Upload 9 files
Browse files- config.json +26 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +259 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/scibert_scivocab_uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.35.2",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 31090
|
| 26 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef31eac551bfc1e71f6bc3a68d965753d901c9c93feea4332cb66e6e04f224a7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35a3dade2b7cbefccf90c0e4fadf2cb3cf8377a4c99770b3dd489b2f99c2d41a
|
| 3 |
+
size 1064
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"101": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"102": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"103": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 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 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22196684777736664,
|
| 3 |
+
"best_model_checkpoint": "sci_cite2/checkpoint-16134",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16134,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.845047725300608e-06,
|
| 14 |
+
"loss": 0.4454,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 9.690095450601216e-06,
|
| 20 |
+
"loss": 0.3583,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 9.535143175901823e-06,
|
| 26 |
+
"loss": 0.3288,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 9.38019090120243e-06,
|
| 32 |
+
"loss": 0.3102,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 9.225238626503039e-06,
|
| 38 |
+
"loss": 0.3006,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.37,
|
| 43 |
+
"learning_rate": 9.070286351803646e-06,
|
| 44 |
+
"loss": 0.2881,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43,
|
| 49 |
+
"learning_rate": 8.915334077104253e-06,
|
| 50 |
+
"loss": 0.2824,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5,
|
| 55 |
+
"learning_rate": 8.76038180240486e-06,
|
| 56 |
+
"loss": 0.2765,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.56,
|
| 61 |
+
"learning_rate": 8.605429527705468e-06,
|
| 62 |
+
"loss": 0.2682,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.62,
|
| 67 |
+
"learning_rate": 8.450477253006075e-06,
|
| 68 |
+
"loss": 0.2638,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.68,
|
| 73 |
+
"learning_rate": 8.295524978306682e-06,
|
| 74 |
+
"loss": 0.259,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.74,
|
| 79 |
+
"learning_rate": 8.14057270360729e-06,
|
| 80 |
+
"loss": 0.257,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.81,
|
| 85 |
+
"learning_rate": 7.985620428907898e-06,
|
| 86 |
+
"loss": 0.2526,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.87,
|
| 91 |
+
"learning_rate": 7.830668154208505e-06,
|
| 92 |
+
"loss": 0.248,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.93,
|
| 97 |
+
"learning_rate": 7.675715879509111e-06,
|
| 98 |
+
"loss": 0.2485,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.99,
|
| 103 |
+
"learning_rate": 7.520763604809719e-06,
|
| 104 |
+
"loss": 0.2418,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"step": 8067,
|
| 110 |
+
"train_accuracy": 0.8732977099630939,
|
| 111 |
+
"train_f1": 0.8722354031725915,
|
| 112 |
+
"train_loss": 0.213734969496727,
|
| 113 |
+
"train_precision": 0.8861924332063127,
|
| 114 |
+
"train_recall": 0.8732977099630939,
|
| 115 |
+
"train_runtime": 2526.3719,
|
| 116 |
+
"train_samples_per_second": 306.526,
|
| 117 |
+
"train_steps_per_second": 3.193
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0,
|
| 121 |
+
"eval_accuracy": 0.8648553719008264,
|
| 122 |
+
"eval_f1": 0.863761374500173,
|
| 123 |
+
"eval_loss": 0.2356892228126526,
|
| 124 |
+
"eval_precision": 0.8767616410024536,
|
| 125 |
+
"eval_recall": 0.8648553719008264,
|
| 126 |
+
"eval_runtime": 633.1197,
|
| 127 |
+
"eval_samples_per_second": 305.787,
|
| 128 |
+
"eval_steps_per_second": 3.186,
|
| 129 |
+
"step": 8067
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.05,
|
| 133 |
+
"learning_rate": 7.365811330110326e-06,
|
| 134 |
+
"loss": 0.222,
|
| 135 |
+
"step": 8500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.12,
|
| 139 |
+
"learning_rate": 7.210859055410934e-06,
|
| 140 |
+
"loss": 0.2236,
|
| 141 |
+
"step": 9000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.18,
|
| 145 |
+
"learning_rate": 7.055906780711541e-06,
|
| 146 |
+
"loss": 0.2179,
|
| 147 |
+
"step": 9500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.24,
|
| 151 |
+
"learning_rate": 6.900954506012149e-06,
|
| 152 |
+
"loss": 0.2204,
|
| 153 |
+
"step": 10000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3,
|
| 157 |
+
"learning_rate": 6.746002231312756e-06,
|
| 158 |
+
"loss": 0.2182,
|
| 159 |
+
"step": 10500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.36,
|
| 163 |
+
"learning_rate": 6.591049956613363e-06,
|
| 164 |
+
"loss": 0.2172,
|
| 165 |
+
"step": 11000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.43,
|
| 169 |
+
"learning_rate": 6.436097681913971e-06,
|
| 170 |
+
"loss": 0.2094,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.49,
|
| 175 |
+
"learning_rate": 6.281145407214578e-06,
|
| 176 |
+
"loss": 0.2139,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.55,
|
| 181 |
+
"learning_rate": 6.126193132515186e-06,
|
| 182 |
+
"loss": 0.2105,
|
| 183 |
+
"step": 12500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.61,
|
| 187 |
+
"learning_rate": 5.9712408578157935e-06,
|
| 188 |
+
"loss": 0.211,
|
| 189 |
+
"step": 13000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.67,
|
| 193 |
+
"learning_rate": 5.8162885831164004e-06,
|
| 194 |
+
"loss": 0.2137,
|
| 195 |
+
"step": 13500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.74,
|
| 199 |
+
"learning_rate": 5.661336308417008e-06,
|
| 200 |
+
"loss": 0.2132,
|
| 201 |
+
"step": 14000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.8,
|
| 205 |
+
"learning_rate": 5.506384033717615e-06,
|
| 206 |
+
"loss": 0.2108,
|
| 207 |
+
"step": 14500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.86,
|
| 211 |
+
"learning_rate": 5.351431759018223e-06,
|
| 212 |
+
"loss": 0.21,
|
| 213 |
+
"step": 15000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.92,
|
| 217 |
+
"learning_rate": 5.196479484318831e-06,
|
| 218 |
+
"loss": 0.2109,
|
| 219 |
+
"step": 15500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.98,
|
| 223 |
+
"learning_rate": 5.041527209619438e-06,
|
| 224 |
+
"loss": 0.2094,
|
| 225 |
+
"step": 16000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.0,
|
| 229 |
+
"step": 16134,
|
| 230 |
+
"train_accuracy": 0.8852553854736195,
|
| 231 |
+
"train_f1": 0.8841428775695753,
|
| 232 |
+
"train_loss": 0.18161344528198242,
|
| 233 |
+
"train_precision": 0.9007014174019812,
|
| 234 |
+
"train_recall": 0.8852553854736195,
|
| 235 |
+
"train_runtime": 2519.4245,
|
| 236 |
+
"train_samples_per_second": 307.371,
|
| 237 |
+
"train_steps_per_second": 3.202
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.0,
|
| 241 |
+
"eval_accuracy": 0.8720867768595041,
|
| 242 |
+
"eval_f1": 0.8708637537852376,
|
| 243 |
+
"eval_loss": 0.22196684777736664,
|
| 244 |
+
"eval_precision": 0.8865148727683396,
|
| 245 |
+
"eval_recall": 0.8720867768595041,
|
| 246 |
+
"eval_runtime": 636.0409,
|
| 247 |
+
"eval_samples_per_second": 304.383,
|
| 248 |
+
"eval_steps_per_second": 3.171,
|
| 249 |
+
"step": 16134
|
| 250 |
+
}
|
| 251 |
+
],
|
| 252 |
+
"logging_steps": 500,
|
| 253 |
+
"max_steps": 32268,
|
| 254 |
+
"num_train_epochs": 4,
|
| 255 |
+
"save_steps": 500,
|
| 256 |
+
"total_flos": 4.0750535009734656e+17,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d583e739efd5092ea8bbc1f6844ab0dd80e2e6f405cd21ca0fed3c63e7b7df6d
|
| 3 |
+
size 4536
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|