Upload 9 files
Browse files- 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 +15 -0
- trainer_state.json +334 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25502057cbbcf590727f8c51c87d294fcea58480453a6c55b9a214be65bc8b70
|
| 3 |
+
size 874819589
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a7c8a0de22bf9d3b23a24f579fdd35a82f8aea7e5e9d37aa4b24363bfdd37eb
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a1381ec8f0b04f9655e96215ad18d00d1e3055868e58a6612866788b2a1599
|
| 3 |
+
size 627
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"never_split": null,
|
| 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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "./saved-model-all-data/checkpoint-882",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"global_step": 1575,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.8670662363608421,
|
| 13 |
+
"eval_f1": 0.5017103762827823,
|
| 14 |
+
"eval_loss": 0.42577993869781494,
|
| 15 |
+
"eval_precision": 0.4592901878914405,
|
| 16 |
+
"eval_recall": 0.5527638190954773,
|
| 17 |
+
"eval_runtime": 0.6534,
|
| 18 |
+
"eval_samples_per_second": 76.527,
|
| 19 |
+
"eval_steps_per_second": 10.714,
|
| 20 |
+
"step": 63
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_accuracy": 0.9293069002612571,
|
| 25 |
+
"eval_f1": 0.7072289156626506,
|
| 26 |
+
"eval_loss": 0.22081975638866425,
|
| 27 |
+
"eval_precision": 0.6793981481481481,
|
| 28 |
+
"eval_recall": 0.7374371859296482,
|
| 29 |
+
"eval_runtime": 0.5804,
|
| 30 |
+
"eval_samples_per_second": 86.142,
|
| 31 |
+
"eval_steps_per_second": 12.06,
|
| 32 |
+
"step": 126
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"eval_accuracy": 0.9549715690794529,
|
| 37 |
+
"eval_f1": 0.8209500609013398,
|
| 38 |
+
"eval_loss": 0.13680364191532135,
|
| 39 |
+
"eval_precision": 0.7966903073286052,
|
| 40 |
+
"eval_recall": 0.8467336683417085,
|
| 41 |
+
"eval_runtime": 0.5883,
|
| 42 |
+
"eval_samples_per_second": 84.997,
|
| 43 |
+
"eval_steps_per_second": 11.9,
|
| 44 |
+
"step": 189
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.0,
|
| 48 |
+
"eval_accuracy": 0.9778699861687413,
|
| 49 |
+
"eval_f1": 0.8866995073891626,
|
| 50 |
+
"eval_loss": 0.07373423129320145,
|
| 51 |
+
"eval_precision": 0.8695652173913043,
|
| 52 |
+
"eval_recall": 0.9045226130653267,
|
| 53 |
+
"eval_runtime": 0.6005,
|
| 54 |
+
"eval_samples_per_second": 83.259,
|
| 55 |
+
"eval_steps_per_second": 11.656,
|
| 56 |
+
"step": 252
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.0,
|
| 60 |
+
"eval_accuracy": 0.9855540187490395,
|
| 61 |
+
"eval_f1": 0.9316239316239316,
|
| 62 |
+
"eval_loss": 0.04712964966893196,
|
| 63 |
+
"eval_precision": 0.9061757719714965,
|
| 64 |
+
"eval_recall": 0.9585427135678392,
|
| 65 |
+
"eval_runtime": 0.6021,
|
| 66 |
+
"eval_samples_per_second": 83.049,
|
| 67 |
+
"eval_steps_per_second": 11.627,
|
| 68 |
+
"step": 315
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.0,
|
| 72 |
+
"eval_accuracy": 0.9929306900261257,
|
| 73 |
+
"eval_f1": 0.9652605459057072,
|
| 74 |
+
"eval_loss": 0.02583940699696541,
|
| 75 |
+
"eval_precision": 0.9534313725490197,
|
| 76 |
+
"eval_recall": 0.9773869346733668,
|
| 77 |
+
"eval_runtime": 0.5826,
|
| 78 |
+
"eval_samples_per_second": 85.82,
|
| 79 |
+
"eval_steps_per_second": 12.015,
|
| 80 |
+
"step": 378
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 7.0,
|
| 84 |
+
"eval_accuracy": 0.9967727063162748,
|
| 85 |
+
"eval_f1": 0.9849435382685068,
|
| 86 |
+
"eval_loss": 0.015803957358002663,
|
| 87 |
+
"eval_precision": 0.9837092731829574,
|
| 88 |
+
"eval_recall": 0.9861809045226131,
|
| 89 |
+
"eval_runtime": 0.5833,
|
| 90 |
+
"eval_samples_per_second": 85.718,
|
| 91 |
+
"eval_steps_per_second": 12.0,
|
| 92 |
+
"step": 441
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.94,
|
| 96 |
+
"learning_rate": 3.644067796610169e-05,
|
| 97 |
+
"loss": 0.268,
|
| 98 |
+
"step": 500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"eval_accuracy": 0.9972337482710927,
|
| 103 |
+
"eval_f1": 0.9880578252671276,
|
| 104 |
+
"eval_loss": 0.012770027853548527,
|
| 105 |
+
"eval_precision": 0.9886792452830189,
|
| 106 |
+
"eval_recall": 0.9874371859296482,
|
| 107 |
+
"eval_runtime": 0.5723,
|
| 108 |
+
"eval_samples_per_second": 87.36,
|
| 109 |
+
"eval_steps_per_second": 12.23,
|
| 110 |
+
"step": 504
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 9.0,
|
| 114 |
+
"eval_accuracy": 0.9978484708775165,
|
| 115 |
+
"eval_f1": 0.9861809045226131,
|
| 116 |
+
"eval_loss": 0.008633743040263653,
|
| 117 |
+
"eval_precision": 0.9861809045226131,
|
| 118 |
+
"eval_recall": 0.9861809045226131,
|
| 119 |
+
"eval_runtime": 0.5754,
|
| 120 |
+
"eval_samples_per_second": 86.898,
|
| 121 |
+
"eval_steps_per_second": 12.166,
|
| 122 |
+
"step": 567
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"eval_accuracy": 0.9983095128323344,
|
| 127 |
+
"eval_f1": 0.9899497487437185,
|
| 128 |
+
"eval_loss": 0.006678320933133364,
|
| 129 |
+
"eval_precision": 0.9899497487437185,
|
| 130 |
+
"eval_recall": 0.9899497487437185,
|
| 131 |
+
"eval_runtime": 0.5717,
|
| 132 |
+
"eval_samples_per_second": 87.461,
|
| 133 |
+
"eval_steps_per_second": 12.245,
|
| 134 |
+
"step": 630
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 11.0,
|
| 138 |
+
"eval_accuracy": 0.9990779160903642,
|
| 139 |
+
"eval_f1": 0.9962311557788944,
|
| 140 |
+
"eval_loss": 0.004529367666691542,
|
| 141 |
+
"eval_precision": 0.9962311557788944,
|
| 142 |
+
"eval_recall": 0.9962311557788944,
|
| 143 |
+
"eval_runtime": 0.5852,
|
| 144 |
+
"eval_samples_per_second": 85.445,
|
| 145 |
+
"eval_steps_per_second": 11.962,
|
| 146 |
+
"step": 693
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 12.0,
|
| 150 |
+
"eval_accuracy": 0.999692638696788,
|
| 151 |
+
"eval_f1": 0.9987437185929648,
|
| 152 |
+
"eval_loss": 0.0013231054181233048,
|
| 153 |
+
"eval_precision": 0.9987437185929648,
|
| 154 |
+
"eval_recall": 0.9987437185929648,
|
| 155 |
+
"eval_runtime": 0.5808,
|
| 156 |
+
"eval_samples_per_second": 86.093,
|
| 157 |
+
"eval_steps_per_second": 12.053,
|
| 158 |
+
"step": 756
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 13.0,
|
| 162 |
+
"eval_accuracy": 0.9990779160903642,
|
| 163 |
+
"eval_f1": 0.9956112852664577,
|
| 164 |
+
"eval_loss": 0.0035528314765542746,
|
| 165 |
+
"eval_precision": 0.9937421777221527,
|
| 166 |
+
"eval_recall": 0.9974874371859297,
|
| 167 |
+
"eval_runtime": 0.6108,
|
| 168 |
+
"eval_samples_per_second": 81.86,
|
| 169 |
+
"eval_steps_per_second": 11.46,
|
| 170 |
+
"step": 819
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.0,
|
| 174 |
+
"eval_accuracy": 1.0,
|
| 175 |
+
"eval_f1": 1.0,
|
| 176 |
+
"eval_loss": 0.00045324634993448853,
|
| 177 |
+
"eval_precision": 1.0,
|
| 178 |
+
"eval_recall": 1.0,
|
| 179 |
+
"eval_runtime": 0.5759,
|
| 180 |
+
"eval_samples_per_second": 86.817,
|
| 181 |
+
"eval_steps_per_second": 12.154,
|
| 182 |
+
"step": 882
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 15.0,
|
| 186 |
+
"eval_accuracy": 1.0,
|
| 187 |
+
"eval_f1": 1.0,
|
| 188 |
+
"eval_loss": 0.00044708128552883863,
|
| 189 |
+
"eval_precision": 1.0,
|
| 190 |
+
"eval_recall": 1.0,
|
| 191 |
+
"eval_runtime": 0.575,
|
| 192 |
+
"eval_samples_per_second": 86.954,
|
| 193 |
+
"eval_steps_per_second": 12.174,
|
| 194 |
+
"step": 945
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 15.87,
|
| 198 |
+
"learning_rate": 1.9491525423728814e-05,
|
| 199 |
+
"loss": 0.0097,
|
| 200 |
+
"step": 1000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 16.0,
|
| 204 |
+
"eval_accuracy": 1.0,
|
| 205 |
+
"eval_f1": 1.0,
|
| 206 |
+
"eval_loss": 0.00018117745639756322,
|
| 207 |
+
"eval_precision": 1.0,
|
| 208 |
+
"eval_recall": 1.0,
|
| 209 |
+
"eval_runtime": 0.5823,
|
| 210 |
+
"eval_samples_per_second": 85.872,
|
| 211 |
+
"eval_steps_per_second": 12.022,
|
| 212 |
+
"step": 1008
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 17.0,
|
| 216 |
+
"eval_accuracy": 1.0,
|
| 217 |
+
"eval_f1": 1.0,
|
| 218 |
+
"eval_loss": 0.00018171708506997675,
|
| 219 |
+
"eval_precision": 1.0,
|
| 220 |
+
"eval_recall": 1.0,
|
| 221 |
+
"eval_runtime": 0.6909,
|
| 222 |
+
"eval_samples_per_second": 72.373,
|
| 223 |
+
"eval_steps_per_second": 10.132,
|
| 224 |
+
"step": 1071
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 18.0,
|
| 228 |
+
"eval_accuracy": 1.0,
|
| 229 |
+
"eval_f1": 1.0,
|
| 230 |
+
"eval_loss": 0.0002043112035607919,
|
| 231 |
+
"eval_precision": 1.0,
|
| 232 |
+
"eval_recall": 1.0,
|
| 233 |
+
"eval_runtime": 0.6068,
|
| 234 |
+
"eval_samples_per_second": 82.399,
|
| 235 |
+
"eval_steps_per_second": 11.536,
|
| 236 |
+
"step": 1134
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 19.0,
|
| 240 |
+
"eval_accuracy": 1.0,
|
| 241 |
+
"eval_f1": 1.0,
|
| 242 |
+
"eval_loss": 0.00015518060536123812,
|
| 243 |
+
"eval_precision": 1.0,
|
| 244 |
+
"eval_recall": 1.0,
|
| 245 |
+
"eval_runtime": 0.594,
|
| 246 |
+
"eval_samples_per_second": 84.176,
|
| 247 |
+
"eval_steps_per_second": 11.785,
|
| 248 |
+
"step": 1197
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 20.0,
|
| 252 |
+
"eval_accuracy": 1.0,
|
| 253 |
+
"eval_f1": 1.0,
|
| 254 |
+
"eval_loss": 0.00014525999722536653,
|
| 255 |
+
"eval_precision": 1.0,
|
| 256 |
+
"eval_recall": 1.0,
|
| 257 |
+
"eval_runtime": 0.5981,
|
| 258 |
+
"eval_samples_per_second": 83.6,
|
| 259 |
+
"eval_steps_per_second": 11.704,
|
| 260 |
+
"step": 1260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 21.0,
|
| 264 |
+
"eval_accuracy": 1.0,
|
| 265 |
+
"eval_f1": 1.0,
|
| 266 |
+
"eval_loss": 0.00013857503654435277,
|
| 267 |
+
"eval_precision": 1.0,
|
| 268 |
+
"eval_recall": 1.0,
|
| 269 |
+
"eval_runtime": 0.5825,
|
| 270 |
+
"eval_samples_per_second": 85.832,
|
| 271 |
+
"eval_steps_per_second": 12.017,
|
| 272 |
+
"step": 1323
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 22.0,
|
| 276 |
+
"eval_accuracy": 1.0,
|
| 277 |
+
"eval_f1": 1.0,
|
| 278 |
+
"eval_loss": 0.00013503569061867893,
|
| 279 |
+
"eval_precision": 1.0,
|
| 280 |
+
"eval_recall": 1.0,
|
| 281 |
+
"eval_runtime": 0.573,
|
| 282 |
+
"eval_samples_per_second": 87.267,
|
| 283 |
+
"eval_steps_per_second": 12.217,
|
| 284 |
+
"step": 1386
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 23.0,
|
| 288 |
+
"eval_accuracy": 1.0,
|
| 289 |
+
"eval_f1": 1.0,
|
| 290 |
+
"eval_loss": 0.00012487478670664132,
|
| 291 |
+
"eval_precision": 1.0,
|
| 292 |
+
"eval_recall": 1.0,
|
| 293 |
+
"eval_runtime": 0.5904,
|
| 294 |
+
"eval_samples_per_second": 84.687,
|
| 295 |
+
"eval_steps_per_second": 11.856,
|
| 296 |
+
"step": 1449
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 23.81,
|
| 300 |
+
"learning_rate": 2.5423728813559323e-06,
|
| 301 |
+
"loss": 0.0019,
|
| 302 |
+
"step": 1500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 24.0,
|
| 306 |
+
"eval_accuracy": 1.0,
|
| 307 |
+
"eval_f1": 1.0,
|
| 308 |
+
"eval_loss": 0.00012091387179680169,
|
| 309 |
+
"eval_precision": 1.0,
|
| 310 |
+
"eval_recall": 1.0,
|
| 311 |
+
"eval_runtime": 0.5792,
|
| 312 |
+
"eval_samples_per_second": 86.322,
|
| 313 |
+
"eval_steps_per_second": 12.085,
|
| 314 |
+
"step": 1512
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 25.0,
|
| 318 |
+
"eval_accuracy": 1.0,
|
| 319 |
+
"eval_f1": 1.0,
|
| 320 |
+
"eval_loss": 0.00011829046707134694,
|
| 321 |
+
"eval_precision": 1.0,
|
| 322 |
+
"eval_recall": 1.0,
|
| 323 |
+
"eval_runtime": 0.6205,
|
| 324 |
+
"eval_samples_per_second": 80.581,
|
| 325 |
+
"eval_steps_per_second": 11.281,
|
| 326 |
+
"step": 1575
|
| 327 |
+
}
|
| 328 |
+
],
|
| 329 |
+
"max_steps": 1575,
|
| 330 |
+
"num_train_epochs": 25,
|
| 331 |
+
"total_flos": 1550715696271320.0,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf590ad94ed3e06f7ac7bc684fa3a96e42ad6f633084f37c17334fcb46ae88a
|
| 3 |
+
size 3835
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|