": 3.2124,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 17.804878048780488,
|
| 517 |
+
"grad_norm": 14.565364837646484,
|
| 518 |
+
"learning_rate": 1e-05,
|
| 519 |
+
"loss": 3.1354,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 18.048780487804876,
|
| 524 |
+
"grad_norm": 14.526548385620117,
|
| 525 |
+
"learning_rate": 1e-05,
|
| 526 |
+
"loss": 3.0789,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 18.29268292682927,
|
| 531 |
+
"grad_norm": 14.852441787719727,
|
| 532 |
+
"learning_rate": 1e-05,
|
| 533 |
+
"loss": 3.1379,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 18.536585365853657,
|
| 538 |
+
"grad_norm": 14.984235763549805,
|
| 539 |
+
"learning_rate": 1e-05,
|
| 540 |
+
"loss": 3.0832,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 18.78048780487805,
|
| 545 |
+
"grad_norm": 13.381596565246582,
|
| 546 |
+
"learning_rate": 1e-05,
|
| 547 |
+
"loss": 3.0988,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 19.024390243902438,
|
| 552 |
+
"grad_norm": 13.721541404724121,
|
| 553 |
+
"learning_rate": 1e-05,
|
| 554 |
+
"loss": 3.0601,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 19.26829268292683,
|
| 559 |
+
"grad_norm": 14.160118103027344,
|
| 560 |
+
"learning_rate": 1e-05,
|
| 561 |
+
"loss": 3.1213,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 19.51219512195122,
|
| 566 |
+
"grad_norm": 14.012876510620117,
|
| 567 |
+
"learning_rate": 1e-05,
|
| 568 |
+
"loss": 3.2049,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 19.75609756097561,
|
| 573 |
+
"grad_norm": 14.465662002563477,
|
| 574 |
+
"learning_rate": 1e-05,
|
| 575 |
+
"loss": 3.1248,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 20.0,
|
| 580 |
+
"grad_norm": 19.51372718811035,
|
| 581 |
+
"learning_rate": 1e-05,
|
| 582 |
+
"loss": 2.9954,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 20.24390243902439,
|
| 587 |
+
"grad_norm": 13.775348663330078,
|
| 588 |
+
"learning_rate": 1e-05,
|
| 589 |
+
"loss": 3.1184,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 20.48780487804878,
|
| 594 |
+
"grad_norm": 15.329011917114258,
|
| 595 |
+
"learning_rate": 1e-05,
|
| 596 |
+
"loss": 3.1376,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 20.73170731707317,
|
| 601 |
+
"grad_norm": 14.254768371582031,
|
| 602 |
+
"learning_rate": 1e-05,
|
| 603 |
+
"loss": 2.9425,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 20.975609756097562,
|
| 608 |
+
"grad_norm": 14.885010719299316,
|
| 609 |
+
"learning_rate": 1e-05,
|
| 610 |
+
"loss": 3.0427,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 21.21951219512195,
|
| 615 |
+
"grad_norm": 13.358927726745605,
|
| 616 |
+
"learning_rate": 1e-05,
|
| 617 |
+
"loss": 3.0594,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 21.463414634146343,
|
| 622 |
+
"grad_norm": 14.775203704833984,
|
| 623 |
+
"learning_rate": 1e-05,
|
| 624 |
+
"loss": 3.0176,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 21.70731707317073,
|
| 629 |
+
"grad_norm": 14.861948013305664,
|
| 630 |
+
"learning_rate": 1e-05,
|
| 631 |
+
"loss": 2.9453,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 21.951219512195124,
|
| 636 |
+
"grad_norm": 13.654282569885254,
|
| 637 |
+
"learning_rate": 1e-05,
|
| 638 |
+
"loss": 3.0511,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 22.195121951219512,
|
| 643 |
+
"grad_norm": 14.70966911315918,
|
| 644 |
+
"learning_rate": 1e-05,
|
| 645 |
+
"loss": 3.023,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 22.4390243902439,
|
| 650 |
+
"grad_norm": 14.872281074523926,
|
| 651 |
+
"learning_rate": 1e-05,
|
| 652 |
+
"loss": 2.9731,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 22.682926829268293,
|
| 657 |
+
"grad_norm": 14.201629638671875,
|
| 658 |
+
"learning_rate": 1e-05,
|
| 659 |
+
"loss": 3.0614,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 22.926829268292682,
|
| 664 |
+
"grad_norm": 16.941543579101562,
|
| 665 |
+
"learning_rate": 1e-05,
|
| 666 |
+
"loss": 3.0268,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 23.170731707317074,
|
| 671 |
+
"grad_norm": 13.769314765930176,
|
| 672 |
+
"learning_rate": 1e-05,
|
| 673 |
+
"loss": 2.9794,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 23.414634146341463,
|
| 678 |
+
"grad_norm": 15.23621654510498,
|
| 679 |
+
"learning_rate": 1e-05,
|
| 680 |
+
"loss": 2.9424,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 23.658536585365855,
|
| 685 |
+
"grad_norm": 14.478521347045898,
|
| 686 |
+
"learning_rate": 1e-05,
|
| 687 |
+
"loss": 2.8599,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 23.902439024390244,
|
| 692 |
+
"grad_norm": 15.78727912902832,
|
| 693 |
+
"learning_rate": 1e-05,
|
| 694 |
+
"loss": 2.9107,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 24.146341463414632,
|
| 699 |
+
"grad_norm": 13.50251579284668,
|
| 700 |
+
"learning_rate": 1e-05,
|
| 701 |
+
"loss": 2.9054,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 24.390243902439025,
|
| 706 |
+
"grad_norm": 14.051477432250977,
|
| 707 |
+
"learning_rate": 1e-05,
|
| 708 |
+
"loss": 2.9868,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 24.634146341463413,
|
| 713 |
+
"grad_norm": 14.178876876831055,
|
| 714 |
+
"learning_rate": 1e-05,
|
| 715 |
+
"loss": 3.0255,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 24.878048780487806,
|
| 720 |
+
"grad_norm": 15.032842636108398,
|
| 721 |
+
"learning_rate": 1e-05,
|
| 722 |
+
"loss": 2.9312,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 25.121951219512194,
|
| 727 |
+
"grad_norm": 16.624441146850586,
|
| 728 |
+
"learning_rate": 1e-05,
|
| 729 |
+
"loss": 2.8341,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 25.365853658536587,
|
| 734 |
+
"grad_norm": 14.353311538696289,
|
| 735 |
+
"learning_rate": 1e-05,
|
| 736 |
+
"loss": 2.9496,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 25.609756097560975,
|
| 741 |
+
"grad_norm": 16.341983795166016,
|
| 742 |
+
"learning_rate": 1e-05,
|
| 743 |
+
"loss": 2.7901,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 25.853658536585368,
|
| 748 |
+
"grad_norm": 15.729475021362305,
|
| 749 |
+
"learning_rate": 1e-05,
|
| 750 |
+
"loss": 2.8535,
|
| 751 |
+
"step": 1060
|
| 752 |
+
}
|
| 753 |
+
],
|
| 754 |
+
"logging_steps": 10,
|
| 755 |
+
"max_steps": 1230,
|
| 756 |
+
"num_input_tokens_seen": 0,
|
| 757 |
+
"num_train_epochs": 30,
|
| 758 |
+
"save_steps": 500,
|
| 759 |
+
"stateful_callbacks": {
|
| 760 |
+
"TrainerControl": {
|
| 761 |
+
"args": {
|
| 762 |
+
"should_epoch_stop": false,
|
| 763 |
+
"should_evaluate": false,
|
| 764 |
+
"should_log": false,
|
| 765 |
+
"should_save": true,
|
| 766 |
+
"should_training_stop": false
|
| 767 |
+
},
|
| 768 |
+
"attributes": {}
|
| 769 |
+
}
|
| 770 |
+
},
|
| 771 |
+
"total_flos": 0.0,
|
| 772 |
+
"train_batch_size": 64,
|
| 773 |
+
"trial_name": null,
|
| 774 |
+
"trial_params": null
|
| 775 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c028c4876049bc6bb78a424268085afa67f4ccb752a59989169c4bb9542f3be8
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|