End of training
Browse files- README.md +5 -0
- all_results.json +9 -9
- eval_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +391 -13
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: mit
|
|
| 3 |
base_model: microsoft/deberta-v3-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: opus-em-deberta-3-large-v2
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# opus-em-deberta-3-large-v2
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 3 |
base_model: microsoft/deberta-v3-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- f1
|
| 8 |
model-index:
|
| 9 |
- name: opus-em-deberta-3-large-v2
|
| 10 |
results: []
|
|
|
|
| 16 |
# opus-em-deberta-3-large-v2
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 10.0020
|
| 21 |
+
- F1: 0.1942
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_f1": 0.1941564561734213,
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 23.
|
| 6 |
"eval_samples": 1916,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 5743,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
"eval_f1": 0.1941564561734213,
|
| 4 |
+
"eval_loss": 10.002016067504883,
|
| 5 |
+
"eval_runtime": 23.7905,
|
| 6 |
"eval_samples": 1916,
|
| 7 |
+
"eval_samples_per_second": 80.536,
|
| 8 |
+
"eval_steps_per_second": 1.261,
|
| 9 |
+
"train_loss": 0.6437026796394221,
|
| 10 |
+
"train_runtime": 3731.8169,
|
| 11 |
"train_samples": 5743,
|
| 12 |
+
"train_samples_per_second": 15.389,
|
| 13 |
+
"train_steps_per_second": 0.48
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_f1": 0.1941564561734213,
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 23.
|
| 6 |
"eval_samples": 1916,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
"eval_f1": 0.1941564561734213,
|
| 4 |
+
"eval_loss": 10.002016067504883,
|
| 5 |
+
"eval_runtime": 23.7905,
|
| 6 |
"eval_samples": 1916,
|
| 7 |
+
"eval_samples_per_second": 80.536,
|
| 8 |
+
"eval_steps_per_second": 1.261
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 5743,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"train_loss": 0.6437026796394221,
|
| 4 |
+
"train_runtime": 3731.8169,
|
| 5 |
"train_samples": 5743,
|
| 6 |
+
"train_samples_per_second": 15.389,
|
| 7 |
+
"train_steps_per_second": 0.48
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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,
|
|
@@ -161,25 +161,403 @@
|
|
| 161 |
{
|
| 162 |
"epoch": 2.9,
|
| 163 |
"learning_rate": 2e-05,
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 520
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
}
|
| 176 |
],
|
| 177 |
"logging_steps": 20,
|
| 178 |
-
"max_steps":
|
| 179 |
"num_input_tokens_seen": 0,
|
| 180 |
-
"num_train_epochs":
|
| 181 |
"save_steps": 500,
|
| 182 |
-
"total_flos":
|
| 183 |
"train_batch_size": 2,
|
| 184 |
"trial_name": null,
|
| 185 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.977715877437326,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1790,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 161 |
{
|
| 162 |
"epoch": 2.9,
|
| 163 |
"learning_rate": 2e-05,
|
| 164 |
+
"loss": 0.8562,
|
| 165 |
"step": 520
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 3.01,
|
| 169 |
+
"learning_rate": 2e-05,
|
| 170 |
+
"loss": 1.1248,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.13,
|
| 175 |
+
"learning_rate": 2e-05,
|
| 176 |
+
"loss": 0.5689,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.24,
|
| 181 |
+
"learning_rate": 2e-05,
|
| 182 |
+
"loss": 0.7794,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.35,
|
| 187 |
+
"learning_rate": 2e-05,
|
| 188 |
+
"loss": 0.9319,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.46,
|
| 193 |
+
"learning_rate": 2e-05,
|
| 194 |
+
"loss": 1.0026,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.57,
|
| 199 |
+
"learning_rate": 2e-05,
|
| 200 |
+
"loss": 0.5143,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.68,
|
| 205 |
+
"learning_rate": 2e-05,
|
| 206 |
+
"loss": 0.8727,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.79,
|
| 211 |
+
"learning_rate": 2e-05,
|
| 212 |
+
"loss": 0.7792,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.91,
|
| 217 |
+
"learning_rate": 2e-05,
|
| 218 |
+
"loss": 0.7502,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.02,
|
| 223 |
+
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.7851,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.13,
|
| 229 |
+
"learning_rate": 2e-05,
|
| 230 |
+
"loss": 1.3474,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.24,
|
| 235 |
+
"learning_rate": 2e-05,
|
| 236 |
+
"loss": 1.5022,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.35,
|
| 241 |
+
"learning_rate": 2e-05,
|
| 242 |
+
"loss": 0.9111,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.46,
|
| 247 |
+
"learning_rate": 2e-05,
|
| 248 |
+
"loss": 2.2783,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.57,
|
| 253 |
+
"learning_rate": 2e-05,
|
| 254 |
+
"loss": 1.1359,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.69,
|
| 259 |
+
"learning_rate": 2e-05,
|
| 260 |
+
"loss": 1.839,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.8,
|
| 265 |
+
"learning_rate": 2e-05,
|
| 266 |
+
"loss": 0.7254,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.91,
|
| 271 |
+
"learning_rate": 2e-05,
|
| 272 |
+
"loss": 1.331,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.02,
|
| 277 |
+
"learning_rate": 2e-05,
|
| 278 |
+
"loss": 0.6719,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.13,
|
| 283 |
+
"learning_rate": 2e-05,
|
| 284 |
+
"loss": 0.8933,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.24,
|
| 289 |
+
"learning_rate": 2e-05,
|
| 290 |
+
"loss": 0.7205,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 5.35,
|
| 295 |
+
"learning_rate": 2e-05,
|
| 296 |
+
"loss": 0.7708,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.47,
|
| 301 |
+
"learning_rate": 2e-05,
|
| 302 |
+
"loss": 0.8574,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 5.58,
|
| 307 |
+
"learning_rate": 2e-05,
|
| 308 |
+
"loss": 0.7874,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 5.69,
|
| 313 |
+
"learning_rate": 2e-05,
|
| 314 |
+
"loss": 0.7614,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 5.8,
|
| 319 |
+
"learning_rate": 2e-05,
|
| 320 |
+
"loss": 0.788,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.91,
|
| 325 |
+
"learning_rate": 2e-05,
|
| 326 |
+
"loss": 0.5983,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.02,
|
| 331 |
+
"learning_rate": 2e-05,
|
| 332 |
+
"loss": 0.7172,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.13,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 0.7758,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.25,
|
| 343 |
+
"learning_rate": 2e-05,
|
| 344 |
+
"loss": 0.7793,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 6.36,
|
| 349 |
+
"learning_rate": 2e-05,
|
| 350 |
+
"loss": 0.958,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.47,
|
| 355 |
+
"learning_rate": 2e-05,
|
| 356 |
+
"loss": 0.9366,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 6.58,
|
| 361 |
+
"learning_rate": 2e-05,
|
| 362 |
+
"loss": 0.876,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 6.69,
|
| 367 |
+
"learning_rate": 2e-05,
|
| 368 |
+
"loss": 0.9187,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.8,
|
| 373 |
+
"learning_rate": 2e-05,
|
| 374 |
+
"loss": 0.6457,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.91,
|
| 379 |
+
"learning_rate": 2e-05,
|
| 380 |
+
"loss": 0.6107,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.03,
|
| 385 |
+
"learning_rate": 2e-05,
|
| 386 |
+
"loss": 1.2681,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.14,
|
| 391 |
+
"learning_rate": 2e-05,
|
| 392 |
+
"loss": 0.824,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 7.25,
|
| 397 |
+
"learning_rate": 2e-05,
|
| 398 |
+
"loss": 0.7997,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 7.36,
|
| 403 |
+
"learning_rate": 2e-05,
|
| 404 |
+
"loss": 0.6423,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 7.47,
|
| 409 |
+
"learning_rate": 2e-05,
|
| 410 |
+
"loss": 0.7917,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 7.58,
|
| 415 |
+
"learning_rate": 2e-05,
|
| 416 |
+
"loss": 0.6285,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.69,
|
| 421 |
+
"learning_rate": 2e-05,
|
| 422 |
+
"loss": 0.7219,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 7.81,
|
| 427 |
+
"learning_rate": 2e-05,
|
| 428 |
+
"loss": 1.3192,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.92,
|
| 433 |
+
"learning_rate": 2e-05,
|
| 434 |
+
"loss": 0.9599,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 8.03,
|
| 439 |
+
"learning_rate": 2e-05,
|
| 440 |
+
"loss": 1.0558,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.14,
|
| 445 |
+
"learning_rate": 2e-05,
|
| 446 |
+
"loss": 0.829,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 8.25,
|
| 451 |
+
"learning_rate": 2e-05,
|
| 452 |
+
"loss": 0.6611,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 8.36,
|
| 457 |
+
"learning_rate": 2e-05,
|
| 458 |
+
"loss": 0.9619,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 8.47,
|
| 463 |
+
"learning_rate": 2e-05,
|
| 464 |
+
"loss": 0.838,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 8.58,
|
| 469 |
+
"learning_rate": 2e-05,
|
| 470 |
+
"loss": 0.6923,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 8.7,
|
| 475 |
+
"learning_rate": 2e-05,
|
| 476 |
+
"loss": 0.7675,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 8.81,
|
| 481 |
+
"learning_rate": 2e-05,
|
| 482 |
+
"loss": 1.038,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 8.92,
|
| 487 |
+
"learning_rate": 2e-05,
|
| 488 |
+
"loss": 0.5607,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.03,
|
| 493 |
+
"learning_rate": 2e-05,
|
| 494 |
+
"loss": 0.8019,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 9.14,
|
| 499 |
+
"learning_rate": 2e-05,
|
| 500 |
+
"loss": 0.7824,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.25,
|
| 505 |
+
"learning_rate": 2e-05,
|
| 506 |
+
"loss": 0.55,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 9.36,
|
| 511 |
+
"learning_rate": 2e-05,
|
| 512 |
+
"loss": 0.625,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 9.48,
|
| 517 |
+
"learning_rate": 2e-05,
|
| 518 |
+
"loss": 0.8339,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 9.59,
|
| 523 |
+
"learning_rate": 2e-05,
|
| 524 |
+
"loss": 0.5907,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 9.7,
|
| 529 |
+
"learning_rate": 2e-05,
|
| 530 |
+
"loss": 0.9135,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 9.81,
|
| 535 |
+
"learning_rate": 2e-05,
|
| 536 |
+
"loss": 1.3289,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 9.92,
|
| 541 |
+
"learning_rate": 2e-05,
|
| 542 |
+
"loss": 1.1937,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 9.98,
|
| 547 |
+
"step": 1790,
|
| 548 |
+
"total_flos": 4485735925153792.0,
|
| 549 |
+
"train_loss": 0.6437026796394221,
|
| 550 |
+
"train_runtime": 3731.8169,
|
| 551 |
+
"train_samples_per_second": 15.389,
|
| 552 |
+
"train_steps_per_second": 0.48
|
| 553 |
}
|
| 554 |
],
|
| 555 |
"logging_steps": 20,
|
| 556 |
+
"max_steps": 1790,
|
| 557 |
"num_input_tokens_seen": 0,
|
| 558 |
+
"num_train_epochs": 10,
|
| 559 |
"save_steps": 500,
|
| 560 |
+
"total_flos": 4485735925153792.0,
|
| 561 |
"train_batch_size": 2,
|
| 562 |
"trial_name": null,
|
| 563 |
"trial_params": null
|