Model save
Browse files- README.md +1 -1
- all_results.json +11 -11
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Dec13_17-25-51_f86c45587747/events.out.tfevents.1702489100.f86c45587747.2060.1 +3 -0
- runs/Dec13_17-40-47_f86c45587747/events.out.tfevents.1702489257.f86c45587747.2060.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +491 -173
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 10
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 15.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 2.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8712962962962963,
|
| 4 |
+
"eval_loss": 0.45238634943962097,
|
| 5 |
+
"eval_runtime": 15.5817,
|
| 6 |
+
"eval_samples_per_second": 69.312,
|
| 7 |
+
"eval_steps_per_second": 8.664,
|
| 8 |
+
"total_flos": 1.339145591637934e+18,
|
| 9 |
+
"train_loss": 0.6042599819324634,
|
| 10 |
+
"train_runtime": 412.4773,
|
| 11 |
+
"train_samples_per_second": 41.893,
|
| 12 |
+
"train_steps_per_second": 2.618
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 15.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.8712962962962963,
|
| 4 |
+
"eval_loss": 0.45238634943962097,
|
| 5 |
+
"eval_runtime": 15.5817,
|
| 6 |
+
"eval_samples_per_second": 69.312,
|
| 7 |
+
"eval_steps_per_second": 8.664
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343245508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e9e589da45f267b74543fb3cf71a3e64ae7573f9ffbf643d2128ab848f036b
|
| 3 |
size 343245508
|
runs/Dec13_17-25-51_f86c45587747/events.out.tfevents.1702489100.f86c45587747.2060.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ce540e1558284f9793fdfb4eff509c6495bb11a69321047444e8790d82a4996
|
| 3 |
+
size 411
|
runs/Dec13_17-40-47_f86c45587747/events.out.tfevents.1702489257.f86c45587747.2060.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95f23499f1e81cdfb1efd1a6cc7bd92a67c13ff9980cacd5bbdd4bcc1a14fa17
|
| 3 |
+
size 47230
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.339145591637934e+18,
|
| 4 |
+
"train_loss": 0.6042599819324634,
|
| 5 |
+
"train_runtime": 412.4773,
|
| 6 |
+
"train_samples_per_second": 41.893,
|
| 7 |
+
"train_steps_per_second": 2.618
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,358 +1,676 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 3000,
|
| 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": 0.04,
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.07,
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.11,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.22,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss":
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss":
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 1.
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss":
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss":
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss":
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate": 0.
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss":
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss":
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 1.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 1.
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 1.
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 300
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 1.
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 310
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 1.
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 320
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 1.
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 330
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 1.
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 340
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 1.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 350
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 1.
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 360
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch": 1.
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 370
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 1.
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 380
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch": 1.
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 390
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch": 1.
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 0.
|
| 249 |
"step": 400
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 1.
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 410
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch": 1.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 420
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 1.
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 430
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 1.
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 440
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch": 1.
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 0.
|
| 279 |
"step": 450
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch": 1.
|
| 283 |
-
"learning_rate":
|
| 284 |
-
"loss": 0.
|
| 285 |
"step": 460
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 1.
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 470
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch": 1.
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 480
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 1.
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 490
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 1.
|
| 307 |
-
"learning_rate":
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 500
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch": 1.
|
| 313 |
-
"learning_rate":
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 510
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch": 1.
|
| 319 |
-
"learning_rate":
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 520
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch": 1.
|
| 325 |
-
"learning_rate":
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 530
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch":
|
| 331 |
-
"learning_rate":
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 540
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch":
|
| 337 |
-
"learning_rate":
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 550
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch": 2.
|
| 343 |
-
"
|
| 344 |
-
"
|
| 345 |
-
"
|
| 346 |
-
|
| 347 |
-
|
| 348 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 349 |
}
|
| 350 |
],
|
| 351 |
"logging_steps": 10,
|
| 352 |
-
"max_steps":
|
| 353 |
-
"num_train_epochs":
|
| 354 |
"save_steps": 3000,
|
| 355 |
-
"total_flos":
|
| 356 |
"trial_name": null,
|
| 357 |
"trial_params": null
|
| 358 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
"eval_steps": 3000,
|
| 6 |
+
"global_step": 1080,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 0.00019814814814814814,
|
| 14 |
+
"loss": 2.1983,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 0.0001962962962962963,
|
| 20 |
+
"loss": 2.1208,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 0.00019444444444444446,
|
| 26 |
+
"loss": 1.8985,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 0.0001925925925925926,
|
| 32 |
+
"loss": 1.726,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 0.00019074074074074075,
|
| 38 |
+
"loss": 1.6799,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 0.00018888888888888888,
|
| 44 |
+
"loss": 1.5807,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"learning_rate": 0.00018703703703703704,
|
| 50 |
+
"loss": 1.5165,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"learning_rate": 0.0001851851851851852,
|
| 56 |
+
"loss": 1.4893,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.33,
|
| 61 |
+
"learning_rate": 0.00018333333333333334,
|
| 62 |
+
"loss": 1.24,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.37,
|
| 67 |
+
"learning_rate": 0.0001814814814814815,
|
| 68 |
+
"loss": 1.2977,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.41,
|
| 73 |
+
"learning_rate": 0.00017962962962962963,
|
| 74 |
+
"loss": 1.2492,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.44,
|
| 79 |
+
"learning_rate": 0.00017777777777777779,
|
| 80 |
+
"loss": 1.1566,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.48,
|
| 85 |
+
"learning_rate": 0.00017592592592592595,
|
| 86 |
+
"loss": 1.3443,
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.52,
|
| 91 |
+
"learning_rate": 0.00017407407407407408,
|
| 92 |
+
"loss": 1.2112,
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"learning_rate": 0.00017222222222222224,
|
| 98 |
+
"loss": 1.0302,
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.59,
|
| 103 |
+
"learning_rate": 0.00017037037037037037,
|
| 104 |
+
"loss": 1.1856,
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.63,
|
| 109 |
+
"learning_rate": 0.00016851851851851853,
|
| 110 |
+
"loss": 1.1745,
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.67,
|
| 115 |
+
"learning_rate": 0.0001666666666666667,
|
| 116 |
+
"loss": 1.0659,
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.7,
|
| 121 |
+
"learning_rate": 0.00016481481481481482,
|
| 122 |
+
"loss": 1.0134,
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.74,
|
| 127 |
+
"learning_rate": 0.00016296296296296295,
|
| 128 |
+
"loss": 0.9692,
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.78,
|
| 133 |
+
"learning_rate": 0.0001611111111111111,
|
| 134 |
+
"loss": 0.8877,
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.81,
|
| 139 |
+
"learning_rate": 0.00015925925925925927,
|
| 140 |
+
"loss": 0.8419,
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.85,
|
| 145 |
+
"learning_rate": 0.00015740740740740743,
|
| 146 |
+
"loss": 0.9147,
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.89,
|
| 151 |
+
"learning_rate": 0.00015555555555555556,
|
| 152 |
+
"loss": 1.0111,
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.93,
|
| 157 |
+
"learning_rate": 0.0001537037037037037,
|
| 158 |
+
"loss": 0.9457,
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.96,
|
| 163 |
+
"learning_rate": 0.00015185185185185185,
|
| 164 |
+
"loss": 0.9867,
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"learning_rate": 0.00015000000000000001,
|
| 170 |
+
"loss": 1.1366,
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 1.04,
|
| 175 |
+
"learning_rate": 0.00014814814814814815,
|
| 176 |
+
"loss": 0.7648,
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 1.07,
|
| 181 |
+
"learning_rate": 0.0001462962962962963,
|
| 182 |
+
"loss": 0.8693,
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 1.11,
|
| 187 |
+
"learning_rate": 0.00014444444444444444,
|
| 188 |
+
"loss": 0.8179,
|
| 189 |
"step": 300
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 1.15,
|
| 193 |
+
"learning_rate": 0.0001425925925925926,
|
| 194 |
+
"loss": 0.8077,
|
| 195 |
"step": 310
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.19,
|
| 199 |
+
"learning_rate": 0.00014074074074074076,
|
| 200 |
+
"loss": 0.941,
|
| 201 |
"step": 320
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 1.22,
|
| 205 |
+
"learning_rate": 0.0001388888888888889,
|
| 206 |
+
"loss": 0.8906,
|
| 207 |
"step": 330
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.26,
|
| 211 |
+
"learning_rate": 0.00013703703703703705,
|
| 212 |
+
"loss": 0.8433,
|
| 213 |
"step": 340
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 1.3,
|
| 217 |
+
"learning_rate": 0.00013518518518518518,
|
| 218 |
+
"loss": 0.7654,
|
| 219 |
"step": 350
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.33,
|
| 223 |
+
"learning_rate": 0.00013333333333333334,
|
| 224 |
+
"loss": 0.7217,
|
| 225 |
"step": 360
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 1.37,
|
| 229 |
+
"learning_rate": 0.0001314814814814815,
|
| 230 |
+
"loss": 0.8744,
|
| 231 |
"step": 370
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 1.41,
|
| 235 |
+
"learning_rate": 0.00012962962962962963,
|
| 236 |
+
"loss": 0.6337,
|
| 237 |
"step": 380
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 1.44,
|
| 241 |
+
"learning_rate": 0.00012777777777777776,
|
| 242 |
+
"loss": 0.6369,
|
| 243 |
"step": 390
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 1.48,
|
| 247 |
+
"learning_rate": 0.00012592592592592592,
|
| 248 |
+
"loss": 0.5268,
|
| 249 |
"step": 400
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 1.52,
|
| 253 |
+
"learning_rate": 0.00012407407407407408,
|
| 254 |
+
"loss": 0.8015,
|
| 255 |
"step": 410
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 1.56,
|
| 259 |
+
"learning_rate": 0.00012222222222222224,
|
| 260 |
+
"loss": 0.5013,
|
| 261 |
"step": 420
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 1.59,
|
| 265 |
+
"learning_rate": 0.00012037037037037037,
|
| 266 |
+
"loss": 0.6063,
|
| 267 |
"step": 430
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 1.63,
|
| 271 |
+
"learning_rate": 0.00011851851851851852,
|
| 272 |
+
"loss": 0.7767,
|
| 273 |
"step": 440
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 1.67,
|
| 277 |
+
"learning_rate": 0.00011666666666666668,
|
| 278 |
+
"loss": 0.5174,
|
| 279 |
"step": 450
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 1.7,
|
| 283 |
+
"learning_rate": 0.00011481481481481482,
|
| 284 |
+
"loss": 0.6391,
|
| 285 |
"step": 460
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 1.74,
|
| 289 |
+
"learning_rate": 0.00011296296296296296,
|
| 290 |
+
"loss": 0.4966,
|
| 291 |
"step": 470
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 1.78,
|
| 295 |
+
"learning_rate": 0.00011111111111111112,
|
| 296 |
+
"loss": 0.5991,
|
| 297 |
"step": 480
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 1.81,
|
| 301 |
+
"learning_rate": 0.00010925925925925926,
|
| 302 |
+
"loss": 0.5499,
|
| 303 |
"step": 490
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 1.85,
|
| 307 |
+
"learning_rate": 0.00010740740740740742,
|
| 308 |
+
"loss": 0.5488,
|
| 309 |
"step": 500
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 1.89,
|
| 313 |
+
"learning_rate": 0.00010555555555555557,
|
| 314 |
+
"loss": 0.5834,
|
| 315 |
"step": 510
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 1.93,
|
| 319 |
+
"learning_rate": 0.0001037037037037037,
|
| 320 |
+
"loss": 0.6238,
|
| 321 |
"step": 520
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 1.96,
|
| 325 |
+
"learning_rate": 0.00010185185185185186,
|
| 326 |
+
"loss": 0.6365,
|
| 327 |
"step": 530
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 2.0,
|
| 331 |
+
"learning_rate": 0.0001,
|
| 332 |
+
"loss": 0.5337,
|
| 333 |
"step": 540
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 2.04,
|
| 337 |
+
"learning_rate": 9.814814814814815e-05,
|
| 338 |
+
"loss": 0.4326,
|
| 339 |
"step": 550
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 2.07,
|
| 343 |
+
"learning_rate": 9.62962962962963e-05,
|
| 344 |
+
"loss": 0.4197,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.11,
|
| 349 |
+
"learning_rate": 9.444444444444444e-05,
|
| 350 |
+
"loss": 0.3268,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.15,
|
| 355 |
+
"learning_rate": 9.25925925925926e-05,
|
| 356 |
+
"loss": 0.3066,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.19,
|
| 361 |
+
"learning_rate": 9.074074074074075e-05,
|
| 362 |
+
"loss": 0.4737,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.22,
|
| 367 |
+
"learning_rate": 8.888888888888889e-05,
|
| 368 |
+
"loss": 0.3185,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.26,
|
| 373 |
+
"learning_rate": 8.703703703703704e-05,
|
| 374 |
+
"loss": 0.4233,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.3,
|
| 379 |
+
"learning_rate": 8.518518518518518e-05,
|
| 380 |
+
"loss": 0.3377,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.33,
|
| 385 |
+
"learning_rate": 8.333333333333334e-05,
|
| 386 |
+
"loss": 0.3957,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.37,
|
| 391 |
+
"learning_rate": 8.148148148148148e-05,
|
| 392 |
+
"loss": 0.3915,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.41,
|
| 397 |
+
"learning_rate": 7.962962962962964e-05,
|
| 398 |
+
"loss": 0.3025,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.44,
|
| 403 |
+
"learning_rate": 7.777777777777778e-05,
|
| 404 |
+
"loss": 0.2896,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.48,
|
| 409 |
+
"learning_rate": 7.592592592592593e-05,
|
| 410 |
+
"loss": 0.2558,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.52,
|
| 415 |
+
"learning_rate": 7.407407407407407e-05,
|
| 416 |
+
"loss": 0.3477,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.56,
|
| 421 |
+
"learning_rate": 7.222222222222222e-05,
|
| 422 |
+
"loss": 0.2111,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.59,
|
| 427 |
+
"learning_rate": 7.037037037037038e-05,
|
| 428 |
+
"loss": 0.2885,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.63,
|
| 433 |
+
"learning_rate": 6.851851851851852e-05,
|
| 434 |
+
"loss": 0.2953,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.67,
|
| 439 |
+
"learning_rate": 6.666666666666667e-05,
|
| 440 |
+
"loss": 0.2415,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.7,
|
| 445 |
+
"learning_rate": 6.481481481481482e-05,
|
| 446 |
+
"loss": 0.3242,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.74,
|
| 451 |
+
"learning_rate": 6.296296296296296e-05,
|
| 452 |
+
"loss": 0.2616,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.78,
|
| 457 |
+
"learning_rate": 6.111111111111112e-05,
|
| 458 |
+
"loss": 0.2853,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.81,
|
| 463 |
+
"learning_rate": 5.925925925925926e-05,
|
| 464 |
+
"loss": 0.2828,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.85,
|
| 469 |
+
"learning_rate": 5.740740740740741e-05,
|
| 470 |
+
"loss": 0.2382,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.89,
|
| 475 |
+
"learning_rate": 5.555555555555556e-05,
|
| 476 |
+
"loss": 0.3508,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.93,
|
| 481 |
+
"learning_rate": 5.370370370370371e-05,
|
| 482 |
+
"loss": 0.2794,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.96,
|
| 487 |
+
"learning_rate": 5.185185185185185e-05,
|
| 488 |
+
"loss": 0.3247,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.0,
|
| 493 |
+
"learning_rate": 5e-05,
|
| 494 |
+
"loss": 0.2753,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.04,
|
| 499 |
+
"learning_rate": 4.814814814814815e-05,
|
| 500 |
+
"loss": 0.1453,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.07,
|
| 505 |
+
"learning_rate": 4.62962962962963e-05,
|
| 506 |
+
"loss": 0.1666,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.11,
|
| 511 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 512 |
+
"loss": 0.1369,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.15,
|
| 517 |
+
"learning_rate": 4.259259259259259e-05,
|
| 518 |
+
"loss": 0.1086,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.19,
|
| 523 |
+
"learning_rate": 4.074074074074074e-05,
|
| 524 |
+
"loss": 0.0967,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.22,
|
| 529 |
+
"learning_rate": 3.888888888888889e-05,
|
| 530 |
+
"loss": 0.1327,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.26,
|
| 535 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 536 |
+
"loss": 0.0848,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.3,
|
| 541 |
+
"learning_rate": 3.518518518518519e-05,
|
| 542 |
+
"loss": 0.1173,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.33,
|
| 547 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 548 |
+
"loss": 0.135,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.37,
|
| 553 |
+
"learning_rate": 3.148148148148148e-05,
|
| 554 |
+
"loss": 0.1979,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.41,
|
| 559 |
+
"learning_rate": 2.962962962962963e-05,
|
| 560 |
+
"loss": 0.1181,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.44,
|
| 565 |
+
"learning_rate": 2.777777777777778e-05,
|
| 566 |
+
"loss": 0.0957,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.48,
|
| 571 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 572 |
+
"loss": 0.0927,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.52,
|
| 577 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 578 |
+
"loss": 0.094,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.56,
|
| 583 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 584 |
+
"loss": 0.1197,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.59,
|
| 589 |
+
"learning_rate": 2.037037037037037e-05,
|
| 590 |
+
"loss": 0.0927,
|
| 591 |
+
"step": 970
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.63,
|
| 595 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 596 |
+
"loss": 0.1523,
|
| 597 |
+
"step": 980
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.67,
|
| 601 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 602 |
+
"loss": 0.2582,
|
| 603 |
+
"step": 990
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.7,
|
| 607 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 608 |
+
"loss": 0.1101,
|
| 609 |
+
"step": 1000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.74,
|
| 613 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 614 |
+
"loss": 0.1582,
|
| 615 |
+
"step": 1010
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.78,
|
| 619 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 620 |
+
"loss": 0.0504,
|
| 621 |
+
"step": 1020
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 3.81,
|
| 625 |
+
"learning_rate": 9.259259259259259e-06,
|
| 626 |
+
"loss": 0.0788,
|
| 627 |
+
"step": 1030
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 3.85,
|
| 631 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 632 |
+
"loss": 0.0607,
|
| 633 |
+
"step": 1040
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.89,
|
| 637 |
+
"learning_rate": 5.555555555555556e-06,
|
| 638 |
+
"loss": 0.1061,
|
| 639 |
+
"step": 1050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.93,
|
| 643 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 644 |
+
"loss": 0.0645,
|
| 645 |
+
"step": 1060
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.96,
|
| 649 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 650 |
+
"loss": 0.0971,
|
| 651 |
+
"step": 1070
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 4.0,
|
| 655 |
+
"learning_rate": 0.0,
|
| 656 |
+
"loss": 0.128,
|
| 657 |
+
"step": 1080
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 4.0,
|
| 661 |
+
"step": 1080,
|
| 662 |
+
"total_flos": 1.339145591637934e+18,
|
| 663 |
+
"train_loss": 0.6042599819324634,
|
| 664 |
+
"train_runtime": 412.4773,
|
| 665 |
+
"train_samples_per_second": 41.893,
|
| 666 |
+
"train_steps_per_second": 2.618
|
| 667 |
}
|
| 668 |
],
|
| 669 |
"logging_steps": 10,
|
| 670 |
+
"max_steps": 1080,
|
| 671 |
+
"num_train_epochs": 4,
|
| 672 |
"save_steps": 3000,
|
| 673 |
+
"total_flos": 1.339145591637934e+18,
|
| 674 |
"trial_name": null,
|
| 675 |
"trial_params": null
|
| 676 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce8c248f033e489c055bf6bb31f2e28906b79dad7e44578cd117fc71cea6f0e4
|
| 3 |
size 4536
|