Upload folder using huggingface_hub
Browse files- config.json +41 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +551 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f50327dcaa38e2ef3962b5e6a7012c73a25cddaa46cbf86c2bb71064716ceed
|
| 3 |
+
size 409103316
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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": false,
|
| 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": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,551 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 5500,
|
| 3 |
+
"best_metric": 0.7810193585711508,
|
| 4 |
+
"best_model_checkpoint": "/Users/wangyiqiu/Desktop/program/\u795e\u7ecf\u7f51\u7edc\u62d3\u6251/results/checkpoint-5500",
|
| 5 |
+
"epoch": 0.3474415666456096,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 5500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006317119393556538,
|
| 14 |
+
"grad_norm": 13.061114311218262,
|
| 15 |
+
"learning_rate": 4.169298799747316e-07,
|
| 16 |
+
"loss": 1.354,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012634238787113077,
|
| 21 |
+
"grad_norm": 13.682186126708984,
|
| 22 |
+
"learning_rate": 8.380711728785009e-07,
|
| 23 |
+
"loss": 1.0853,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018951358180669616,
|
| 28 |
+
"grad_norm": 4.851679801940918,
|
| 29 |
+
"learning_rate": 1.2592124657822702e-06,
|
| 30 |
+
"loss": 0.9111,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.025268477574226154,
|
| 35 |
+
"grad_norm": 5.82253360748291,
|
| 36 |
+
"learning_rate": 1.6803537586860393e-06,
|
| 37 |
+
"loss": 0.7179,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03158559696778269,
|
| 42 |
+
"grad_norm": 5.032683372497559,
|
| 43 |
+
"learning_rate": 2.1014950515898086e-06,
|
| 44 |
+
"loss": 0.6422,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03158559696778269,
|
| 49 |
+
"eval_accuracy": 0.7368075050637859,
|
| 50 |
+
"eval_f1": 0.7170832086299176,
|
| 51 |
+
"eval_loss": 0.6070035696029663,
|
| 52 |
+
"eval_precision": 0.7218199142709759,
|
| 53 |
+
"eval_recall": 0.7368075050637859,
|
| 54 |
+
"eval_runtime": 582.5178,
|
| 55 |
+
"eval_samples_per_second": 96.619,
|
| 56 |
+
"eval_steps_per_second": 3.02,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03790271636133923,
|
| 61 |
+
"grad_norm": 7.424877166748047,
|
| 62 |
+
"learning_rate": 2.5226363444935774e-06,
|
| 63 |
+
"loss": 0.6155,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04421983575489577,
|
| 68 |
+
"grad_norm": 16.976255416870117,
|
| 69 |
+
"learning_rate": 2.943777637397347e-06,
|
| 70 |
+
"loss": 0.5944,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05053695514845231,
|
| 75 |
+
"grad_norm": 9.103567123413086,
|
| 76 |
+
"learning_rate": 3.3649189303011164e-06,
|
| 77 |
+
"loss": 0.5812,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.056854074542008845,
|
| 82 |
+
"grad_norm": 7.061375617980957,
|
| 83 |
+
"learning_rate": 3.7860602232048853e-06,
|
| 84 |
+
"loss": 0.5965,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.06317119393556538,
|
| 89 |
+
"grad_norm": 6.224503040313721,
|
| 90 |
+
"learning_rate": 4.207201516108655e-06,
|
| 91 |
+
"loss": 0.5553,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06317119393556538,
|
| 96 |
+
"eval_accuracy": 0.7581642443409972,
|
| 97 |
+
"eval_f1": 0.7448374295446439,
|
| 98 |
+
"eval_loss": 0.5610596537590027,
|
| 99 |
+
"eval_precision": 0.7461287482946488,
|
| 100 |
+
"eval_recall": 0.7581642443409972,
|
| 101 |
+
"eval_runtime": 584.5541,
|
| 102 |
+
"eval_samples_per_second": 96.282,
|
| 103 |
+
"eval_steps_per_second": 3.009,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.06948831332912192,
|
| 108 |
+
"grad_norm": 6.321476459503174,
|
| 109 |
+
"learning_rate": 4.628342809012423e-06,
|
| 110 |
+
"loss": 0.592,
|
| 111 |
+
"step": 1100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07580543272267846,
|
| 115 |
+
"grad_norm": 8.201200485229492,
|
| 116 |
+
"learning_rate": 5.0494841019161935e-06,
|
| 117 |
+
"loss": 0.5518,
|
| 118 |
+
"step": 1200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.082122552116235,
|
| 122 |
+
"grad_norm": 6.514477729797363,
|
| 123 |
+
"learning_rate": 5.470625394819963e-06,
|
| 124 |
+
"loss": 0.5897,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.08843967150979154,
|
| 129 |
+
"grad_norm": 8.077017784118652,
|
| 130 |
+
"learning_rate": 5.891766687723732e-06,
|
| 131 |
+
"loss": 0.5476,
|
| 132 |
+
"step": 1400
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.09475679090334807,
|
| 136 |
+
"grad_norm": 9.256704330444336,
|
| 137 |
+
"learning_rate": 6.3129079806275005e-06,
|
| 138 |
+
"loss": 0.5263,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.09475679090334807,
|
| 143 |
+
"eval_accuracy": 0.7675278064034683,
|
| 144 |
+
"eval_f1": 0.7632915279870514,
|
| 145 |
+
"eval_loss": 0.5426821112632751,
|
| 146 |
+
"eval_precision": 0.760979358962669,
|
| 147 |
+
"eval_recall": 0.7675278064034683,
|
| 148 |
+
"eval_runtime": 587.2504,
|
| 149 |
+
"eval_samples_per_second": 95.84,
|
| 150 |
+
"eval_steps_per_second": 2.995,
|
| 151 |
+
"step": 1500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10107391029690461,
|
| 155 |
+
"grad_norm": 6.117814064025879,
|
| 156 |
+
"learning_rate": 6.73404927353127e-06,
|
| 157 |
+
"loss": 0.5563,
|
| 158 |
+
"step": 1600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.10739102969046115,
|
| 162 |
+
"grad_norm": 9.015992164611816,
|
| 163 |
+
"learning_rate": 7.15519056643504e-06,
|
| 164 |
+
"loss": 0.5622,
|
| 165 |
+
"step": 1700
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11370814908401769,
|
| 169 |
+
"grad_norm": 8.684099197387695,
|
| 170 |
+
"learning_rate": 7.576331859338809e-06,
|
| 171 |
+
"loss": 0.5483,
|
| 172 |
+
"step": 1800
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.12002526847757422,
|
| 176 |
+
"grad_norm": 5.517951488494873,
|
| 177 |
+
"learning_rate": 7.997473152242578e-06,
|
| 178 |
+
"loss": 0.5467,
|
| 179 |
+
"step": 1900
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.12634238787113075,
|
| 183 |
+
"grad_norm": 4.840009689331055,
|
| 184 |
+
"learning_rate": 8.418614445146347e-06,
|
| 185 |
+
"loss": 0.5472,
|
| 186 |
+
"step": 2000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.12634238787113075,
|
| 190 |
+
"eval_accuracy": 0.7682740485412743,
|
| 191 |
+
"eval_f1": 0.7644619158467771,
|
| 192 |
+
"eval_loss": 0.5479554533958435,
|
| 193 |
+
"eval_precision": 0.7616941910129872,
|
| 194 |
+
"eval_recall": 0.7682740485412743,
|
| 195 |
+
"eval_runtime": 594.3974,
|
| 196 |
+
"eval_samples_per_second": 94.687,
|
| 197 |
+
"eval_steps_per_second": 2.959,
|
| 198 |
+
"step": 2000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1326595072646873,
|
| 202 |
+
"grad_norm": 9.188036918640137,
|
| 203 |
+
"learning_rate": 8.839755738050117e-06,
|
| 204 |
+
"loss": 0.5436,
|
| 205 |
+
"step": 2100
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13897662665824384,
|
| 209 |
+
"grad_norm": 5.845507621765137,
|
| 210 |
+
"learning_rate": 9.260897030953885e-06,
|
| 211 |
+
"loss": 0.5684,
|
| 212 |
+
"step": 2200
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14529374605180037,
|
| 216 |
+
"grad_norm": 6.014614105224609,
|
| 217 |
+
"learning_rate": 9.682038323857656e-06,
|
| 218 |
+
"loss": 0.5268,
|
| 219 |
+
"step": 2300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15161086544535693,
|
| 223 |
+
"grad_norm": 5.183818817138672,
|
| 224 |
+
"learning_rate": 1.0103179616761426e-05,
|
| 225 |
+
"loss": 0.5505,
|
| 226 |
+
"step": 2400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15792798483891346,
|
| 230 |
+
"grad_norm": 4.270262718200684,
|
| 231 |
+
"learning_rate": 1.0524320909665192e-05,
|
| 232 |
+
"loss": 0.5327,
|
| 233 |
+
"step": 2500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15792798483891346,
|
| 237 |
+
"eval_accuracy": 0.7718631178707225,
|
| 238 |
+
"eval_f1": 0.7701652961241094,
|
| 239 |
+
"eval_loss": 0.538950502872467,
|
| 240 |
+
"eval_precision": 0.7692113501499637,
|
| 241 |
+
"eval_recall": 0.7718631178707225,
|
| 242 |
+
"eval_runtime": 598.0361,
|
| 243 |
+
"eval_samples_per_second": 94.111,
|
| 244 |
+
"eval_steps_per_second": 2.941,
|
| 245 |
+
"step": 2500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.16424510423247,
|
| 249 |
+
"grad_norm": 6.861387729644775,
|
| 250 |
+
"learning_rate": 1.0945462202568964e-05,
|
| 251 |
+
"loss": 0.5301,
|
| 252 |
+
"step": 2600
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.17056222362602652,
|
| 256 |
+
"grad_norm": 7.5304670333862305,
|
| 257 |
+
"learning_rate": 1.1366603495472733e-05,
|
| 258 |
+
"loss": 0.5254,
|
| 259 |
+
"step": 2700
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.17687934301958308,
|
| 263 |
+
"grad_norm": 5.88840913772583,
|
| 264 |
+
"learning_rate": 1.1787744788376501e-05,
|
| 265 |
+
"loss": 0.5387,
|
| 266 |
+
"step": 2800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.1831964624131396,
|
| 270 |
+
"grad_norm": 6.836195945739746,
|
| 271 |
+
"learning_rate": 1.2208886081280271e-05,
|
| 272 |
+
"loss": 0.5235,
|
| 273 |
+
"step": 2900
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.18951358180669614,
|
| 277 |
+
"grad_norm": 4.248595237731934,
|
| 278 |
+
"learning_rate": 1.263002737418404e-05,
|
| 279 |
+
"loss": 0.5342,
|
| 280 |
+
"step": 3000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.18951358180669614,
|
| 284 |
+
"eval_accuracy": 0.7746348743825735,
|
| 285 |
+
"eval_f1": 0.7710043344887744,
|
| 286 |
+
"eval_loss": 0.5276312828063965,
|
| 287 |
+
"eval_precision": 0.7689047947812672,
|
| 288 |
+
"eval_recall": 0.7746348743825735,
|
| 289 |
+
"eval_runtime": 599.7353,
|
| 290 |
+
"eval_samples_per_second": 93.845,
|
| 291 |
+
"eval_steps_per_second": 2.933,
|
| 292 |
+
"step": 3000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.19583070120025267,
|
| 296 |
+
"grad_norm": 6.620116710662842,
|
| 297 |
+
"learning_rate": 1.3051168667087808e-05,
|
| 298 |
+
"loss": 0.5432,
|
| 299 |
+
"step": 3100
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.20214782059380923,
|
| 303 |
+
"grad_norm": 4.005882740020752,
|
| 304 |
+
"learning_rate": 1.3472309959991578e-05,
|
| 305 |
+
"loss": 0.5201,
|
| 306 |
+
"step": 3200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.20846493998736576,
|
| 310 |
+
"grad_norm": 3.873512029647827,
|
| 311 |
+
"learning_rate": 1.3893451252895347e-05,
|
| 312 |
+
"loss": 0.5418,
|
| 313 |
+
"step": 3300
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.2147820593809223,
|
| 317 |
+
"grad_norm": 4.081575870513916,
|
| 318 |
+
"learning_rate": 1.4314592545799117e-05,
|
| 319 |
+
"loss": 0.5298,
|
| 320 |
+
"step": 3400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.22109917877447885,
|
| 324 |
+
"grad_norm": 4.8460187911987305,
|
| 325 |
+
"learning_rate": 1.4735733838702885e-05,
|
| 326 |
+
"loss": 0.5397,
|
| 327 |
+
"step": 3500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.22109917877447885,
|
| 331 |
+
"eval_accuracy": 0.7759319142887602,
|
| 332 |
+
"eval_f1": 0.774823898413337,
|
| 333 |
+
"eval_loss": 0.5257604718208313,
|
| 334 |
+
"eval_precision": 0.7763093994740736,
|
| 335 |
+
"eval_recall": 0.7759319142887602,
|
| 336 |
+
"eval_runtime": 594.4851,
|
| 337 |
+
"eval_samples_per_second": 94.674,
|
| 338 |
+
"eval_steps_per_second": 2.959,
|
| 339 |
+
"step": 3500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.22741629816803538,
|
| 343 |
+
"grad_norm": 6.513636589050293,
|
| 344 |
+
"learning_rate": 1.5156875131606654e-05,
|
| 345 |
+
"loss": 0.5385,
|
| 346 |
+
"step": 3600
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2337334175615919,
|
| 350 |
+
"grad_norm": 3.679028272628784,
|
| 351 |
+
"learning_rate": 1.5578016424510425e-05,
|
| 352 |
+
"loss": 0.535,
|
| 353 |
+
"step": 3700
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.24005053695514844,
|
| 357 |
+
"grad_norm": 4.075804233551025,
|
| 358 |
+
"learning_rate": 1.5999157717414192e-05,
|
| 359 |
+
"loss": 0.5328,
|
| 360 |
+
"step": 3800
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.246367656348705,
|
| 364 |
+
"grad_norm": 5.875431060791016,
|
| 365 |
+
"learning_rate": 1.6420299010317962e-05,
|
| 366 |
+
"loss": 0.5185,
|
| 367 |
+
"step": 3900
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2526847757422615,
|
| 371 |
+
"grad_norm": 4.358110427856445,
|
| 372 |
+
"learning_rate": 1.6841440303221732e-05,
|
| 373 |
+
"loss": 0.5258,
|
| 374 |
+
"step": 4000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2526847757422615,
|
| 378 |
+
"eval_accuracy": 0.7764471767172453,
|
| 379 |
+
"eval_f1": 0.7730067867423673,
|
| 380 |
+
"eval_loss": 0.5273372530937195,
|
| 381 |
+
"eval_precision": 0.7717055148059055,
|
| 382 |
+
"eval_recall": 0.7764471767172453,
|
| 383 |
+
"eval_runtime": 619.3303,
|
| 384 |
+
"eval_samples_per_second": 90.876,
|
| 385 |
+
"eval_steps_per_second": 2.84,
|
| 386 |
+
"step": 4000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.25900189513581806,
|
| 390 |
+
"grad_norm": 7.376357078552246,
|
| 391 |
+
"learning_rate": 1.72625815961255e-05,
|
| 392 |
+
"loss": 0.5503,
|
| 393 |
+
"step": 4100
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.2653190145293746,
|
| 397 |
+
"grad_norm": 5.432462215423584,
|
| 398 |
+
"learning_rate": 1.7683722889029273e-05,
|
| 399 |
+
"loss": 0.553,
|
| 400 |
+
"step": 4200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.2716361339229311,
|
| 404 |
+
"grad_norm": 6.945136547088623,
|
| 405 |
+
"learning_rate": 1.810486418193304e-05,
|
| 406 |
+
"loss": 0.5419,
|
| 407 |
+
"step": 4300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.2779532533164877,
|
| 411 |
+
"grad_norm": 6.844213008880615,
|
| 412 |
+
"learning_rate": 1.852600547483681e-05,
|
| 413 |
+
"loss": 0.5099,
|
| 414 |
+
"step": 4400
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.28427037271004424,
|
| 418 |
+
"grad_norm": 5.679586410522461,
|
| 419 |
+
"learning_rate": 1.894714676774058e-05,
|
| 420 |
+
"loss": 0.5279,
|
| 421 |
+
"step": 4500
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.28427037271004424,
|
| 425 |
+
"eval_accuracy": 0.7729647134074837,
|
| 426 |
+
"eval_f1": 0.7772108859877666,
|
| 427 |
+
"eval_loss": 0.5350751280784607,
|
| 428 |
+
"eval_precision": 0.7841446398228663,
|
| 429 |
+
"eval_recall": 0.7729647134074837,
|
| 430 |
+
"eval_runtime": 591.8805,
|
| 431 |
+
"eval_samples_per_second": 95.09,
|
| 432 |
+
"eval_steps_per_second": 2.972,
|
| 433 |
+
"step": 4500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.29058749210360074,
|
| 437 |
+
"grad_norm": 3.3693079948425293,
|
| 438 |
+
"learning_rate": 1.9368288060644346e-05,
|
| 439 |
+
"loss": 0.5476,
|
| 440 |
+
"step": 4600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.2969046114971573,
|
| 444 |
+
"grad_norm": 4.541057109832764,
|
| 445 |
+
"learning_rate": 1.9789429353548117e-05,
|
| 446 |
+
"loss": 0.5136,
|
| 447 |
+
"step": 4700
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.30322173089071386,
|
| 451 |
+
"grad_norm": 5.138273239135742,
|
| 452 |
+
"learning_rate": 1.997660326150535e-05,
|
| 453 |
+
"loss": 0.52,
|
| 454 |
+
"step": 4800
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.30953885028427036,
|
| 458 |
+
"grad_norm": 4.229297161102295,
|
| 459 |
+
"learning_rate": 1.9929809784516042e-05,
|
| 460 |
+
"loss": 0.5062,
|
| 461 |
+
"step": 4900
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.3158559696778269,
|
| 465 |
+
"grad_norm": 5.270105361938477,
|
| 466 |
+
"learning_rate": 1.9883016307526733e-05,
|
| 467 |
+
"loss": 0.5279,
|
| 468 |
+
"step": 5000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.3158559696778269,
|
| 472 |
+
"eval_accuracy": 0.7755587932198571,
|
| 473 |
+
"eval_f1": 0.7683528683622288,
|
| 474 |
+
"eval_loss": 0.5248374938964844,
|
| 475 |
+
"eval_precision": 0.773228927982264,
|
| 476 |
+
"eval_recall": 0.7755587932198571,
|
| 477 |
+
"eval_runtime": 590.1122,
|
| 478 |
+
"eval_samples_per_second": 95.375,
|
| 479 |
+
"eval_steps_per_second": 2.981,
|
| 480 |
+
"step": 5000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3221730890713834,
|
| 484 |
+
"grad_norm": 3.831350564956665,
|
| 485 |
+
"learning_rate": 1.9836222830537423e-05,
|
| 486 |
+
"loss": 0.5414,
|
| 487 |
+
"step": 5100
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.32849020846494,
|
| 491 |
+
"grad_norm": 4.2018938064575195,
|
| 492 |
+
"learning_rate": 1.9789429353548117e-05,
|
| 493 |
+
"loss": 0.5281,
|
| 494 |
+
"step": 5200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.33480732785849654,
|
| 498 |
+
"grad_norm": 4.186958312988281,
|
| 499 |
+
"learning_rate": 1.974263587655881e-05,
|
| 500 |
+
"loss": 0.5359,
|
| 501 |
+
"step": 5300
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.34112444725205304,
|
| 505 |
+
"grad_norm": 4.530041694641113,
|
| 506 |
+
"learning_rate": 1.9695842399569504e-05,
|
| 507 |
+
"loss": 0.5433,
|
| 508 |
+
"step": 5400
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.3474415666456096,
|
| 512 |
+
"grad_norm": 5.412771224975586,
|
| 513 |
+
"learning_rate": 1.9649048922580194e-05,
|
| 514 |
+
"loss": 0.5351,
|
| 515 |
+
"step": 5500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.3474415666456096,
|
| 519 |
+
"eval_accuracy": 0.7780107316726484,
|
| 520 |
+
"eval_f1": 0.7810193585711508,
|
| 521 |
+
"eval_loss": 0.5162075757980347,
|
| 522 |
+
"eval_precision": 0.7869921344375624,
|
| 523 |
+
"eval_recall": 0.7780107316726484,
|
| 524 |
+
"eval_runtime": 1985.1511,
|
| 525 |
+
"eval_samples_per_second": 28.351,
|
| 526 |
+
"eval_steps_per_second": 0.886,
|
| 527 |
+
"step": 5500
|
| 528 |
+
}
|
| 529 |
+
],
|
| 530 |
+
"logging_steps": 100,
|
| 531 |
+
"max_steps": 47490,
|
| 532 |
+
"num_input_tokens_seen": 0,
|
| 533 |
+
"num_train_epochs": 3,
|
| 534 |
+
"save_steps": 500,
|
| 535 |
+
"stateful_callbacks": {
|
| 536 |
+
"TrainerControl": {
|
| 537 |
+
"args": {
|
| 538 |
+
"should_epoch_stop": false,
|
| 539 |
+
"should_evaluate": false,
|
| 540 |
+
"should_log": false,
|
| 541 |
+
"should_save": true,
|
| 542 |
+
"should_training_stop": false
|
| 543 |
+
},
|
| 544 |
+
"attributes": {}
|
| 545 |
+
}
|
| 546 |
+
},
|
| 547 |
+
"total_flos": 1.1576990380032e+16,
|
| 548 |
+
"train_batch_size": 32,
|
| 549 |
+
"trial_name": null,
|
| 550 |
+
"trial_params": null
|
| 551 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88724115c05a14013e1bf5182b6efa00270cfee7c30485da6eb058c6d09f75a8
|
| 3 |
+
size 5805
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|