Upload folder using huggingface_hub
Browse files- README.md +3 -3
- all_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +125 -209
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -31,12 +31,12 @@ More information needed
|
|
| 31 |
### Training hyperparameters
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
-
- learning_rate:
|
| 35 |
- train_batch_size: 1
|
| 36 |
- eval_batch_size: 1
|
| 37 |
- seed: 42
|
| 38 |
-
- gradient_accumulation_steps:
|
| 39 |
-
- total_train_batch_size:
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: constant
|
| 42 |
- num_epochs: 5.0
|
|
|
|
| 31 |
### Training hyperparameters
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 1e-05
|
| 35 |
- train_batch_size: 1
|
| 36 |
- eval_batch_size: 1
|
| 37 |
- seed: 42
|
| 38 |
+
- gradient_accumulation_steps: 8
|
| 39 |
+
- total_train_batch_size: 8
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: constant
|
| 42 |
- num_epochs: 5.0
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 4.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.94,
|
| 3 |
+
"train_loss": 2.042334004452354,
|
| 4 |
+
"train_runtime": 318.1284,
|
| 5 |
+
"train_samples": 308,
|
| 6 |
+
"train_samples_per_second": 4.841,
|
| 7 |
+
"train_steps_per_second": 0.597
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70790896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b01c7704f3eac1238c897e633f9b20a7acce4704430aacf188f1e033cca89ca3
|
| 3 |
size 70790896
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 4.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.94,
|
| 3 |
+
"train_loss": 2.042334004452354,
|
| 4 |
+
"train_runtime": 318.1284,
|
| 5 |
+
"train_samples": 308,
|
| 6 |
+
"train_samples_per_second": 4.841,
|
| 7 |
+
"train_steps_per_second": 0.597
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,340 +1,256 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 4.
|
| 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.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 5
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 10
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 15
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss":
|
| 33 |
"step": 20
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
"step": 25
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss":
|
| 45 |
"step": 30
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 35
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss":
|
| 57 |
"step": 40
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss":
|
| 63 |
"step": 45
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch":
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss":
|
| 69 |
"step": 50
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 1.
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss":
|
| 75 |
"step": 55
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 1.
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss":
|
| 81 |
"step": 60
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 1.
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss":
|
| 87 |
"step": 65
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 1.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 70
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 1.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss":
|
| 99 |
"step": 75
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss":
|
| 105 |
"step": 80
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss":
|
| 111 |
"step": 85
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss":
|
| 117 |
"step": 90
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss":
|
| 123 |
"step": 95
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss":
|
| 129 |
"step": 100
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss":
|
| 135 |
"step": 105
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 2.
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss":
|
| 141 |
"step": 110
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 2.
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss":
|
| 147 |
"step": 115
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss":
|
| 153 |
"step": 120
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss":
|
| 159 |
"step": 125
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss":
|
| 165 |
"step": 130
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss":
|
| 171 |
"step": 135
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss":
|
| 177 |
"step": 140
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss":
|
| 183 |
"step": 145
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss":
|
| 189 |
"step": 150
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss":
|
| 195 |
"step": 155
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss":
|
| 201 |
"step": 160
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss":
|
| 207 |
"step": 165
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss":
|
| 213 |
"step": 170
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss":
|
| 219 |
"step": 175
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss":
|
| 225 |
"step": 180
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss":
|
| 231 |
"step": 185
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss":
|
| 237 |
"step": 190
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
"
|
| 247 |
-
"learning_rate": 0.001,
|
| 248 |
-
"loss": 3.6588,
|
| 249 |
-
"step": 200
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 3.89,
|
| 253 |
-
"learning_rate": 0.001,
|
| 254 |
-
"loss": 3.6882,
|
| 255 |
-
"step": 205
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 3.99,
|
| 259 |
-
"learning_rate": 0.001,
|
| 260 |
-
"loss": 3.6627,
|
| 261 |
-
"step": 210
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 4.08,
|
| 265 |
-
"learning_rate": 0.001,
|
| 266 |
-
"loss": 3.5937,
|
| 267 |
-
"step": 215
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 4.17,
|
| 271 |
-
"learning_rate": 0.001,
|
| 272 |
-
"loss": 3.6135,
|
| 273 |
-
"step": 220
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 4.27,
|
| 277 |
-
"learning_rate": 0.001,
|
| 278 |
-
"loss": 3.6352,
|
| 279 |
-
"step": 225
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 4.36,
|
| 283 |
-
"learning_rate": 0.001,
|
| 284 |
-
"loss": 3.6514,
|
| 285 |
-
"step": 230
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 4.46,
|
| 289 |
-
"learning_rate": 0.001,
|
| 290 |
-
"loss": 3.6351,
|
| 291 |
-
"step": 235
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 4.55,
|
| 295 |
-
"learning_rate": 0.001,
|
| 296 |
-
"loss": 3.6453,
|
| 297 |
-
"step": 240
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 4.65,
|
| 301 |
-
"learning_rate": 0.001,
|
| 302 |
-
"loss": 3.6458,
|
| 303 |
-
"step": 245
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 4.74,
|
| 307 |
-
"learning_rate": 0.001,
|
| 308 |
-
"loss": 3.6196,
|
| 309 |
-
"step": 250
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 4.84,
|
| 313 |
-
"learning_rate": 0.001,
|
| 314 |
-
"loss": 3.6168,
|
| 315 |
-
"step": 255
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 4.93,
|
| 319 |
-
"learning_rate": 0.001,
|
| 320 |
-
"loss": 3.6403,
|
| 321 |
-
"step": 260
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 4.93,
|
| 325 |
-
"step": 260,
|
| 326 |
-
"total_flos": 1.527316217856e+16,
|
| 327 |
-
"train_loss": 3.7126791367164027,
|
| 328 |
-
"train_runtime": 6928.357,
|
| 329 |
-
"train_samples_per_second": 4.868,
|
| 330 |
-
"train_steps_per_second": 0.038
|
| 331 |
}
|
| 332 |
],
|
| 333 |
"logging_steps": 5,
|
| 334 |
-
"max_steps":
|
| 335 |
"num_train_epochs": 5,
|
| 336 |
"save_steps": 1000,
|
| 337 |
-
"total_flos":
|
| 338 |
"trial_name": null,
|
| 339 |
"trial_params": null
|
| 340 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.935064935064935,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 190,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.13,
|
| 13 |
+
"learning_rate": 1e-05,
|
| 14 |
+
"loss": 2.0916,
|
| 15 |
"step": 5
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.26,
|
| 19 |
+
"learning_rate": 1e-05,
|
| 20 |
+
"loss": 2.0612,
|
| 21 |
"step": 10
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.39,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"loss": 2.0475,
|
| 27 |
"step": 15
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.52,
|
| 31 |
+
"learning_rate": 1e-05,
|
| 32 |
+
"loss": 2.113,
|
| 33 |
"step": 20
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.65,
|
| 37 |
+
"learning_rate": 1e-05,
|
| 38 |
+
"loss": 2.0671,
|
| 39 |
"step": 25
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.78,
|
| 43 |
+
"learning_rate": 1e-05,
|
| 44 |
+
"loss": 2.0571,
|
| 45 |
"step": 30
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.91,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 2.1778,
|
| 51 |
"step": 35
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 1.04,
|
| 55 |
+
"learning_rate": 1e-05,
|
| 56 |
+
"loss": 1.9966,
|
| 57 |
"step": 40
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 1.17,
|
| 61 |
+
"learning_rate": 1e-05,
|
| 62 |
+
"loss": 2.1532,
|
| 63 |
"step": 45
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 1.3,
|
| 67 |
+
"learning_rate": 1e-05,
|
| 68 |
+
"loss": 2.0544,
|
| 69 |
"step": 50
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 1.43,
|
| 73 |
+
"learning_rate": 1e-05,
|
| 74 |
+
"loss": 2.0557,
|
| 75 |
"step": 55
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 1.56,
|
| 79 |
+
"learning_rate": 1e-05,
|
| 80 |
+
"loss": 1.9958,
|
| 81 |
"step": 60
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 1.69,
|
| 85 |
+
"learning_rate": 1e-05,
|
| 86 |
+
"loss": 2.0753,
|
| 87 |
"step": 65
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 1.82,
|
| 91 |
+
"learning_rate": 1e-05,
|
| 92 |
+
"loss": 2.0377,
|
| 93 |
"step": 70
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 1.95,
|
| 97 |
+
"learning_rate": 1e-05,
|
| 98 |
+
"loss": 2.0342,
|
| 99 |
"step": 75
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 2.08,
|
| 103 |
+
"learning_rate": 1e-05,
|
| 104 |
+
"loss": 2.0771,
|
| 105 |
"step": 80
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 2.21,
|
| 109 |
+
"learning_rate": 1e-05,
|
| 110 |
+
"loss": 2.0425,
|
| 111 |
"step": 85
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 2.34,
|
| 115 |
+
"learning_rate": 1e-05,
|
| 116 |
+
"loss": 2.0426,
|
| 117 |
"step": 90
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 2.47,
|
| 121 |
+
"learning_rate": 1e-05,
|
| 122 |
+
"loss": 2.0426,
|
| 123 |
"step": 95
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 2.6,
|
| 127 |
+
"learning_rate": 1e-05,
|
| 128 |
+
"loss": 2.0512,
|
| 129 |
"step": 100
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 2.73,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 2.0731,
|
| 135 |
"step": 105
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 2.86,
|
| 139 |
+
"learning_rate": 1e-05,
|
| 140 |
+
"loss": 2.0021,
|
| 141 |
"step": 110
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 2.99,
|
| 145 |
+
"learning_rate": 1e-05,
|
| 146 |
+
"loss": 2.01,
|
| 147 |
"step": 115
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 3.12,
|
| 151 |
+
"learning_rate": 1e-05,
|
| 152 |
+
"loss": 2.0817,
|
| 153 |
"step": 120
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 3.25,
|
| 157 |
+
"learning_rate": 1e-05,
|
| 158 |
+
"loss": 1.9851,
|
| 159 |
"step": 125
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 3.38,
|
| 163 |
+
"learning_rate": 1e-05,
|
| 164 |
+
"loss": 2.0813,
|
| 165 |
"step": 130
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 3.51,
|
| 169 |
+
"learning_rate": 1e-05,
|
| 170 |
+
"loss": 1.9777,
|
| 171 |
"step": 135
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 3.64,
|
| 175 |
+
"learning_rate": 1e-05,
|
| 176 |
+
"loss": 2.0708,
|
| 177 |
"step": 140
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 3.77,
|
| 181 |
+
"learning_rate": 1e-05,
|
| 182 |
+
"loss": 1.9515,
|
| 183 |
"step": 145
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 3.9,
|
| 187 |
+
"learning_rate": 1e-05,
|
| 188 |
+
"loss": 2.0794,
|
| 189 |
"step": 150
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 4.03,
|
| 193 |
+
"learning_rate": 1e-05,
|
| 194 |
+
"loss": 1.9146,
|
| 195 |
"step": 155
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 4.16,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 2.0522,
|
| 201 |
"step": 160
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 4.29,
|
| 205 |
+
"learning_rate": 1e-05,
|
| 206 |
+
"loss": 1.9599,
|
| 207 |
"step": 165
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 4.42,
|
| 211 |
+
"learning_rate": 1e-05,
|
| 212 |
+
"loss": 1.9645,
|
| 213 |
"step": 170
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 4.55,
|
| 217 |
+
"learning_rate": 1e-05,
|
| 218 |
+
"loss": 1.9873,
|
| 219 |
"step": 175
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 4.68,
|
| 223 |
+
"learning_rate": 1e-05,
|
| 224 |
+
"loss": 2.0311,
|
| 225 |
"step": 180
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 4.81,
|
| 229 |
+
"learning_rate": 1e-05,
|
| 230 |
+
"loss": 2.0541,
|
| 231 |
"step": 185
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 4.94,
|
| 235 |
+
"learning_rate": 1e-05,
|
| 236 |
+
"loss": 2.0583,
|
| 237 |
"step": 190
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 4.94,
|
| 241 |
+
"step": 190,
|
| 242 |
+
"total_flos": 697572311040000.0,
|
| 243 |
+
"train_loss": 2.042334004452354,
|
| 244 |
+
"train_runtime": 318.1284,
|
| 245 |
+
"train_samples_per_second": 4.841,
|
| 246 |
+
"train_steps_per_second": 0.597
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
}
|
| 248 |
],
|
| 249 |
"logging_steps": 5,
|
| 250 |
+
"max_steps": 190,
|
| 251 |
"num_train_epochs": 5,
|
| 252 |
"save_steps": 1000,
|
| 253 |
+
"total_flos": 697572311040000.0,
|
| 254 |
"trial_name": null,
|
| 255 |
"trial_params": null
|
| 256 |
}
|
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 sha256:14c4ad59d2bec1733b3950f3135d8f641dadbdde098573f9f64da556199a2758
|
| 3 |
size 4027
|