Upload folder using huggingface_hub
Browse files- checkpoint-3125/config.json +31 -0
- checkpoint-3125/model.safetensors +3 -0
- checkpoint-3125/optimizer.pt +3 -0
- checkpoint-3125/rng_state.pth +3 -0
- checkpoint-3125/scheduler.pt +3 -0
- checkpoint-3125/tokenizer.json +0 -0
- checkpoint-3125/tokenizer_config.json +15 -0
- checkpoint-3125/trainer_state.json +260 -0
- checkpoint-3125/training_args.bin +3 -0
- checkpoint-6250/checkpoint-3125/config.json +31 -0
- checkpoint-6250/checkpoint-3125/model.safetensors +3 -0
- checkpoint-6250/checkpoint-3125/optimizer.pt +3 -0
- checkpoint-6250/checkpoint-3125/rng_state.pth +3 -0
- checkpoint-6250/checkpoint-3125/scheduler.pt +3 -0
- checkpoint-6250/checkpoint-3125/tokenizer.json +0 -0
- checkpoint-6250/checkpoint-3125/tokenizer_config.json +15 -0
- checkpoint-6250/checkpoint-3125/trainer_state.json +260 -0
- checkpoint-6250/checkpoint-3125/training_args.bin +3 -0
- checkpoint-6250/config-Copy1.json +31 -0
- checkpoint-6250/config.json +31 -0
- checkpoint-6250/model-Copy1.safetensors +3 -0
- checkpoint-6250/model.safetensors +3 -0
- checkpoint-6250/optimizer.pt +3 -0
- checkpoint-6250/rng_state.pth +3 -0
- checkpoint-6250/scheduler.pt +3 -0
- checkpoint-6250/tokenizer-Copy1.json +0 -0
- checkpoint-6250/tokenizer.json +0 -0
- checkpoint-6250/tokenizer_config-Copy1.json +15 -0
- checkpoint-6250/tokenizer_config.json +15 -0
- checkpoint-6250/trainer_state.json +486 -0
- checkpoint-6250/training_args-Copy1.bin +3 -0
- checkpoint-6250/training_args.bin +3 -0
- config.json +31 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
checkpoint-3125/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.14.1",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
checkpoint-3125/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77c0b6cb76b8923525ebd36090528ed89c07639ff94164bfdbb76d442594521a
|
| 3 |
+
size 437958624
|
checkpoint-3125/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d8c4a723c16a6748d8ed01b67e658df3be2ec0ac759c07fc990b146ff55885
|
| 3 |
+
size 876038394
|
checkpoint-3125/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02021f76c303e6aba7d48d294e35c4eae4c624c0081e2ff978db4f26464c3732
|
| 3 |
+
size 14244
|
checkpoint-3125/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01e6f993b68c496698638e2cbd381e107c95f4ff5148616b044312f0f7c0a753
|
| 3 |
+
size 1064
|
checkpoint-3125/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3125/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-3125/trainer_state.json
ADDED
|
@@ -0,0 +1,260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3125,
|
| 3 |
+
"best_metric": 0.25182339549064636,
|
| 4 |
+
"best_model_checkpoint": "./bert-finetuned\\checkpoint-3125",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3125,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.032,
|
| 14 |
+
"grad_norm": 13.48560905456543,
|
| 15 |
+
"learning_rate": 1.96832e-05,
|
| 16 |
+
"loss": 0.5259920883178711,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.064,
|
| 21 |
+
"grad_norm": 1.4620904922485352,
|
| 22 |
+
"learning_rate": 1.93632e-05,
|
| 23 |
+
"loss": 0.3553178787231445,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.096,
|
| 28 |
+
"grad_norm": 0.5326040983200073,
|
| 29 |
+
"learning_rate": 1.90432e-05,
|
| 30 |
+
"loss": 0.3424180221557617,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.128,
|
| 35 |
+
"grad_norm": 32.138343811035156,
|
| 36 |
+
"learning_rate": 1.87232e-05,
|
| 37 |
+
"loss": 0.34127422332763674,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"grad_norm": 14.847369194030762,
|
| 43 |
+
"learning_rate": 1.84032e-05,
|
| 44 |
+
"loss": 0.33502582550048826,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.192,
|
| 49 |
+
"grad_norm": 9.288370132446289,
|
| 50 |
+
"learning_rate": 1.80832e-05,
|
| 51 |
+
"loss": 0.36018058776855466,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.224,
|
| 56 |
+
"grad_norm": 5.515246391296387,
|
| 57 |
+
"learning_rate": 1.77632e-05,
|
| 58 |
+
"loss": 0.3056466102600098,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.256,
|
| 63 |
+
"grad_norm": 36.022945404052734,
|
| 64 |
+
"learning_rate": 1.7443200000000003e-05,
|
| 65 |
+
"loss": 0.29051521301269534,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.288,
|
| 70 |
+
"grad_norm": 17.22569465637207,
|
| 71 |
+
"learning_rate": 1.7123200000000002e-05,
|
| 72 |
+
"loss": 0.32096527099609373,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.32,
|
| 77 |
+
"grad_norm": 11.046714782714844,
|
| 78 |
+
"learning_rate": 1.6803200000000002e-05,
|
| 79 |
+
"loss": 0.3179695510864258,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.352,
|
| 84 |
+
"grad_norm": 8.951647758483887,
|
| 85 |
+
"learning_rate": 1.6483200000000002e-05,
|
| 86 |
+
"loss": 0.2773170280456543,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.384,
|
| 91 |
+
"grad_norm": 15.794150352478027,
|
| 92 |
+
"learning_rate": 1.61632e-05,
|
| 93 |
+
"loss": 0.3346487808227539,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.416,
|
| 98 |
+
"grad_norm": 18.145700454711914,
|
| 99 |
+
"learning_rate": 1.58432e-05,
|
| 100 |
+
"loss": 0.3296665191650391,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.448,
|
| 105 |
+
"grad_norm": 9.669306755065918,
|
| 106 |
+
"learning_rate": 1.55232e-05,
|
| 107 |
+
"loss": 0.3087940216064453,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.48,
|
| 112 |
+
"grad_norm": 11.44780445098877,
|
| 113 |
+
"learning_rate": 1.52032e-05,
|
| 114 |
+
"loss": 0.28897178649902344,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.512,
|
| 119 |
+
"grad_norm": 0.7766106128692627,
|
| 120 |
+
"learning_rate": 1.4883200000000002e-05,
|
| 121 |
+
"loss": 0.29357257843017576,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.544,
|
| 126 |
+
"grad_norm": 46.51291275024414,
|
| 127 |
+
"learning_rate": 1.4563200000000001e-05,
|
| 128 |
+
"loss": 0.30526941299438476,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.576,
|
| 133 |
+
"grad_norm": 6.34660530090332,
|
| 134 |
+
"learning_rate": 1.4243200000000001e-05,
|
| 135 |
+
"loss": 0.25921268463134767,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.608,
|
| 140 |
+
"grad_norm": 1.1790388822555542,
|
| 141 |
+
"learning_rate": 1.39232e-05,
|
| 142 |
+
"loss": 0.3411357879638672,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.64,
|
| 147 |
+
"grad_norm": 16.262535095214844,
|
| 148 |
+
"learning_rate": 1.36032e-05,
|
| 149 |
+
"loss": 0.2934623908996582,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.672,
|
| 154 |
+
"grad_norm": 29.619890213012695,
|
| 155 |
+
"learning_rate": 1.32832e-05,
|
| 156 |
+
"loss": 0.2961533737182617,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.704,
|
| 161 |
+
"grad_norm": 8.219003677368164,
|
| 162 |
+
"learning_rate": 1.29632e-05,
|
| 163 |
+
"loss": 0.3191648292541504,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.736,
|
| 168 |
+
"grad_norm": 17.816516876220703,
|
| 169 |
+
"learning_rate": 1.2643200000000003e-05,
|
| 170 |
+
"loss": 0.29726606369018554,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.768,
|
| 175 |
+
"grad_norm": 27.65273094177246,
|
| 176 |
+
"learning_rate": 1.2323200000000003e-05,
|
| 177 |
+
"loss": 0.3006927108764648,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8,
|
| 182 |
+
"grad_norm": 15.806839942932129,
|
| 183 |
+
"learning_rate": 1.2003200000000002e-05,
|
| 184 |
+
"loss": 0.2578249168395996,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.832,
|
| 189 |
+
"grad_norm": 0.5523794889450073,
|
| 190 |
+
"learning_rate": 1.1683200000000002e-05,
|
| 191 |
+
"loss": 0.3062942695617676,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.864,
|
| 196 |
+
"grad_norm": 17.4210262298584,
|
| 197 |
+
"learning_rate": 1.1363200000000002e-05,
|
| 198 |
+
"loss": 0.289460563659668,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.896,
|
| 203 |
+
"grad_norm": 16.39777946472168,
|
| 204 |
+
"learning_rate": 1.1043200000000001e-05,
|
| 205 |
+
"loss": 0.2848842239379883,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.928,
|
| 210 |
+
"grad_norm": 0.6758588552474976,
|
| 211 |
+
"learning_rate": 1.0723200000000001e-05,
|
| 212 |
+
"loss": 0.2830107879638672,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.96,
|
| 217 |
+
"grad_norm": 5.286366939544678,
|
| 218 |
+
"learning_rate": 1.04032e-05,
|
| 219 |
+
"loss": 0.27878957748413086,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.992,
|
| 224 |
+
"grad_norm": 1.4205851554870605,
|
| 225 |
+
"learning_rate": 1.0083200000000002e-05,
|
| 226 |
+
"loss": 0.28188695907592776,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.0,
|
| 231 |
+
"eval_accuracy": 0.91344,
|
| 232 |
+
"eval_loss": 0.25182339549064636,
|
| 233 |
+
"eval_runtime": 986.1508,
|
| 234 |
+
"eval_samples_per_second": 25.351,
|
| 235 |
+
"eval_steps_per_second": 3.169,
|
| 236 |
+
"step": 3125
|
| 237 |
+
}
|
| 238 |
+
],
|
| 239 |
+
"logging_steps": 100,
|
| 240 |
+
"max_steps": 6250,
|
| 241 |
+
"num_input_tokens_seen": 0,
|
| 242 |
+
"num_train_epochs": 2,
|
| 243 |
+
"save_steps": 500,
|
| 244 |
+
"stateful_callbacks": {
|
| 245 |
+
"TrainerControl": {
|
| 246 |
+
"args": {
|
| 247 |
+
"should_epoch_stop": false,
|
| 248 |
+
"should_evaluate": false,
|
| 249 |
+
"should_log": false,
|
| 250 |
+
"should_save": true,
|
| 251 |
+
"should_training_stop": false
|
| 252 |
+
},
|
| 253 |
+
"attributes": {}
|
| 254 |
+
}
|
| 255 |
+
},
|
| 256 |
+
"total_flos": 3288888192000000.0,
|
| 257 |
+
"train_batch_size": 8,
|
| 258 |
+
"trial_name": null,
|
| 259 |
+
"trial_params": null
|
| 260 |
+
}
|
checkpoint-3125/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868d76fe5c27aa5a37ce01ffda78be7213533a448a8f4016458c266811c48bd2
|
| 3 |
+
size 4728
|
checkpoint-6250/checkpoint-3125/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.14.1",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
checkpoint-6250/checkpoint-3125/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77c0b6cb76b8923525ebd36090528ed89c07639ff94164bfdbb76d442594521a
|
| 3 |
+
size 437958624
|
checkpoint-6250/checkpoint-3125/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d8c4a723c16a6748d8ed01b67e658df3be2ec0ac759c07fc990b146ff55885
|
| 3 |
+
size 876038394
|
checkpoint-6250/checkpoint-3125/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02021f76c303e6aba7d48d294e35c4eae4c624c0081e2ff978db4f26464c3732
|
| 3 |
+
size 14244
|
checkpoint-6250/checkpoint-3125/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01e6f993b68c496698638e2cbd381e107c95f4ff5148616b044312f0f7c0a753
|
| 3 |
+
size 1064
|
checkpoint-6250/checkpoint-3125/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6250/checkpoint-3125/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-6250/checkpoint-3125/trainer_state.json
ADDED
|
@@ -0,0 +1,260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3125,
|
| 3 |
+
"best_metric": 0.25182339549064636,
|
| 4 |
+
"best_model_checkpoint": "./bert-finetuned\\checkpoint-3125",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3125,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.032,
|
| 14 |
+
"grad_norm": 13.48560905456543,
|
| 15 |
+
"learning_rate": 1.96832e-05,
|
| 16 |
+
"loss": 0.5259920883178711,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.064,
|
| 21 |
+
"grad_norm": 1.4620904922485352,
|
| 22 |
+
"learning_rate": 1.93632e-05,
|
| 23 |
+
"loss": 0.3553178787231445,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.096,
|
| 28 |
+
"grad_norm": 0.5326040983200073,
|
| 29 |
+
"learning_rate": 1.90432e-05,
|
| 30 |
+
"loss": 0.3424180221557617,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.128,
|
| 35 |
+
"grad_norm": 32.138343811035156,
|
| 36 |
+
"learning_rate": 1.87232e-05,
|
| 37 |
+
"loss": 0.34127422332763674,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"grad_norm": 14.847369194030762,
|
| 43 |
+
"learning_rate": 1.84032e-05,
|
| 44 |
+
"loss": 0.33502582550048826,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.192,
|
| 49 |
+
"grad_norm": 9.288370132446289,
|
| 50 |
+
"learning_rate": 1.80832e-05,
|
| 51 |
+
"loss": 0.36018058776855466,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.224,
|
| 56 |
+
"grad_norm": 5.515246391296387,
|
| 57 |
+
"learning_rate": 1.77632e-05,
|
| 58 |
+
"loss": 0.3056466102600098,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.256,
|
| 63 |
+
"grad_norm": 36.022945404052734,
|
| 64 |
+
"learning_rate": 1.7443200000000003e-05,
|
| 65 |
+
"loss": 0.29051521301269534,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.288,
|
| 70 |
+
"grad_norm": 17.22569465637207,
|
| 71 |
+
"learning_rate": 1.7123200000000002e-05,
|
| 72 |
+
"loss": 0.32096527099609373,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.32,
|
| 77 |
+
"grad_norm": 11.046714782714844,
|
| 78 |
+
"learning_rate": 1.6803200000000002e-05,
|
| 79 |
+
"loss": 0.3179695510864258,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.352,
|
| 84 |
+
"grad_norm": 8.951647758483887,
|
| 85 |
+
"learning_rate": 1.6483200000000002e-05,
|
| 86 |
+
"loss": 0.2773170280456543,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.384,
|
| 91 |
+
"grad_norm": 15.794150352478027,
|
| 92 |
+
"learning_rate": 1.61632e-05,
|
| 93 |
+
"loss": 0.3346487808227539,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.416,
|
| 98 |
+
"grad_norm": 18.145700454711914,
|
| 99 |
+
"learning_rate": 1.58432e-05,
|
| 100 |
+
"loss": 0.3296665191650391,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.448,
|
| 105 |
+
"grad_norm": 9.669306755065918,
|
| 106 |
+
"learning_rate": 1.55232e-05,
|
| 107 |
+
"loss": 0.3087940216064453,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.48,
|
| 112 |
+
"grad_norm": 11.44780445098877,
|
| 113 |
+
"learning_rate": 1.52032e-05,
|
| 114 |
+
"loss": 0.28897178649902344,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.512,
|
| 119 |
+
"grad_norm": 0.7766106128692627,
|
| 120 |
+
"learning_rate": 1.4883200000000002e-05,
|
| 121 |
+
"loss": 0.29357257843017576,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.544,
|
| 126 |
+
"grad_norm": 46.51291275024414,
|
| 127 |
+
"learning_rate": 1.4563200000000001e-05,
|
| 128 |
+
"loss": 0.30526941299438476,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.576,
|
| 133 |
+
"grad_norm": 6.34660530090332,
|
| 134 |
+
"learning_rate": 1.4243200000000001e-05,
|
| 135 |
+
"loss": 0.25921268463134767,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.608,
|
| 140 |
+
"grad_norm": 1.1790388822555542,
|
| 141 |
+
"learning_rate": 1.39232e-05,
|
| 142 |
+
"loss": 0.3411357879638672,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.64,
|
| 147 |
+
"grad_norm": 16.262535095214844,
|
| 148 |
+
"learning_rate": 1.36032e-05,
|
| 149 |
+
"loss": 0.2934623908996582,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.672,
|
| 154 |
+
"grad_norm": 29.619890213012695,
|
| 155 |
+
"learning_rate": 1.32832e-05,
|
| 156 |
+
"loss": 0.2961533737182617,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.704,
|
| 161 |
+
"grad_norm": 8.219003677368164,
|
| 162 |
+
"learning_rate": 1.29632e-05,
|
| 163 |
+
"loss": 0.3191648292541504,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.736,
|
| 168 |
+
"grad_norm": 17.816516876220703,
|
| 169 |
+
"learning_rate": 1.2643200000000003e-05,
|
| 170 |
+
"loss": 0.29726606369018554,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.768,
|
| 175 |
+
"grad_norm": 27.65273094177246,
|
| 176 |
+
"learning_rate": 1.2323200000000003e-05,
|
| 177 |
+
"loss": 0.3006927108764648,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8,
|
| 182 |
+
"grad_norm": 15.806839942932129,
|
| 183 |
+
"learning_rate": 1.2003200000000002e-05,
|
| 184 |
+
"loss": 0.2578249168395996,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.832,
|
| 189 |
+
"grad_norm": 0.5523794889450073,
|
| 190 |
+
"learning_rate": 1.1683200000000002e-05,
|
| 191 |
+
"loss": 0.3062942695617676,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.864,
|
| 196 |
+
"grad_norm": 17.4210262298584,
|
| 197 |
+
"learning_rate": 1.1363200000000002e-05,
|
| 198 |
+
"loss": 0.289460563659668,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.896,
|
| 203 |
+
"grad_norm": 16.39777946472168,
|
| 204 |
+
"learning_rate": 1.1043200000000001e-05,
|
| 205 |
+
"loss": 0.2848842239379883,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.928,
|
| 210 |
+
"grad_norm": 0.6758588552474976,
|
| 211 |
+
"learning_rate": 1.0723200000000001e-05,
|
| 212 |
+
"loss": 0.2830107879638672,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.96,
|
| 217 |
+
"grad_norm": 5.286366939544678,
|
| 218 |
+
"learning_rate": 1.04032e-05,
|
| 219 |
+
"loss": 0.27878957748413086,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.992,
|
| 224 |
+
"grad_norm": 1.4205851554870605,
|
| 225 |
+
"learning_rate": 1.0083200000000002e-05,
|
| 226 |
+
"loss": 0.28188695907592776,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.0,
|
| 231 |
+
"eval_accuracy": 0.91344,
|
| 232 |
+
"eval_loss": 0.25182339549064636,
|
| 233 |
+
"eval_runtime": 986.1508,
|
| 234 |
+
"eval_samples_per_second": 25.351,
|
| 235 |
+
"eval_steps_per_second": 3.169,
|
| 236 |
+
"step": 3125
|
| 237 |
+
}
|
| 238 |
+
],
|
| 239 |
+
"logging_steps": 100,
|
| 240 |
+
"max_steps": 6250,
|
| 241 |
+
"num_input_tokens_seen": 0,
|
| 242 |
+
"num_train_epochs": 2,
|
| 243 |
+
"save_steps": 500,
|
| 244 |
+
"stateful_callbacks": {
|
| 245 |
+
"TrainerControl": {
|
| 246 |
+
"args": {
|
| 247 |
+
"should_epoch_stop": false,
|
| 248 |
+
"should_evaluate": false,
|
| 249 |
+
"should_log": false,
|
| 250 |
+
"should_save": true,
|
| 251 |
+
"should_training_stop": false
|
| 252 |
+
},
|
| 253 |
+
"attributes": {}
|
| 254 |
+
}
|
| 255 |
+
},
|
| 256 |
+
"total_flos": 3288888192000000.0,
|
| 257 |
+
"train_batch_size": 8,
|
| 258 |
+
"trial_name": null,
|
| 259 |
+
"trial_params": null
|
| 260 |
+
}
|
checkpoint-6250/checkpoint-3125/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868d76fe5c27aa5a37ce01ffda78be7213533a448a8f4016458c266811c48bd2
|
| 3 |
+
size 4728
|
checkpoint-6250/config-Copy1.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.14.1",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
checkpoint-6250/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.14.1",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
checkpoint-6250/model-Copy1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:429fa93cbf29aab5d8a8e2c238eade2abbb5f0f628b42095871d8d51c4436077
|
| 3 |
+
size 437958624
|
checkpoint-6250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea50dee8d168ac8b0a8a9215cdf614c45020858a0b4ee2e5f6c84c1b784b40c6
|
| 3 |
+
size 437958624
|
checkpoint-6250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fbd820bbc0911e1366480d33c646715e7f7cf6ea3d47b5faf02dfe800fbae8d
|
| 3 |
+
size 876038394
|
checkpoint-6250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fd055cbe86457af4fd65860ddd8e8c2465b199f9b0973aa0bc488cae646ebbc
|
| 3 |
+
size 14244
|
checkpoint-6250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c98d6e30b5ee01a2f9f1c3dbce99a5ad3046a424ead6d7a0d21f1db1af032078
|
| 3 |
+
size 1064
|
checkpoint-6250/tokenizer-Copy1.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6250/tokenizer_config-Copy1.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-6250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-6250/trainer_state.json
ADDED
|
@@ -0,0 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3125,
|
| 3 |
+
"best_metric": 0.25182339549064636,
|
| 4 |
+
"best_model_checkpoint": "./bert-finetuned\\checkpoint-3125",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 6250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.032,
|
| 14 |
+
"grad_norm": 13.48560905456543,
|
| 15 |
+
"learning_rate": 1.96832e-05,
|
| 16 |
+
"loss": 0.5259920883178711,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.064,
|
| 21 |
+
"grad_norm": 1.4620904922485352,
|
| 22 |
+
"learning_rate": 1.93632e-05,
|
| 23 |
+
"loss": 0.3553178787231445,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.096,
|
| 28 |
+
"grad_norm": 0.5326040983200073,
|
| 29 |
+
"learning_rate": 1.90432e-05,
|
| 30 |
+
"loss": 0.3424180221557617,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.128,
|
| 35 |
+
"grad_norm": 32.138343811035156,
|
| 36 |
+
"learning_rate": 1.87232e-05,
|
| 37 |
+
"loss": 0.34127422332763674,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"grad_norm": 14.847369194030762,
|
| 43 |
+
"learning_rate": 1.84032e-05,
|
| 44 |
+
"loss": 0.33502582550048826,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.192,
|
| 49 |
+
"grad_norm": 9.288370132446289,
|
| 50 |
+
"learning_rate": 1.80832e-05,
|
| 51 |
+
"loss": 0.36018058776855466,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.224,
|
| 56 |
+
"grad_norm": 5.515246391296387,
|
| 57 |
+
"learning_rate": 1.77632e-05,
|
| 58 |
+
"loss": 0.3056466102600098,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.256,
|
| 63 |
+
"grad_norm": 36.022945404052734,
|
| 64 |
+
"learning_rate": 1.7443200000000003e-05,
|
| 65 |
+
"loss": 0.29051521301269534,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.288,
|
| 70 |
+
"grad_norm": 17.22569465637207,
|
| 71 |
+
"learning_rate": 1.7123200000000002e-05,
|
| 72 |
+
"loss": 0.32096527099609373,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.32,
|
| 77 |
+
"grad_norm": 11.046714782714844,
|
| 78 |
+
"learning_rate": 1.6803200000000002e-05,
|
| 79 |
+
"loss": 0.3179695510864258,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.352,
|
| 84 |
+
"grad_norm": 8.951647758483887,
|
| 85 |
+
"learning_rate": 1.6483200000000002e-05,
|
| 86 |
+
"loss": 0.2773170280456543,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.384,
|
| 91 |
+
"grad_norm": 15.794150352478027,
|
| 92 |
+
"learning_rate": 1.61632e-05,
|
| 93 |
+
"loss": 0.3346487808227539,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.416,
|
| 98 |
+
"grad_norm": 18.145700454711914,
|
| 99 |
+
"learning_rate": 1.58432e-05,
|
| 100 |
+
"loss": 0.3296665191650391,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.448,
|
| 105 |
+
"grad_norm": 9.669306755065918,
|
| 106 |
+
"learning_rate": 1.55232e-05,
|
| 107 |
+
"loss": 0.3087940216064453,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.48,
|
| 112 |
+
"grad_norm": 11.44780445098877,
|
| 113 |
+
"learning_rate": 1.52032e-05,
|
| 114 |
+
"loss": 0.28897178649902344,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.512,
|
| 119 |
+
"grad_norm": 0.7766106128692627,
|
| 120 |
+
"learning_rate": 1.4883200000000002e-05,
|
| 121 |
+
"loss": 0.29357257843017576,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.544,
|
| 126 |
+
"grad_norm": 46.51291275024414,
|
| 127 |
+
"learning_rate": 1.4563200000000001e-05,
|
| 128 |
+
"loss": 0.30526941299438476,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.576,
|
| 133 |
+
"grad_norm": 6.34660530090332,
|
| 134 |
+
"learning_rate": 1.4243200000000001e-05,
|
| 135 |
+
"loss": 0.25921268463134767,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.608,
|
| 140 |
+
"grad_norm": 1.1790388822555542,
|
| 141 |
+
"learning_rate": 1.39232e-05,
|
| 142 |
+
"loss": 0.3411357879638672,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.64,
|
| 147 |
+
"grad_norm": 16.262535095214844,
|
| 148 |
+
"learning_rate": 1.36032e-05,
|
| 149 |
+
"loss": 0.2934623908996582,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.672,
|
| 154 |
+
"grad_norm": 29.619890213012695,
|
| 155 |
+
"learning_rate": 1.32832e-05,
|
| 156 |
+
"loss": 0.2961533737182617,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.704,
|
| 161 |
+
"grad_norm": 8.219003677368164,
|
| 162 |
+
"learning_rate": 1.29632e-05,
|
| 163 |
+
"loss": 0.3191648292541504,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.736,
|
| 168 |
+
"grad_norm": 17.816516876220703,
|
| 169 |
+
"learning_rate": 1.2643200000000003e-05,
|
| 170 |
+
"loss": 0.29726606369018554,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.768,
|
| 175 |
+
"grad_norm": 27.65273094177246,
|
| 176 |
+
"learning_rate": 1.2323200000000003e-05,
|
| 177 |
+
"loss": 0.3006927108764648,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8,
|
| 182 |
+
"grad_norm": 15.806839942932129,
|
| 183 |
+
"learning_rate": 1.2003200000000002e-05,
|
| 184 |
+
"loss": 0.2578249168395996,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.832,
|
| 189 |
+
"grad_norm": 0.5523794889450073,
|
| 190 |
+
"learning_rate": 1.1683200000000002e-05,
|
| 191 |
+
"loss": 0.3062942695617676,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.864,
|
| 196 |
+
"grad_norm": 17.4210262298584,
|
| 197 |
+
"learning_rate": 1.1363200000000002e-05,
|
| 198 |
+
"loss": 0.289460563659668,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.896,
|
| 203 |
+
"grad_norm": 16.39777946472168,
|
| 204 |
+
"learning_rate": 1.1043200000000001e-05,
|
| 205 |
+
"loss": 0.2848842239379883,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.928,
|
| 210 |
+
"grad_norm": 0.6758588552474976,
|
| 211 |
+
"learning_rate": 1.0723200000000001e-05,
|
| 212 |
+
"loss": 0.2830107879638672,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.96,
|
| 217 |
+
"grad_norm": 5.286366939544678,
|
| 218 |
+
"learning_rate": 1.04032e-05,
|
| 219 |
+
"loss": 0.27878957748413086,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.992,
|
| 224 |
+
"grad_norm": 1.4205851554870605,
|
| 225 |
+
"learning_rate": 1.0083200000000002e-05,
|
| 226 |
+
"loss": 0.28188695907592776,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.0,
|
| 231 |
+
"eval_accuracy": 0.91344,
|
| 232 |
+
"eval_loss": 0.25182339549064636,
|
| 233 |
+
"eval_runtime": 986.1508,
|
| 234 |
+
"eval_samples_per_second": 25.351,
|
| 235 |
+
"eval_steps_per_second": 3.169,
|
| 236 |
+
"step": 3125
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.024,
|
| 240 |
+
"grad_norm": 23.98052978515625,
|
| 241 |
+
"learning_rate": 9.7632e-06,
|
| 242 |
+
"loss": 0.22016559600830077,
|
| 243 |
+
"step": 3200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.056,
|
| 247 |
+
"grad_norm": 0.1547488421201706,
|
| 248 |
+
"learning_rate": 9.443200000000001e-06,
|
| 249 |
+
"loss": 0.1825577735900879,
|
| 250 |
+
"step": 3300
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.088,
|
| 254 |
+
"grad_norm": 0.08227001875638962,
|
| 255 |
+
"learning_rate": 9.123200000000001e-06,
|
| 256 |
+
"loss": 0.18940446853637696,
|
| 257 |
+
"step": 3400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.12,
|
| 261 |
+
"grad_norm": 0.1420843005180359,
|
| 262 |
+
"learning_rate": 8.8032e-06,
|
| 263 |
+
"loss": 0.1907291030883789,
|
| 264 |
+
"step": 3500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.152,
|
| 268 |
+
"grad_norm": 20.10905647277832,
|
| 269 |
+
"learning_rate": 8.4832e-06,
|
| 270 |
+
"loss": 0.13428974151611328,
|
| 271 |
+
"step": 3600
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.184,
|
| 275 |
+
"grad_norm": 0.08670040965080261,
|
| 276 |
+
"learning_rate": 8.163200000000002e-06,
|
| 277 |
+
"loss": 0.20151216506958008,
|
| 278 |
+
"step": 3700
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.216,
|
| 282 |
+
"grad_norm": 0.12150638550519943,
|
| 283 |
+
"learning_rate": 7.843200000000001e-06,
|
| 284 |
+
"loss": 0.21653879165649415,
|
| 285 |
+
"step": 3800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.248,
|
| 289 |
+
"grad_norm": 51.36846160888672,
|
| 290 |
+
"learning_rate": 7.5232e-06,
|
| 291 |
+
"loss": 0.20837539672851563,
|
| 292 |
+
"step": 3900
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.28,
|
| 296 |
+
"grad_norm": 0.3351477086544037,
|
| 297 |
+
"learning_rate": 7.2032e-06,
|
| 298 |
+
"loss": 0.13957653045654297,
|
| 299 |
+
"step": 4000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.312,
|
| 303 |
+
"grad_norm": 37.384944915771484,
|
| 304 |
+
"learning_rate": 6.883200000000001e-06,
|
| 305 |
+
"loss": 0.18269227981567382,
|
| 306 |
+
"step": 4100
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.3439999999999999,
|
| 310 |
+
"grad_norm": 34.17870330810547,
|
| 311 |
+
"learning_rate": 6.563200000000001e-06,
|
| 312 |
+
"loss": 0.16323944091796874,
|
| 313 |
+
"step": 4200
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.376,
|
| 317 |
+
"grad_norm": 0.16373877227306366,
|
| 318 |
+
"learning_rate": 6.243200000000001e-06,
|
| 319 |
+
"loss": 0.2217327117919922,
|
| 320 |
+
"step": 4300
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.408,
|
| 324 |
+
"grad_norm": 0.12130839377641678,
|
| 325 |
+
"learning_rate": 5.9232e-06,
|
| 326 |
+
"loss": 0.21164512634277344,
|
| 327 |
+
"step": 4400
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.44,
|
| 331 |
+
"grad_norm": 0.49366509914398193,
|
| 332 |
+
"learning_rate": 5.603200000000001e-06,
|
| 333 |
+
"loss": 0.15027467727661134,
|
| 334 |
+
"step": 4500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.472,
|
| 338 |
+
"grad_norm": 0.2988877296447754,
|
| 339 |
+
"learning_rate": 5.2832000000000005e-06,
|
| 340 |
+
"loss": 0.18775032043457032,
|
| 341 |
+
"step": 4600
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.504,
|
| 345 |
+
"grad_norm": 4.440558433532715,
|
| 346 |
+
"learning_rate": 4.9632e-06,
|
| 347 |
+
"loss": 0.18664859771728515,
|
| 348 |
+
"step": 4700
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.536,
|
| 352 |
+
"grad_norm": 51.274925231933594,
|
| 353 |
+
"learning_rate": 4.643200000000001e-06,
|
| 354 |
+
"loss": 0.1700606346130371,
|
| 355 |
+
"step": 4800
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.568,
|
| 359 |
+
"grad_norm": 0.055947449058294296,
|
| 360 |
+
"learning_rate": 4.3232e-06,
|
| 361 |
+
"loss": 0.18889652252197264,
|
| 362 |
+
"step": 4900
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.6,
|
| 366 |
+
"grad_norm": 0.05315174534916878,
|
| 367 |
+
"learning_rate": 4.0032e-06,
|
| 368 |
+
"loss": 0.14541624069213868,
|
| 369 |
+
"step": 5000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.6320000000000001,
|
| 373 |
+
"grad_norm": 10.145916938781738,
|
| 374 |
+
"learning_rate": 3.6832e-06,
|
| 375 |
+
"loss": 0.1497050380706787,
|
| 376 |
+
"step": 5100
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.6640000000000001,
|
| 380 |
+
"grad_norm": 0.11655700206756592,
|
| 381 |
+
"learning_rate": 3.3632000000000003e-06,
|
| 382 |
+
"loss": 0.22427309036254883,
|
| 383 |
+
"step": 5200
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.696,
|
| 387 |
+
"grad_norm": 0.08289012312889099,
|
| 388 |
+
"learning_rate": 3.0432e-06,
|
| 389 |
+
"loss": 0.16921247482299806,
|
| 390 |
+
"step": 5300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.728,
|
| 394 |
+
"grad_norm": 0.5657999515533447,
|
| 395 |
+
"learning_rate": 2.7232000000000005e-06,
|
| 396 |
+
"loss": 0.19958620071411132,
|
| 397 |
+
"step": 5400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.76,
|
| 401 |
+
"grad_norm": 28.683853149414062,
|
| 402 |
+
"learning_rate": 2.4032e-06,
|
| 403 |
+
"loss": 0.1758890151977539,
|
| 404 |
+
"step": 5500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.792,
|
| 408 |
+
"grad_norm": 10.876383781433105,
|
| 409 |
+
"learning_rate": 2.0832000000000002e-06,
|
| 410 |
+
"loss": 0.14310768127441406,
|
| 411 |
+
"step": 5600
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.8239999999999998,
|
| 415 |
+
"grad_norm": 0.21740658581256866,
|
| 416 |
+
"learning_rate": 1.7632000000000001e-06,
|
| 417 |
+
"loss": 0.1492612648010254,
|
| 418 |
+
"step": 5700
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.8559999999999999,
|
| 422 |
+
"grad_norm": 0.0751764252781868,
|
| 423 |
+
"learning_rate": 1.4432000000000002e-06,
|
| 424 |
+
"loss": 0.142544641494751,
|
| 425 |
+
"step": 5800
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.888,
|
| 429 |
+
"grad_norm": 10.577505111694336,
|
| 430 |
+
"learning_rate": 1.1232e-06,
|
| 431 |
+
"loss": 0.16017223358154298,
|
| 432 |
+
"step": 5900
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.92,
|
| 436 |
+
"grad_norm": 0.20831380784511566,
|
| 437 |
+
"learning_rate": 8.032000000000001e-07,
|
| 438 |
+
"loss": 0.15626992225646974,
|
| 439 |
+
"step": 6000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.952,
|
| 443 |
+
"grad_norm": 22.45941162109375,
|
| 444 |
+
"learning_rate": 4.832000000000001e-07,
|
| 445 |
+
"loss": 0.1922291946411133,
|
| 446 |
+
"step": 6100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.984,
|
| 450 |
+
"grad_norm": 0.194715678691864,
|
| 451 |
+
"learning_rate": 1.6320000000000003e-07,
|
| 452 |
+
"loss": 0.1705477523803711,
|
| 453 |
+
"step": 6200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.0,
|
| 457 |
+
"eval_accuracy": 0.92528,
|
| 458 |
+
"eval_loss": 0.31806525588035583,
|
| 459 |
+
"eval_runtime": 1429.0197,
|
| 460 |
+
"eval_samples_per_second": 17.495,
|
| 461 |
+
"eval_steps_per_second": 2.187,
|
| 462 |
+
"step": 6250
|
| 463 |
+
}
|
| 464 |
+
],
|
| 465 |
+
"logging_steps": 100,
|
| 466 |
+
"max_steps": 6250,
|
| 467 |
+
"num_input_tokens_seen": 0,
|
| 468 |
+
"num_train_epochs": 2,
|
| 469 |
+
"save_steps": 500,
|
| 470 |
+
"stateful_callbacks": {
|
| 471 |
+
"TrainerControl": {
|
| 472 |
+
"args": {
|
| 473 |
+
"should_epoch_stop": false,
|
| 474 |
+
"should_evaluate": false,
|
| 475 |
+
"should_log": false,
|
| 476 |
+
"should_save": true,
|
| 477 |
+
"should_training_stop": true
|
| 478 |
+
},
|
| 479 |
+
"attributes": {}
|
| 480 |
+
}
|
| 481 |
+
},
|
| 482 |
+
"total_flos": 6577776384000000.0,
|
| 483 |
+
"train_batch_size": 8,
|
| 484 |
+
"trial_name": null,
|
| 485 |
+
"trial_params": null
|
| 486 |
+
}
|
checkpoint-6250/training_args-Copy1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868d76fe5c27aa5a37ce01ffda78be7213533a448a8f4016458c266811c48bd2
|
| 3 |
+
size 4728
|
checkpoint-6250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868d76fe5c27aa5a37ce01ffda78be7213533a448a8f4016458c266811c48bd2
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"is_decoder": false,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.14.1",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 30522
|
| 31 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:429fa93cbf29aab5d8a8e2c238eade2abbb5f0f628b42095871d8d51c4436077
|
| 3 |
+
size 437958624
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868d76fe5c27aa5a37ce01ffda78be7213533a448a8f4016458c266811c48bd2
|
| 3 |
+
size 4728
|