Cameron Clarke
commited on
Commit
•
7d529b5
1
Parent(s):
1224b9a
add model
Browse files- config.json +24 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +392 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 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 |
+
"transformers_version": "4.5.0",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 28996
|
| 24 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0ce995f76bc2f1767f84600752c24f6843097e936f637e4e54c12a7a6612bb6
|
| 3 |
+
size 866620625
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94706ca1aaf3f95379041aa1c280b418494b659f9cc06000d63e076f43d4e5e
|
| 3 |
+
size 433336585
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d436b52b186954abb3602d89e031278bc339acb8742b2e2285c8f09bceeb7afb
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8276850886339938,
|
| 3 |
+
"best_model_checkpoint": "./runs/checkpoint-29920",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 29920,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.218154152691866e-05,
|
| 13 |
+
"loss": 0.2013,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 1.2078899619883618e-05,
|
| 19 |
+
"loss": 0.1722,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 1.1976257712848578e-05,
|
| 25 |
+
"loss": 0.1653,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 1.1873615805813536e-05,
|
| 31 |
+
"loss": 0.1488,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 1.1770973898778496e-05,
|
| 37 |
+
"loss": 0.136,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"learning_rate": 1.1668331991743454e-05,
|
| 43 |
+
"loss": 0.1522,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23,
|
| 48 |
+
"learning_rate": 1.1565690084708414e-05,
|
| 49 |
+
"loss": 0.1457,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"learning_rate": 1.1463048177673372e-05,
|
| 55 |
+
"loss": 0.1337,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"learning_rate": 1.1360406270638331e-05,
|
| 61 |
+
"loss": 0.1346,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.33,
|
| 66 |
+
"learning_rate": 1.1257764363603291e-05,
|
| 67 |
+
"loss": 0.1354,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.37,
|
| 72 |
+
"learning_rate": 1.115512245656825e-05,
|
| 73 |
+
"loss": 0.1442,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.4,
|
| 78 |
+
"learning_rate": 1.1052480549533209e-05,
|
| 79 |
+
"loss": 0.126,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.43,
|
| 84 |
+
"learning_rate": 1.0949838642498167e-05,
|
| 85 |
+
"loss": 0.1274,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.47,
|
| 90 |
+
"learning_rate": 1.0847196735463127e-05,
|
| 91 |
+
"loss": 0.1225,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5,
|
| 96 |
+
"learning_rate": 1.0744554828428085e-05,
|
| 97 |
+
"loss": 0.1301,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.53,
|
| 102 |
+
"learning_rate": 1.0641912921393045e-05,
|
| 103 |
+
"loss": 0.1357,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.57,
|
| 108 |
+
"learning_rate": 1.0539271014358003e-05,
|
| 109 |
+
"loss": 0.1272,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6,
|
| 114 |
+
"learning_rate": 1.0436629107322963e-05,
|
| 115 |
+
"loss": 0.1353,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.64,
|
| 120 |
+
"learning_rate": 1.0333987200287922e-05,
|
| 121 |
+
"loss": 0.1361,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.67,
|
| 126 |
+
"learning_rate": 1.023134529325288e-05,
|
| 127 |
+
"loss": 0.1303,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7,
|
| 132 |
+
"learning_rate": 1.012870338621784e-05,
|
| 133 |
+
"loss": 0.1294,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.74,
|
| 138 |
+
"learning_rate": 1.00260614791828e-05,
|
| 139 |
+
"loss": 0.1131,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.77,
|
| 144 |
+
"learning_rate": 9.923419572147758e-06,
|
| 145 |
+
"loss": 0.1072,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.8,
|
| 150 |
+
"learning_rate": 9.820777665112718e-06,
|
| 151 |
+
"loss": 0.1222,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.84,
|
| 156 |
+
"learning_rate": 9.718135758077678e-06,
|
| 157 |
+
"loss": 0.1221,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.87,
|
| 162 |
+
"learning_rate": 9.615493851042636e-06,
|
| 163 |
+
"loss": 0.1196,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9,
|
| 168 |
+
"learning_rate": 9.512851944007596e-06,
|
| 169 |
+
"loss": 0.1191,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.94,
|
| 174 |
+
"learning_rate": 9.410210036972554e-06,
|
| 175 |
+
"loss": 0.1185,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.97,
|
| 180 |
+
"learning_rate": 9.307568129937513e-06,
|
| 181 |
+
"loss": 0.1265,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0,
|
| 186 |
+
"eval_accuracy": 0.9647807886095305,
|
| 187 |
+
"eval_f1": 0.8202175303902751,
|
| 188 |
+
"eval_loss": 0.13746094703674316,
|
| 189 |
+
"eval_precision": 0.8026546456298522,
|
| 190 |
+
"eval_recall": 0.8385661957090529,
|
| 191 |
+
"eval_runtime": 509.4329,
|
| 192 |
+
"eval_samples_per_second": 78.309,
|
| 193 |
+
"step": 14960
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0,
|
| 197 |
+
"learning_rate": 9.204926222902473e-06,
|
| 198 |
+
"loss": 0.1162,
|
| 199 |
+
"step": 15000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.04,
|
| 203 |
+
"learning_rate": 9.102284315867431e-06,
|
| 204 |
+
"loss": 0.0916,
|
| 205 |
+
"step": 15500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.07,
|
| 209 |
+
"learning_rate": 8.999642408832391e-06,
|
| 210 |
+
"loss": 0.0878,
|
| 211 |
+
"step": 16000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.1,
|
| 215 |
+
"learning_rate": 8.897000501797349e-06,
|
| 216 |
+
"loss": 0.0929,
|
| 217 |
+
"step": 16500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.14,
|
| 221 |
+
"learning_rate": 8.794358594762309e-06,
|
| 222 |
+
"loss": 0.1018,
|
| 223 |
+
"step": 17000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.17,
|
| 227 |
+
"learning_rate": 8.691716687727267e-06,
|
| 228 |
+
"loss": 0.098,
|
| 229 |
+
"step": 17500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2,
|
| 233 |
+
"learning_rate": 8.589074780692227e-06,
|
| 234 |
+
"loss": 0.0895,
|
| 235 |
+
"step": 18000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.24,
|
| 239 |
+
"learning_rate": 8.486432873657185e-06,
|
| 240 |
+
"loss": 0.0824,
|
| 241 |
+
"step": 18500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.27,
|
| 245 |
+
"learning_rate": 8.383790966622145e-06,
|
| 246 |
+
"loss": 0.0758,
|
| 247 |
+
"step": 19000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3,
|
| 251 |
+
"learning_rate": 8.281149059587103e-06,
|
| 252 |
+
"loss": 0.088,
|
| 253 |
+
"step": 19500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.34,
|
| 257 |
+
"learning_rate": 8.178507152552062e-06,
|
| 258 |
+
"loss": 0.0975,
|
| 259 |
+
"step": 20000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.37,
|
| 263 |
+
"learning_rate": 8.075865245517022e-06,
|
| 264 |
+
"loss": 0.0917,
|
| 265 |
+
"step": 20500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.4,
|
| 269 |
+
"learning_rate": 7.97322333848198e-06,
|
| 270 |
+
"loss": 0.0952,
|
| 271 |
+
"step": 21000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.44,
|
| 275 |
+
"learning_rate": 7.87058143144694e-06,
|
| 276 |
+
"loss": 0.0963,
|
| 277 |
+
"step": 21500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.47,
|
| 281 |
+
"learning_rate": 7.767939524411898e-06,
|
| 282 |
+
"loss": 0.092,
|
| 283 |
+
"step": 22000
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.5,
|
| 287 |
+
"learning_rate": 7.665297617376858e-06,
|
| 288 |
+
"loss": 0.1029,
|
| 289 |
+
"step": 22500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.54,
|
| 293 |
+
"learning_rate": 7.562655710341816e-06,
|
| 294 |
+
"loss": 0.0938,
|
| 295 |
+
"step": 23000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.57,
|
| 299 |
+
"learning_rate": 7.460013803306776e-06,
|
| 300 |
+
"loss": 0.0995,
|
| 301 |
+
"step": 23500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.6,
|
| 305 |
+
"learning_rate": 7.357371896271735e-06,
|
| 306 |
+
"loss": 0.0875,
|
| 307 |
+
"step": 24000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.64,
|
| 311 |
+
"learning_rate": 7.254729989236694e-06,
|
| 312 |
+
"loss": 0.1,
|
| 313 |
+
"step": 24500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.67,
|
| 317 |
+
"learning_rate": 7.152088082201653e-06,
|
| 318 |
+
"loss": 0.0841,
|
| 319 |
+
"step": 25000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.7,
|
| 323 |
+
"learning_rate": 7.049446175166612e-06,
|
| 324 |
+
"loss": 0.09,
|
| 325 |
+
"step": 25500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.74,
|
| 329 |
+
"learning_rate": 6.946804268131571e-06,
|
| 330 |
+
"loss": 0.0797,
|
| 331 |
+
"step": 26000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.77,
|
| 335 |
+
"learning_rate": 6.84416236109653e-06,
|
| 336 |
+
"loss": 0.0888,
|
| 337 |
+
"step": 26500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.8,
|
| 341 |
+
"learning_rate": 6.74152045406149e-06,
|
| 342 |
+
"loss": 0.0804,
|
| 343 |
+
"step": 27000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.84,
|
| 347 |
+
"learning_rate": 6.638878547026448e-06,
|
| 348 |
+
"loss": 0.0989,
|
| 349 |
+
"step": 27500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.87,
|
| 353 |
+
"learning_rate": 6.536236639991408e-06,
|
| 354 |
+
"loss": 0.0879,
|
| 355 |
+
"step": 28000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.91,
|
| 359 |
+
"learning_rate": 6.433594732956366e-06,
|
| 360 |
+
"loss": 0.0955,
|
| 361 |
+
"step": 28500
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.94,
|
| 365 |
+
"learning_rate": 6.330952825921326e-06,
|
| 366 |
+
"loss": 0.0928,
|
| 367 |
+
"step": 29000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.97,
|
| 371 |
+
"learning_rate": 6.228310918886284e-06,
|
| 372 |
+
"loss": 0.0852,
|
| 373 |
+
"step": 29500
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.0,
|
| 377 |
+
"eval_accuracy": 0.9668613541222771,
|
| 378 |
+
"eval_f1": 0.8276850886339938,
|
| 379 |
+
"eval_loss": 0.13479416072368622,
|
| 380 |
+
"eval_precision": 0.8246753246753247,
|
| 381 |
+
"eval_recall": 0.8307169021454736,
|
| 382 |
+
"eval_runtime": 509.3337,
|
| 383 |
+
"eval_samples_per_second": 78.324,
|
| 384 |
+
"step": 29920
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"max_steps": 59840,
|
| 388 |
+
"num_train_epochs": 4,
|
| 389 |
+
"total_flos": 7.964185065787392e+16,
|
| 390 |
+
"trial_name": null,
|
| 391 |
+
"trial_params": null
|
| 392 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72a05080c59d1d5ab9836e9c57e5502886de4cec57a59d44064e381710d1c61c
|
| 3 |
+
size 2351
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|