Upload folder using huggingface_hub
Browse files- README.md +5 -5
- all_results.json +12 -12
- eval_results.json +7 -7
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +40 -754
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [./core2/](https://huggingface.co/./core2/) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 2.
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -40,10 +40,10 @@ The following hyperparameters were used during training:
|
|
| 40 |
- train_batch_size: 1
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
-
- gradient_accumulation_steps:
|
| 44 |
-
- total_train_batch_size:
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
-
- lr_scheduler_type:
|
| 47 |
- num_epochs: 1.0
|
| 48 |
|
| 49 |
### Training results
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [./core2/](https://huggingface.co/./core2/) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.2227
|
| 20 |
+
- Accuracy: 0.4777
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 40 |
- train_batch_size: 1
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 512
|
| 44 |
+
- total_train_batch_size: 512
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: constant
|
| 47 |
- num_epochs: 1.0
|
| 48 |
|
| 49 |
### Training results
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 2.
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
"eval_samples": 129,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 9.
|
| 9 |
-
"perplexity":
|
| 10 |
-
"train_loss":
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples":
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second":
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.9,
|
| 3 |
+
"eval_accuracy": 0.4777027590230891,
|
| 4 |
+
"eval_loss": 2.222717761993408,
|
| 5 |
+
"eval_runtime": 1.797,
|
| 6 |
"eval_samples": 129,
|
| 7 |
+
"eval_samples_per_second": 71.786,
|
| 8 |
+
"eval_steps_per_second": 9.46,
|
| 9 |
+
"perplexity": 9.2323882343288,
|
| 10 |
+
"train_loss": 2.689473125669691,
|
| 11 |
+
"train_runtime": 118.9327,
|
| 12 |
+
"train_samples": 5117,
|
| 13 |
+
"train_samples_per_second": 43.024,
|
| 14 |
+
"train_steps_per_second": 0.076
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 2.
|
| 5 |
-
"eval_runtime": 1.
|
| 6 |
"eval_samples": 129,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 9.
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.9,
|
| 3 |
+
"eval_accuracy": 0.4777027590230891,
|
| 4 |
+
"eval_loss": 2.222717761993408,
|
| 5 |
+
"eval_runtime": 1.797,
|
| 6 |
"eval_samples": 129,
|
| 7 |
+
"eval_samples_per_second": 71.786,
|
| 8 |
+
"eval_steps_per_second": 9.46,
|
| 9 |
+
"perplexity": 9.2323882343288
|
| 10 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 929067029
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57f122b3164f3ec83b608251f67e4b6d4771c756f4fc5a1e7b9481acfbd9921e
|
| 3 |
size 929067029
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.9,
|
| 3 |
+
"train_loss": 2.689473125669691,
|
| 4 |
+
"train_runtime": 118.9327,
|
| 5 |
+
"train_samples": 5117,
|
| 6 |
+
"train_samples_per_second": 43.024,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,796 +1,82 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.01,
|
| 13 |
-
"learning_rate": 0.0009922456575682382,
|
| 14 |
-
"loss": 4.0749,
|
| 15 |
-
"step": 50
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.02,
|
| 19 |
-
"learning_rate": 0.0009844913151364765,
|
| 20 |
-
"loss": 3.9181,
|
| 21 |
-
"step": 100
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.02,
|
| 25 |
-
"learning_rate": 0.0009767369727047147,
|
| 26 |
-
"loss": 3.8669,
|
| 27 |
-
"step": 150
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.03,
|
| 31 |
-
"learning_rate": 0.0009689826302729528,
|
| 32 |
-
"loss": 3.8069,
|
| 33 |
-
"step": 200
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.04,
|
| 37 |
-
"learning_rate": 0.000961228287841191,
|
| 38 |
-
"loss": 3.7749,
|
| 39 |
-
"step": 250
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.05,
|
| 43 |
-
"learning_rate": 0.0009534739454094294,
|
| 44 |
-
"loss": 3.7757,
|
| 45 |
-
"step": 300
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.05,
|
| 49 |
-
"learning_rate": 0.0009457196029776675,
|
| 50 |
-
"loss": 3.7511,
|
| 51 |
-
"step": 350
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.06,
|
| 55 |
-
"learning_rate": 0.0009379652605459057,
|
| 56 |
-
"loss": 3.684,
|
| 57 |
-
"step": 400
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.07,
|
| 61 |
-
"learning_rate": 0.000930210918114144,
|
| 62 |
-
"loss": 3.6771,
|
| 63 |
-
"step": 450
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.08,
|
| 67 |
-
"learning_rate": 0.0009224565756823822,
|
| 68 |
-
"loss": 3.6402,
|
| 69 |
-
"step": 500
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.09,
|
| 73 |
-
"learning_rate": 0.0009147022332506204,
|
| 74 |
-
"loss": 3.6889,
|
| 75 |
-
"step": 550
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.09,
|
| 79 |
-
"learning_rate": 0.0009069478908188585,
|
| 80 |
-
"loss": 3.6868,
|
| 81 |
-
"step": 600
|
| 82 |
-
},
|
| 83 |
{
|
| 84 |
"epoch": 0.1,
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss":
|
| 87 |
-
"step":
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.11,
|
| 91 |
-
"learning_rate": 0.000891439205955335,
|
| 92 |
-
"loss": 3.6314,
|
| 93 |
-
"step": 700
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.12,
|
| 97 |
-
"learning_rate": 0.0008836848635235732,
|
| 98 |
-
"loss": 3.6376,
|
| 99 |
-
"step": 750
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.12,
|
| 103 |
-
"learning_rate": 0.0008759305210918114,
|
| 104 |
-
"loss": 3.6291,
|
| 105 |
-
"step": 800
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.13,
|
| 109 |
-
"learning_rate": 0.0008681761786600497,
|
| 110 |
-
"loss": 3.629,
|
| 111 |
-
"step": 850
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.14,
|
| 115 |
-
"learning_rate": 0.0008604218362282879,
|
| 116 |
-
"loss": 3.5972,
|
| 117 |
-
"step": 900
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 0.15,
|
| 121 |
-
"learning_rate": 0.0008526674937965261,
|
| 122 |
-
"loss": 3.6299,
|
| 123 |
-
"step": 950
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.16,
|
| 127 |
-
"learning_rate": 0.0008449131513647643,
|
| 128 |
-
"loss": 3.551,
|
| 129 |
-
"step": 1000
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.16,
|
| 133 |
-
"learning_rate": 0.0008371588089330025,
|
| 134 |
-
"loss": 3.5943,
|
| 135 |
-
"step": 1050
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.17,
|
| 139 |
-
"learning_rate": 0.0008294044665012407,
|
| 140 |
-
"loss": 3.5458,
|
| 141 |
-
"step": 1100
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.18,
|
| 145 |
-
"learning_rate": 0.0008216501240694789,
|
| 146 |
-
"loss": 3.581,
|
| 147 |
-
"step": 1150
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 0.19,
|
| 151 |
-
"learning_rate": 0.0008138957816377171,
|
| 152 |
-
"loss": 3.542,
|
| 153 |
-
"step": 1200
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.19,
|
| 157 |
-
"learning_rate": 0.0008061414392059554,
|
| 158 |
-
"loss": 3.5666,
|
| 159 |
-
"step": 1250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.2,
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 3.
|
| 165 |
-
"step":
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.21,
|
| 169 |
-
"learning_rate": 0.0007906327543424317,
|
| 170 |
-
"loss": 3.5315,
|
| 171 |
-
"step": 1350
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.22,
|
| 175 |
-
"learning_rate": 0.00078287841191067,
|
| 176 |
-
"loss": 3.4934,
|
| 177 |
-
"step": 1400
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.22,
|
| 181 |
-
"learning_rate": 0.0007751240694789083,
|
| 182 |
-
"loss": 3.5086,
|
| 183 |
-
"step": 1450
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 0.23,
|
| 187 |
-
"learning_rate": 0.0007673697270471465,
|
| 188 |
-
"loss": 3.5028,
|
| 189 |
-
"step": 1500
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.24,
|
| 193 |
-
"learning_rate": 0.0007596153846153846,
|
| 194 |
-
"loss": 3.4822,
|
| 195 |
-
"step": 1550
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.25,
|
| 199 |
-
"learning_rate": 0.0007518610421836228,
|
| 200 |
-
"loss": 3.4943,
|
| 201 |
-
"step": 1600
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.26,
|
| 205 |
-
"learning_rate": 0.0007441066997518611,
|
| 206 |
-
"loss": 3.5014,
|
| 207 |
-
"step": 1650
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.26,
|
| 211 |
-
"learning_rate": 0.0007363523573200993,
|
| 212 |
-
"loss": 3.4705,
|
| 213 |
-
"step": 1700
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.27,
|
| 217 |
-
"learning_rate": 0.0007285980148883374,
|
| 218 |
-
"loss": 3.4899,
|
| 219 |
-
"step": 1750
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.28,
|
| 223 |
-
"learning_rate": 0.0007208436724565756,
|
| 224 |
-
"loss": 3.4403,
|
| 225 |
-
"step": 1800
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.29,
|
| 229 |
-
"learning_rate": 0.0007130893300248139,
|
| 230 |
-
"loss": 3.4123,
|
| 231 |
-
"step": 1850
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.29,
|
| 235 |
-
"learning_rate": 0.0007053349875930521,
|
| 236 |
-
"loss": 3.4231,
|
| 237 |
-
"step": 1900
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 0.3,
|
| 241 |
-
"learning_rate": 0.
|
| 242 |
-
"loss": 3.
|
| 243 |
-
"step":
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.31,
|
| 247 |
-
"learning_rate": 0.0006898263027295286,
|
| 248 |
-
"loss": 3.3722,
|
| 249 |
-
"step": 2000
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.32,
|
| 253 |
-
"learning_rate": 0.0006820719602977668,
|
| 254 |
-
"loss": 3.4255,
|
| 255 |
-
"step": 2050
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.33,
|
| 259 |
-
"learning_rate": 0.000674317617866005,
|
| 260 |
-
"loss": 3.4004,
|
| 261 |
-
"step": 2100
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.33,
|
| 265 |
-
"learning_rate": 0.0006665632754342432,
|
| 266 |
-
"loss": 3.3749,
|
| 267 |
-
"step": 2150
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.34,
|
| 271 |
-
"learning_rate": 0.0006588089330024815,
|
| 272 |
-
"loss": 3.3498,
|
| 273 |
-
"step": 2200
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.35,
|
| 277 |
-
"learning_rate": 0.0006510545905707196,
|
| 278 |
-
"loss": 3.4563,
|
| 279 |
-
"step": 2250
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.36,
|
| 283 |
-
"learning_rate": 0.0006433002481389578,
|
| 284 |
-
"loss": 3.392,
|
| 285 |
-
"step": 2300
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.36,
|
| 289 |
-
"learning_rate": 0.000635545905707196,
|
| 290 |
-
"loss": 3.3686,
|
| 291 |
-
"step": 2350
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.37,
|
| 295 |
-
"learning_rate": 0.0006277915632754343,
|
| 296 |
-
"loss": 3.3739,
|
| 297 |
-
"step": 2400
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.38,
|
| 301 |
-
"learning_rate": 0.0006200372208436724,
|
| 302 |
-
"loss": 3.3357,
|
| 303 |
-
"step": 2450
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.39,
|
| 307 |
-
"learning_rate": 0.0006122828784119106,
|
| 308 |
-
"loss": 3.3859,
|
| 309 |
-
"step": 2500
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.4,
|
| 313 |
-
"learning_rate": 0.0006045285359801489,
|
| 314 |
-
"loss": 3.3605,
|
| 315 |
-
"step": 2550
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.4,
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss":
|
| 321 |
-
"step":
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.41,
|
| 325 |
-
"learning_rate": 0.0005890198511166254,
|
| 326 |
-
"loss": 3.3729,
|
| 327 |
-
"step": 2650
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.42,
|
| 331 |
-
"learning_rate": 0.0005812655086848635,
|
| 332 |
-
"loss": 3.3592,
|
| 333 |
-
"step": 2700
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.43,
|
| 337 |
-
"learning_rate": 0.0005735111662531017,
|
| 338 |
-
"loss": 3.3576,
|
| 339 |
-
"step": 2750
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.43,
|
| 343 |
-
"learning_rate": 0.00056575682382134,
|
| 344 |
-
"loss": 3.3464,
|
| 345 |
-
"step": 2800
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.44,
|
| 349 |
-
"learning_rate": 0.0005580024813895782,
|
| 350 |
-
"loss": 3.3225,
|
| 351 |
-
"step": 2850
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 0.45,
|
| 355 |
-
"learning_rate": 0.0005502481389578163,
|
| 356 |
-
"loss": 3.3228,
|
| 357 |
-
"step": 2900
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 0.46,
|
| 361 |
-
"learning_rate": 0.0005424937965260545,
|
| 362 |
-
"loss": 3.3369,
|
| 363 |
-
"step": 2950
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 0.47,
|
| 367 |
-
"learning_rate": 0.0005347394540942928,
|
| 368 |
-
"loss": 3.2912,
|
| 369 |
-
"step": 3000
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.47,
|
| 373 |
-
"learning_rate": 0.000526985111662531,
|
| 374 |
-
"loss": 3.2722,
|
| 375 |
-
"step": 3050
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.48,
|
| 379 |
-
"learning_rate": 0.0005192307692307693,
|
| 380 |
-
"loss": 3.2878,
|
| 381 |
-
"step": 3100
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.49,
|
| 385 |
-
"learning_rate": 0.0005114764267990075,
|
| 386 |
-
"loss": 3.2558,
|
| 387 |
-
"step": 3150
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.5,
|
| 391 |
-
"learning_rate": 0.0005037220843672457,
|
| 392 |
-
"loss": 3.3018,
|
| 393 |
-
"step": 3200
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.5,
|
| 397 |
-
"learning_rate": 0.
|
| 398 |
-
"loss":
|
| 399 |
-
"step":
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.51,
|
| 403 |
-
"learning_rate": 0.00048821339950372213,
|
| 404 |
-
"loss": 3.2249,
|
| 405 |
-
"step": 3300
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.52,
|
| 409 |
-
"learning_rate": 0.0004804590570719603,
|
| 410 |
-
"loss": 3.2703,
|
| 411 |
-
"step": 3350
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.53,
|
| 415 |
-
"learning_rate": 0.00047270471464019853,
|
| 416 |
-
"loss": 3.2871,
|
| 417 |
-
"step": 3400
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.54,
|
| 421 |
-
"learning_rate": 0.0004649503722084367,
|
| 422 |
-
"loss": 3.2357,
|
| 423 |
-
"step": 3450
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.54,
|
| 427 |
-
"learning_rate": 0.000457196029776675,
|
| 428 |
-
"loss": 3.2428,
|
| 429 |
-
"step": 3500
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.55,
|
| 433 |
-
"learning_rate": 0.00044944168734491316,
|
| 434 |
-
"loss": 3.2125,
|
| 435 |
-
"step": 3550
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.56,
|
| 439 |
-
"learning_rate": 0.0004416873449131514,
|
| 440 |
-
"loss": 3.2338,
|
| 441 |
-
"step": 3600
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.57,
|
| 445 |
-
"learning_rate": 0.00043393300248138956,
|
| 446 |
-
"loss": 3.288,
|
| 447 |
-
"step": 3650
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 0.57,
|
| 451 |
-
"learning_rate": 0.0004261786600496278,
|
| 452 |
-
"loss": 3.2564,
|
| 453 |
-
"step": 3700
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.58,
|
| 457 |
-
"learning_rate": 0.000418424317617866,
|
| 458 |
-
"loss": 3.1859,
|
| 459 |
-
"step": 3750
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.59,
|
| 463 |
-
"learning_rate": 0.00041066997518610424,
|
| 464 |
-
"loss": 3.2368,
|
| 465 |
-
"step": 3800
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.6,
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss":
|
| 471 |
-
"step":
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.6,
|
| 475 |
-
"learning_rate": 0.00039516129032258064,
|
| 476 |
-
"loss": 3.1754,
|
| 477 |
-
"step": 3900
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 0.61,
|
| 481 |
-
"learning_rate": 0.00038740694789081887,
|
| 482 |
-
"loss": 3.2392,
|
| 483 |
-
"step": 3950
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 0.62,
|
| 487 |
-
"learning_rate": 0.00037965260545905704,
|
| 488 |
-
"loss": 3.2382,
|
| 489 |
-
"step": 4000
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.63,
|
| 493 |
-
"learning_rate": 0.00037189826302729527,
|
| 494 |
-
"loss": 3.2545,
|
| 495 |
-
"step": 4050
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.64,
|
| 499 |
-
"learning_rate": 0.00036414392059553355,
|
| 500 |
-
"loss": 3.1993,
|
| 501 |
-
"step": 4100
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.64,
|
| 505 |
-
"learning_rate": 0.0003563895781637717,
|
| 506 |
-
"loss": 3.1565,
|
| 507 |
-
"step": 4150
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.65,
|
| 511 |
-
"learning_rate": 0.00034863523573200995,
|
| 512 |
-
"loss": 3.2112,
|
| 513 |
-
"step": 4200
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.66,
|
| 517 |
-
"learning_rate": 0.0003408808933002481,
|
| 518 |
-
"loss": 3.1617,
|
| 519 |
-
"step": 4250
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 0.67,
|
| 523 |
-
"learning_rate": 0.00033312655086848635,
|
| 524 |
-
"loss": 3.1602,
|
| 525 |
-
"step": 4300
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 0.67,
|
| 529 |
-
"learning_rate": 0.0003253722084367246,
|
| 530 |
-
"loss": 3.1477,
|
| 531 |
-
"step": 4350
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.68,
|
| 535 |
-
"learning_rate": 0.0003176178660049628,
|
| 536 |
-
"loss": 3.1583,
|
| 537 |
-
"step": 4400
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.69,
|
| 541 |
-
"learning_rate": 0.00030986352357320103,
|
| 542 |
-
"loss": 3.207,
|
| 543 |
-
"step": 4450
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 0.7,
|
| 547 |
-
"learning_rate": 0.
|
| 548 |
-
"loss":
|
| 549 |
-
"step":
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 0.71,
|
| 553 |
-
"learning_rate": 0.00029435483870967743,
|
| 554 |
-
"loss": 3.0965,
|
| 555 |
-
"step": 4550
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 0.71,
|
| 559 |
-
"learning_rate": 0.0002866004962779156,
|
| 560 |
-
"loss": 3.154,
|
| 561 |
-
"step": 4600
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 0.72,
|
| 565 |
-
"learning_rate": 0.0002788461538461539,
|
| 566 |
-
"loss": 3.1413,
|
| 567 |
-
"step": 4650
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 0.73,
|
| 571 |
-
"learning_rate": 0.00027109181141439205,
|
| 572 |
-
"loss": 3.1373,
|
| 573 |
-
"step": 4700
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.74,
|
| 577 |
-
"learning_rate": 0.0002633374689826303,
|
| 578 |
-
"loss": 3.1198,
|
| 579 |
-
"step": 4750
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 0.74,
|
| 583 |
-
"learning_rate": 0.0002555831265508685,
|
| 584 |
-
"loss": 3.1047,
|
| 585 |
-
"step": 4800
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.75,
|
| 589 |
-
"learning_rate": 0.0002478287841191067,
|
| 590 |
-
"loss": 3.1728,
|
| 591 |
-
"step": 4850
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.76,
|
| 595 |
-
"learning_rate": 0.0002400744416873449,
|
| 596 |
-
"loss": 3.1262,
|
| 597 |
-
"step": 4900
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 0.77,
|
| 601 |
-
"learning_rate": 0.00023232009925558313,
|
| 602 |
-
"loss": 3.1111,
|
| 603 |
-
"step": 4950
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 0.78,
|
| 607 |
-
"learning_rate": 0.00022456575682382136,
|
| 608 |
-
"loss": 3.1426,
|
| 609 |
-
"step": 5000
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.78,
|
| 613 |
-
"learning_rate": 0.00021681141439205956,
|
| 614 |
-
"loss": 3.1709,
|
| 615 |
-
"step": 5050
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 0.79,
|
| 619 |
-
"learning_rate": 0.00020905707196029776,
|
| 620 |
-
"loss": 3.1666,
|
| 621 |
-
"step": 5100
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.8,
|
| 625 |
-
"learning_rate": 0.
|
| 626 |
-
"loss":
|
| 627 |
-
"step":
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 0.81,
|
| 631 |
-
"learning_rate": 0.0001935483870967742,
|
| 632 |
-
"loss": 3.1585,
|
| 633 |
-
"step": 5200
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.81,
|
| 637 |
-
"learning_rate": 0.00018579404466501241,
|
| 638 |
-
"loss": 3.0784,
|
| 639 |
-
"step": 5250
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 0.82,
|
| 643 |
-
"learning_rate": 0.00017803970223325061,
|
| 644 |
-
"loss": 3.1064,
|
| 645 |
-
"step": 5300
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 0.83,
|
| 649 |
-
"learning_rate": 0.00017028535980148884,
|
| 650 |
-
"loss": 3.1601,
|
| 651 |
-
"step": 5350
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 0.84,
|
| 655 |
-
"learning_rate": 0.00016253101736972707,
|
| 656 |
-
"loss": 3.1306,
|
| 657 |
-
"step": 5400
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 0.85,
|
| 661 |
-
"learning_rate": 0.00015477667493796527,
|
| 662 |
-
"loss": 3.1461,
|
| 663 |
-
"step": 5450
|
| 664 |
-
},
|
| 665 |
-
{
|
| 666 |
-
"epoch": 0.85,
|
| 667 |
-
"learning_rate": 0.00014702233250620347,
|
| 668 |
-
"loss": 3.1139,
|
| 669 |
-
"step": 5500
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.86,
|
| 673 |
-
"learning_rate": 0.0001392679900744417,
|
| 674 |
-
"loss": 3.0884,
|
| 675 |
-
"step": 5550
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 0.87,
|
| 679 |
-
"learning_rate": 0.0001315136476426799,
|
| 680 |
-
"loss": 3.1221,
|
| 681 |
-
"step": 5600
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 0.88,
|
| 685 |
-
"learning_rate": 0.00012375930521091812,
|
| 686 |
-
"loss": 3.0781,
|
| 687 |
-
"step": 5650
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 0.88,
|
| 691 |
-
"learning_rate": 0.00011600496277915632,
|
| 692 |
-
"loss": 3.156,
|
| 693 |
-
"step": 5700
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"epoch": 0.89,
|
| 697 |
-
"learning_rate": 0.00010825062034739454,
|
| 698 |
-
"loss": 3.1047,
|
| 699 |
-
"step": 5750
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.9,
|
| 703 |
-
"learning_rate": 0.
|
| 704 |
-
"loss":
|
| 705 |
-
"step":
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"epoch": 0.91,
|
| 709 |
-
"learning_rate": 9.274193548387098e-05,
|
| 710 |
-
"loss": 3.1423,
|
| 711 |
-
"step": 5850
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 0.91,
|
| 715 |
-
"learning_rate": 8.498759305210918e-05,
|
| 716 |
-
"loss": 3.1057,
|
| 717 |
-
"step": 5900
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 0.92,
|
| 721 |
-
"learning_rate": 7.723325062034739e-05,
|
| 722 |
-
"loss": 3.0984,
|
| 723 |
-
"step": 5950
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 0.93,
|
| 727 |
-
"learning_rate": 6.947890818858562e-05,
|
| 728 |
-
"loss": 3.1098,
|
| 729 |
-
"step": 6000
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 0.94,
|
| 733 |
-
"learning_rate": 6.172456575682382e-05,
|
| 734 |
-
"loss": 3.1232,
|
| 735 |
-
"step": 6050
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 0.
|
| 739 |
-
"
|
| 740 |
-
"
|
| 741 |
-
"
|
| 742 |
-
|
| 743 |
-
|
| 744 |
-
"
|
| 745 |
-
"learning_rate": 4.621588089330025e-05,
|
| 746 |
-
"loss": 3.1156,
|
| 747 |
-
"step": 6150
|
| 748 |
-
},
|
| 749 |
-
{
|
| 750 |
-
"epoch": 0.96,
|
| 751 |
-
"learning_rate": 3.846153846153846e-05,
|
| 752 |
-
"loss": 3.1295,
|
| 753 |
-
"step": 6200
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"epoch": 0.97,
|
| 757 |
-
"learning_rate": 3.0707196029776676e-05,
|
| 758 |
-
"loss": 3.0784,
|
| 759 |
-
"step": 6250
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 0.98,
|
| 763 |
-
"learning_rate": 2.295285359801489e-05,
|
| 764 |
-
"loss": 3.1048,
|
| 765 |
-
"step": 6300
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.98,
|
| 769 |
-
"learning_rate": 1.5198511166253101e-05,
|
| 770 |
-
"loss": 3.1145,
|
| 771 |
-
"step": 6350
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 0.99,
|
| 775 |
-
"learning_rate": 7.444168734491316e-06,
|
| 776 |
-
"loss": 3.185,
|
| 777 |
-
"step": 6400
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 1.0,
|
| 781 |
-
"step": 6448,
|
| 782 |
-
"total_flos": 1.0568400432109978e+17,
|
| 783 |
-
"train_loss": 3.3343640817306177,
|
| 784 |
-
"train_runtime": 1458.5581,
|
| 785 |
-
"train_samples_per_second": 35.367,
|
| 786 |
-
"train_steps_per_second": 4.421
|
| 787 |
}
|
| 788 |
],
|
| 789 |
-
"logging_steps":
|
| 790 |
-
"max_steps":
|
| 791 |
"num_train_epochs": 1,
|
| 792 |
-
"save_steps": -
|
| 793 |
-
"total_flos":
|
| 794 |
"trial_name": null,
|
| 795 |
"trial_params": null
|
| 796 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9005276529216337,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.1,
|
| 13 |
+
"learning_rate": 0.001,
|
| 14 |
+
"loss": 2.3313,
|
| 15 |
+
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.2,
|
| 19 |
+
"learning_rate": 0.001,
|
| 20 |
+
"loss": 3.851,
|
| 21 |
+
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.3,
|
| 25 |
+
"learning_rate": 0.001,
|
| 26 |
+
"loss": 3.2287,
|
| 27 |
+
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.4,
|
| 31 |
+
"learning_rate": 0.001,
|
| 32 |
+
"loss": 2.7855,
|
| 33 |
+
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.5,
|
| 37 |
+
"learning_rate": 0.001,
|
| 38 |
+
"loss": 2.6085,
|
| 39 |
+
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.6,
|
| 43 |
+
"learning_rate": 0.001,
|
| 44 |
+
"loss": 2.4226,
|
| 45 |
+
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.7,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 2.3728,
|
| 51 |
+
"step": 7
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.8,
|
| 55 |
+
"learning_rate": 0.001,
|
| 56 |
+
"loss": 2.3366,
|
| 57 |
+
"step": 8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.9,
|
| 61 |
+
"learning_rate": 0.001,
|
| 62 |
+
"loss": 2.2684,
|
| 63 |
+
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.9,
|
| 67 |
+
"step": 9,
|
| 68 |
+
"total_flos": 9440754728435712.0,
|
| 69 |
+
"train_loss": 2.689473125669691,
|
| 70 |
+
"train_runtime": 118.9327,
|
| 71 |
+
"train_samples_per_second": 43.024,
|
| 72 |
+
"train_steps_per_second": 0.076
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
}
|
| 74 |
],
|
| 75 |
+
"logging_steps": 1.0,
|
| 76 |
+
"max_steps": 9,
|
| 77 |
"num_train_epochs": 1,
|
| 78 |
+
"save_steps": -9,
|
| 79 |
+
"total_flos": 9440754728435712.0,
|
| 80 |
"trial_name": null,
|
| 81 |
"trial_params": null
|
| 82 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b86cd19e50153cca84ec432ffe3a736db67de735000a21e789fbd7059d3ac7d6
|
| 3 |
size 4027
|