Commit ·
98ed32c
1
Parent(s): a6c9fa3
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 +14 -0
- trainer_state.json +406 -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 sha256:9af496d3f122fba035b2966b3ca517f44e45e8933cecdde736c2c874732cfe7b
|
| 3 |
+
size 818843397
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ef181d8b6d656bc0e0d99f801a77f0cc3f0e663011eca1365b853163b78b5d5
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f49d9ae327671a9a85afade1c599a97f3c16eec9ee00688d71a77ecd7f94fdd
|
| 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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "bert-base-chinese",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.48704663212435234,
|
| 3 |
+
"best_model_checkpoint": "/bert-finetuned-insurence\\checkpoint-21876",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"global_step": 21876,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.27,
|
| 12 |
+
"learning_rate": 1.9725726823916623e-05,
|
| 13 |
+
"loss": 0.2098,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.55,
|
| 18 |
+
"learning_rate": 1.9451453647833244e-05,
|
| 19 |
+
"loss": 0.1358,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.82,
|
| 24 |
+
"learning_rate": 1.9177180471749866e-05,
|
| 25 |
+
"loss": 0.1246,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_accuracy": 0.067,
|
| 31 |
+
"eval_f1": 0.2237460815047022,
|
| 32 |
+
"eval_loss": 0.11870492994785309,
|
| 33 |
+
"eval_roc_auc": 0.564982260472908,
|
| 34 |
+
"eval_runtime": 3.809,
|
| 35 |
+
"eval_samples_per_second": 262.534,
|
| 36 |
+
"eval_steps_per_second": 16.54,
|
| 37 |
+
"step": 1823
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.1,
|
| 41 |
+
"learning_rate": 1.8902907295666487e-05,
|
| 42 |
+
"loss": 0.1198,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.37,
|
| 47 |
+
"learning_rate": 1.8628634119583108e-05,
|
| 48 |
+
"loss": 0.1134,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.65,
|
| 53 |
+
"learning_rate": 1.8354360943499726e-05,
|
| 54 |
+
"loss": 0.112,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.92,
|
| 59 |
+
"learning_rate": 1.8080087767416347e-05,
|
| 60 |
+
"loss": 0.108,
|
| 61 |
+
"step": 3500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.0,
|
| 65 |
+
"eval_accuracy": 0.091,
|
| 66 |
+
"eval_f1": 0.395417348608838,
|
| 67 |
+
"eval_loss": 0.1071208193898201,
|
| 68 |
+
"eval_roc_auc": 0.6367943008116848,
|
| 69 |
+
"eval_runtime": 3.7754,
|
| 70 |
+
"eval_samples_per_second": 264.874,
|
| 71 |
+
"eval_steps_per_second": 16.687,
|
| 72 |
+
"step": 3646
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.19,
|
| 76 |
+
"learning_rate": 1.780581459133297e-05,
|
| 77 |
+
"loss": 0.1045,
|
| 78 |
+
"step": 4000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.47,
|
| 82 |
+
"learning_rate": 1.753154141524959e-05,
|
| 83 |
+
"loss": 0.1032,
|
| 84 |
+
"step": 4500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.74,
|
| 88 |
+
"learning_rate": 1.725726823916621e-05,
|
| 89 |
+
"loss": 0.1015,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.0,
|
| 94 |
+
"eval_accuracy": 0.099,
|
| 95 |
+
"eval_f1": 0.4248240563019834,
|
| 96 |
+
"eval_loss": 0.10228820890188217,
|
| 97 |
+
"eval_roc_auc": 0.6505844350435338,
|
| 98 |
+
"eval_runtime": 3.7574,
|
| 99 |
+
"eval_samples_per_second": 266.144,
|
| 100 |
+
"eval_steps_per_second": 16.767,
|
| 101 |
+
"step": 5469
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.02,
|
| 105 |
+
"learning_rate": 1.6982995063082832e-05,
|
| 106 |
+
"loss": 0.0992,
|
| 107 |
+
"step": 5500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.29,
|
| 111 |
+
"learning_rate": 1.6708721886999454e-05,
|
| 112 |
+
"loss": 0.0948,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.57,
|
| 117 |
+
"learning_rate": 1.643444871091607e-05,
|
| 118 |
+
"loss": 0.0956,
|
| 119 |
+
"step": 6500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.84,
|
| 123 |
+
"learning_rate": 1.6160175534832693e-05,
|
| 124 |
+
"loss": 0.0951,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.0,
|
| 129 |
+
"eval_accuracy": 0.109,
|
| 130 |
+
"eval_f1": 0.45458612975391494,
|
| 131 |
+
"eval_loss": 0.1022321805357933,
|
| 132 |
+
"eval_roc_auc": 0.6718894766522545,
|
| 133 |
+
"eval_runtime": 3.7018,
|
| 134 |
+
"eval_samples_per_second": 270.139,
|
| 135 |
+
"eval_steps_per_second": 17.019,
|
| 136 |
+
"step": 7292
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.11,
|
| 140 |
+
"learning_rate": 1.5885902358749318e-05,
|
| 141 |
+
"loss": 0.0921,
|
| 142 |
+
"step": 7500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.39,
|
| 146 |
+
"learning_rate": 1.5611629182665936e-05,
|
| 147 |
+
"loss": 0.0869,
|
| 148 |
+
"step": 8000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.66,
|
| 152 |
+
"learning_rate": 1.5337356006582557e-05,
|
| 153 |
+
"loss": 0.0885,
|
| 154 |
+
"step": 8500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 4.94,
|
| 158 |
+
"learning_rate": 1.5063082830499178e-05,
|
| 159 |
+
"loss": 0.0879,
|
| 160 |
+
"step": 9000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 5.0,
|
| 164 |
+
"eval_accuracy": 0.109,
|
| 165 |
+
"eval_f1": 0.4628664979907725,
|
| 166 |
+
"eval_loss": 0.10198137164115906,
|
| 167 |
+
"eval_roc_auc": 0.6755769918598361,
|
| 168 |
+
"eval_runtime": 3.7578,
|
| 169 |
+
"eval_samples_per_second": 266.11,
|
| 170 |
+
"eval_steps_per_second": 16.765,
|
| 171 |
+
"step": 9115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.21,
|
| 175 |
+
"learning_rate": 1.47888096544158e-05,
|
| 176 |
+
"loss": 0.0836,
|
| 177 |
+
"step": 9500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.49,
|
| 181 |
+
"learning_rate": 1.4514536478332419e-05,
|
| 182 |
+
"loss": 0.0816,
|
| 183 |
+
"step": 10000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.76,
|
| 187 |
+
"learning_rate": 1.4240263302249042e-05,
|
| 188 |
+
"loss": 0.0814,
|
| 189 |
+
"step": 10500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.0,
|
| 193 |
+
"eval_accuracy": 0.119,
|
| 194 |
+
"eval_f1": 0.4794083526682134,
|
| 195 |
+
"eval_loss": 0.10448325425386429,
|
| 196 |
+
"eval_roc_auc": 0.6865024293997813,
|
| 197 |
+
"eval_runtime": 3.7811,
|
| 198 |
+
"eval_samples_per_second": 264.471,
|
| 199 |
+
"eval_steps_per_second": 16.662,
|
| 200 |
+
"step": 10938
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.03,
|
| 204 |
+
"learning_rate": 1.3965990126165663e-05,
|
| 205 |
+
"loss": 0.0809,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.31,
|
| 210 |
+
"learning_rate": 1.3691716950082283e-05,
|
| 211 |
+
"loss": 0.076,
|
| 212 |
+
"step": 11500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.58,
|
| 216 |
+
"learning_rate": 1.3417443773998904e-05,
|
| 217 |
+
"loss": 0.0753,
|
| 218 |
+
"step": 12000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.86,
|
| 222 |
+
"learning_rate": 1.3143170597915524e-05,
|
| 223 |
+
"loss": 0.0763,
|
| 224 |
+
"step": 12500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.0,
|
| 228 |
+
"eval_accuracy": 0.12,
|
| 229 |
+
"eval_f1": 0.46037735849056594,
|
| 230 |
+
"eval_loss": 0.10638366639614105,
|
| 231 |
+
"eval_roc_auc": 0.6724519962621105,
|
| 232 |
+
"eval_runtime": 3.6527,
|
| 233 |
+
"eval_samples_per_second": 273.773,
|
| 234 |
+
"eval_steps_per_second": 17.248,
|
| 235 |
+
"step": 12761
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 7.13,
|
| 239 |
+
"learning_rate": 1.2868897421832145e-05,
|
| 240 |
+
"loss": 0.073,
|
| 241 |
+
"step": 13000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.41,
|
| 245 |
+
"learning_rate": 1.2594624245748768e-05,
|
| 246 |
+
"loss": 0.0711,
|
| 247 |
+
"step": 13500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.68,
|
| 251 |
+
"learning_rate": 1.2320351069665388e-05,
|
| 252 |
+
"loss": 0.0707,
|
| 253 |
+
"step": 14000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 7.95,
|
| 257 |
+
"learning_rate": 1.2046077893582009e-05,
|
| 258 |
+
"loss": 0.0719,
|
| 259 |
+
"step": 14500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 8.0,
|
| 263 |
+
"eval_accuracy": 0.117,
|
| 264 |
+
"eval_f1": 0.48321579689703803,
|
| 265 |
+
"eval_loss": 0.10909124463796616,
|
| 266 |
+
"eval_roc_auc": 0.6927193397787977,
|
| 267 |
+
"eval_runtime": 3.6568,
|
| 268 |
+
"eval_samples_per_second": 273.464,
|
| 269 |
+
"eval_steps_per_second": 17.228,
|
| 270 |
+
"step": 14584
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 8.23,
|
| 274 |
+
"learning_rate": 1.177180471749863e-05,
|
| 275 |
+
"loss": 0.0659,
|
| 276 |
+
"step": 15000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 8.5,
|
| 280 |
+
"learning_rate": 1.149753154141525e-05,
|
| 281 |
+
"loss": 0.0669,
|
| 282 |
+
"step": 15500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 8.78,
|
| 286 |
+
"learning_rate": 1.1223258365331871e-05,
|
| 287 |
+
"loss": 0.0666,
|
| 288 |
+
"step": 16000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.0,
|
| 292 |
+
"eval_accuracy": 0.114,
|
| 293 |
+
"eval_f1": 0.4760218385716393,
|
| 294 |
+
"eval_loss": 0.11018569767475128,
|
| 295 |
+
"eval_roc_auc": 0.6823008499632444,
|
| 296 |
+
"eval_runtime": 3.7151,
|
| 297 |
+
"eval_samples_per_second": 269.174,
|
| 298 |
+
"eval_steps_per_second": 16.958,
|
| 299 |
+
"step": 16407
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 9.05,
|
| 303 |
+
"learning_rate": 1.0948985189248494e-05,
|
| 304 |
+
"loss": 0.0662,
|
| 305 |
+
"step": 16500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.33,
|
| 309 |
+
"learning_rate": 1.0674712013165114e-05,
|
| 310 |
+
"loss": 0.0626,
|
| 311 |
+
"step": 17000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 9.6,
|
| 315 |
+
"learning_rate": 1.0400438837081735e-05,
|
| 316 |
+
"loss": 0.0622,
|
| 317 |
+
"step": 17500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.87,
|
| 321 |
+
"learning_rate": 1.0126165660998355e-05,
|
| 322 |
+
"loss": 0.0632,
|
| 323 |
+
"step": 18000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 10.0,
|
| 327 |
+
"eval_accuracy": 0.12,
|
| 328 |
+
"eval_f1": 0.47904364107734404,
|
| 329 |
+
"eval_loss": 0.11133165657520294,
|
| 330 |
+
"eval_roc_auc": 0.6874577169116662,
|
| 331 |
+
"eval_runtime": 3.6393,
|
| 332 |
+
"eval_samples_per_second": 274.78,
|
| 333 |
+
"eval_steps_per_second": 17.311,
|
| 334 |
+
"step": 18230
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 10.15,
|
| 338 |
+
"learning_rate": 9.851892484914976e-06,
|
| 339 |
+
"loss": 0.0612,
|
| 340 |
+
"step": 18500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 10.42,
|
| 344 |
+
"learning_rate": 9.577619308831597e-06,
|
| 345 |
+
"loss": 0.0592,
|
| 346 |
+
"step": 19000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 10.7,
|
| 350 |
+
"learning_rate": 9.303346132748218e-06,
|
| 351 |
+
"loss": 0.0589,
|
| 352 |
+
"step": 19500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.97,
|
| 356 |
+
"learning_rate": 9.02907295666484e-06,
|
| 357 |
+
"loss": 0.0591,
|
| 358 |
+
"step": 20000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 11.0,
|
| 362 |
+
"eval_accuracy": 0.112,
|
| 363 |
+
"eval_f1": 0.47534802784222746,
|
| 364 |
+
"eval_loss": 0.11583616584539413,
|
| 365 |
+
"eval_roc_auc": 0.6848022405962436,
|
| 366 |
+
"eval_runtime": 3.6433,
|
| 367 |
+
"eval_samples_per_second": 274.479,
|
| 368 |
+
"eval_steps_per_second": 17.292,
|
| 369 |
+
"step": 20053
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 11.25,
|
| 373 |
+
"learning_rate": 8.75479978058146e-06,
|
| 374 |
+
"loss": 0.0561,
|
| 375 |
+
"step": 20500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 11.52,
|
| 379 |
+
"learning_rate": 8.48052660449808e-06,
|
| 380 |
+
"loss": 0.0553,
|
| 381 |
+
"step": 21000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 11.79,
|
| 385 |
+
"learning_rate": 8.206253428414702e-06,
|
| 386 |
+
"loss": 0.0562,
|
| 387 |
+
"step": 21500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 12.0,
|
| 391 |
+
"eval_accuracy": 0.114,
|
| 392 |
+
"eval_f1": 0.48704663212435234,
|
| 393 |
+
"eval_loss": 0.11700723320245743,
|
| 394 |
+
"eval_roc_auc": 0.6955956463313885,
|
| 395 |
+
"eval_runtime": 3.6462,
|
| 396 |
+
"eval_samples_per_second": 274.256,
|
| 397 |
+
"eval_steps_per_second": 17.278,
|
| 398 |
+
"step": 21876
|
| 399 |
+
}
|
| 400 |
+
],
|
| 401 |
+
"max_steps": 36460,
|
| 402 |
+
"num_train_epochs": 20,
|
| 403 |
+
"total_flos": 2.3033804521688064e+16,
|
| 404 |
+
"trial_name": null,
|
| 405 |
+
"trial_params": null
|
| 406 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08305c3a41da0a145a676aa35db2f16d172b4f5f4b25dcc6840aaa3d003f6ab1
|
| 3 |
+
size 3451
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|