Initial commit
Browse files- config.json +42 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +295 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.3,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"tokenizer_class": "BertTokenizerFast",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.55.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 21128
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06459a5855fb805116788ce80be65ca09cfdbb7b0f67a8a638002af4f2e8c24
|
| 3 |
+
size 409103316
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad1817e619bb80dbc16b0e11dcbf9a46a1cb6ffdf5352b4fc579ba47f1fb6679
|
| 3 |
+
size 818322571
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adb5eade5023f94993dc7a4693b81114891bd16631759b8004a18bbb4ad27c6d
|
| 3 |
+
size 14391
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44babe7144fd17e2239ff38d65a1d9462278772f543376d836706d67813596c0
|
| 3 |
+
size 1465
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 158,
|
| 3 |
+
"best_metric": 0.9977549332388042,
|
| 4 |
+
"best_model_checkpoint": "ckpt/checkpoint-158",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 237,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08917197452229299,
|
| 14 |
+
"grad_norm": 8.361231803894043,
|
| 15 |
+
"learning_rate": 5.2173913043478265e-06,
|
| 16 |
+
"loss": 1.0968,
|
| 17 |
+
"step": 7
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.17834394904458598,
|
| 21 |
+
"grad_norm": 17.40561866760254,
|
| 22 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 23 |
+
"loss": 0.8108,
|
| 24 |
+
"step": 14
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.267515923566879,
|
| 28 |
+
"grad_norm": 97.01270294189453,
|
| 29 |
+
"learning_rate": 1.739130434782609e-05,
|
| 30 |
+
"loss": 0.5853,
|
| 31 |
+
"step": 21
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.35668789808917195,
|
| 35 |
+
"grad_norm": 3.1324217319488525,
|
| 36 |
+
"learning_rate": 1.9626168224299065e-05,
|
| 37 |
+
"loss": 0.3892,
|
| 38 |
+
"step": 28
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.445859872611465,
|
| 42 |
+
"grad_norm": 1.4563965797424316,
|
| 43 |
+
"learning_rate": 1.8971962616822433e-05,
|
| 44 |
+
"loss": 0.1388,
|
| 45 |
+
"step": 35
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.535031847133758,
|
| 49 |
+
"grad_norm": 2.76413631439209,
|
| 50 |
+
"learning_rate": 1.8317757009345797e-05,
|
| 51 |
+
"loss": 0.089,
|
| 52 |
+
"step": 42
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.6242038216560509,
|
| 56 |
+
"grad_norm": 0.3331431448459625,
|
| 57 |
+
"learning_rate": 1.766355140186916e-05,
|
| 58 |
+
"loss": 0.0415,
|
| 59 |
+
"step": 49
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.7133757961783439,
|
| 63 |
+
"grad_norm": 0.1350180059671402,
|
| 64 |
+
"learning_rate": 1.7009345794392526e-05,
|
| 65 |
+
"loss": 0.0251,
|
| 66 |
+
"step": 56
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.802547770700637,
|
| 70 |
+
"grad_norm": 2.5682196617126465,
|
| 71 |
+
"learning_rate": 1.635514018691589e-05,
|
| 72 |
+
"loss": 0.0202,
|
| 73 |
+
"step": 63
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.89171974522293,
|
| 77 |
+
"grad_norm": 0.08181392401456833,
|
| 78 |
+
"learning_rate": 1.5700934579439254e-05,
|
| 79 |
+
"loss": 0.0297,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.9808917197452229,
|
| 84 |
+
"grad_norm": 6.680551052093506,
|
| 85 |
+
"learning_rate": 1.5046728971962619e-05,
|
| 86 |
+
"loss": 0.0258,
|
| 87 |
+
"step": 77
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.0,
|
| 91 |
+
"eval_accuracy": 0.9971641261963843,
|
| 92 |
+
"eval_f1": 0.9971641134681397,
|
| 93 |
+
"eval_loss": 0.01230512373149395,
|
| 94 |
+
"eval_runtime": 565.2201,
|
| 95 |
+
"eval_samples_per_second": 29.946,
|
| 96 |
+
"eval_steps_per_second": 0.469,
|
| 97 |
+
"step": 79
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.0636942675159236,
|
| 101 |
+
"grad_norm": 2.224886417388916,
|
| 102 |
+
"learning_rate": 1.4392523364485981e-05,
|
| 103 |
+
"loss": 0.0253,
|
| 104 |
+
"step": 84
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.1528662420382165,
|
| 108 |
+
"grad_norm": 3.0570154190063477,
|
| 109 |
+
"learning_rate": 1.3738317757009347e-05,
|
| 110 |
+
"loss": 0.0058,
|
| 111 |
+
"step": 91
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.2420382165605095,
|
| 115 |
+
"grad_norm": 2.5847160816192627,
|
| 116 |
+
"learning_rate": 1.308411214953271e-05,
|
| 117 |
+
"loss": 0.0248,
|
| 118 |
+
"step": 98
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.3312101910828025,
|
| 122 |
+
"grad_norm": 0.09943564236164093,
|
| 123 |
+
"learning_rate": 1.2429906542056076e-05,
|
| 124 |
+
"loss": 0.0072,
|
| 125 |
+
"step": 105
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.4203821656050954,
|
| 129 |
+
"grad_norm": 0.05498664453625679,
|
| 130 |
+
"learning_rate": 1.177570093457944e-05,
|
| 131 |
+
"loss": 0.0038,
|
| 132 |
+
"step": 112
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.5095541401273884,
|
| 136 |
+
"grad_norm": 0.04277191683650017,
|
| 137 |
+
"learning_rate": 1.1121495327102804e-05,
|
| 138 |
+
"loss": 0.0233,
|
| 139 |
+
"step": 119
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.5987261146496814,
|
| 143 |
+
"grad_norm": 0.03371246159076691,
|
| 144 |
+
"learning_rate": 1.0467289719626168e-05,
|
| 145 |
+
"loss": 0.0124,
|
| 146 |
+
"step": 126
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.6878980891719744,
|
| 150 |
+
"grad_norm": 2.893360137939453,
|
| 151 |
+
"learning_rate": 9.813084112149533e-06,
|
| 152 |
+
"loss": 0.0031,
|
| 153 |
+
"step": 133
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.7770700636942676,
|
| 157 |
+
"grad_norm": 0.38178956508636475,
|
| 158 |
+
"learning_rate": 9.158878504672899e-06,
|
| 159 |
+
"loss": 0.0189,
|
| 160 |
+
"step": 140
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.8662420382165605,
|
| 164 |
+
"grad_norm": 3.5433061122894287,
|
| 165 |
+
"learning_rate": 8.504672897196263e-06,
|
| 166 |
+
"loss": 0.0108,
|
| 167 |
+
"step": 147
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.9554140127388535,
|
| 171 |
+
"grad_norm": 3.068488121032715,
|
| 172 |
+
"learning_rate": 7.850467289719627e-06,
|
| 173 |
+
"loss": 0.0227,
|
| 174 |
+
"step": 154
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0,
|
| 178 |
+
"eval_accuracy": 0.9977549332388042,
|
| 179 |
+
"eval_f1": 0.9977549332388042,
|
| 180 |
+
"eval_loss": 0.00890457071363926,
|
| 181 |
+
"eval_runtime": 628.1179,
|
| 182 |
+
"eval_samples_per_second": 26.947,
|
| 183 |
+
"eval_steps_per_second": 0.422,
|
| 184 |
+
"step": 158
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.038216560509554,
|
| 188 |
+
"grad_norm": 10.418376922607422,
|
| 189 |
+
"learning_rate": 7.196261682242991e-06,
|
| 190 |
+
"loss": 0.0108,
|
| 191 |
+
"step": 161
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.127388535031847,
|
| 195 |
+
"grad_norm": 6.960994243621826,
|
| 196 |
+
"learning_rate": 6.542056074766355e-06,
|
| 197 |
+
"loss": 0.0092,
|
| 198 |
+
"step": 168
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.21656050955414,
|
| 202 |
+
"grad_norm": 0.026628026738762856,
|
| 203 |
+
"learning_rate": 5.88785046728972e-06,
|
| 204 |
+
"loss": 0.0054,
|
| 205 |
+
"step": 175
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.305732484076433,
|
| 209 |
+
"grad_norm": 0.9253213405609131,
|
| 210 |
+
"learning_rate": 5.233644859813084e-06,
|
| 211 |
+
"loss": 0.007,
|
| 212 |
+
"step": 182
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.394904458598726,
|
| 216 |
+
"grad_norm": 0.022573892027139664,
|
| 217 |
+
"learning_rate": 4.579439252336449e-06,
|
| 218 |
+
"loss": 0.0087,
|
| 219 |
+
"step": 189
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.484076433121019,
|
| 223 |
+
"grad_norm": 0.02918878197669983,
|
| 224 |
+
"learning_rate": 3.925233644859814e-06,
|
| 225 |
+
"loss": 0.0016,
|
| 226 |
+
"step": 196
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.573248407643312,
|
| 230 |
+
"grad_norm": 0.02902228757739067,
|
| 231 |
+
"learning_rate": 3.2710280373831774e-06,
|
| 232 |
+
"loss": 0.0016,
|
| 233 |
+
"step": 203
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.662420382165605,
|
| 237 |
+
"grad_norm": 0.02445131167769432,
|
| 238 |
+
"learning_rate": 2.616822429906542e-06,
|
| 239 |
+
"loss": 0.0024,
|
| 240 |
+
"step": 210
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.7515923566878984,
|
| 244 |
+
"grad_norm": 0.029552167281508446,
|
| 245 |
+
"learning_rate": 1.962616822429907e-06,
|
| 246 |
+
"loss": 0.0127,
|
| 247 |
+
"step": 217
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.840764331210191,
|
| 251 |
+
"grad_norm": 0.027709346264600754,
|
| 252 |
+
"learning_rate": 1.308411214953271e-06,
|
| 253 |
+
"loss": 0.0096,
|
| 254 |
+
"step": 224
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.9299363057324843,
|
| 258 |
+
"grad_norm": 0.02452605403959751,
|
| 259 |
+
"learning_rate": 6.542056074766355e-07,
|
| 260 |
+
"loss": 0.0015,
|
| 261 |
+
"step": 231
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.0,
|
| 265 |
+
"eval_accuracy": 0.9976367718303202,
|
| 266 |
+
"eval_f1": 0.9976367505503017,
|
| 267 |
+
"eval_loss": 0.009330125525593758,
|
| 268 |
+
"eval_runtime": 864.6395,
|
| 269 |
+
"eval_samples_per_second": 19.576,
|
| 270 |
+
"eval_steps_per_second": 0.306,
|
| 271 |
+
"step": 237
|
| 272 |
+
}
|
| 273 |
+
],
|
| 274 |
+
"logging_steps": 7,
|
| 275 |
+
"max_steps": 237,
|
| 276 |
+
"num_input_tokens_seen": 0,
|
| 277 |
+
"num_train_epochs": 3,
|
| 278 |
+
"save_steps": 500,
|
| 279 |
+
"stateful_callbacks": {
|
| 280 |
+
"TrainerControl": {
|
| 281 |
+
"args": {
|
| 282 |
+
"should_epoch_stop": false,
|
| 283 |
+
"should_evaluate": false,
|
| 284 |
+
"should_log": false,
|
| 285 |
+
"should_save": true,
|
| 286 |
+
"should_training_stop": true
|
| 287 |
+
},
|
| 288 |
+
"attributes": {}
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"total_flos": 1973350632960000.0,
|
| 292 |
+
"train_batch_size": 32,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a019710eb7a77a720bfc7c7c6fd6969ca4398112abc462fa5b91d4105bc53a1a
|
| 3 |
+
size 5777
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|