Training in progress, step 450, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 527048968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e24748dd822f756ed4242c60fb3d818c5f3f1403f7cb0cb26a0606a7d914d965
|
| 3 |
size 527048968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1054135994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdfefe9eb25e71faaeda047c0bbb4cb850579c1403c64a030c9a88643911c666
|
| 3 |
size 1054135994
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f76c4c2dca19bfb0a463693a0e409b44510488650d816e566bccd2a2851e9524
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -152,6 +152,296 @@
|
|
| 152 |
"EMA_steps_per_second": 23.56,
|
| 153 |
"epoch": 6.521739130434782,
|
| 154 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 155 |
}
|
| 156 |
],
|
| 157 |
"logging_steps": 10,
|
|
@@ -171,7 +461,7 @@
|
|
| 171 |
"attributes": {}
|
| 172 |
}
|
| 173 |
},
|
| 174 |
-
"total_flos":
|
| 175 |
"train_batch_size": 4,
|
| 176 |
"trial_name": null,
|
| 177 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7163676619529724,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-450",
|
| 4 |
+
"epoch": 19.565217391304348,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 450,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 152 |
"EMA_steps_per_second": 23.56,
|
| 153 |
"epoch": 6.521739130434782,
|
| 154 |
"step": 150
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.956521739130435,
|
| 158 |
+
"grad_norm": 1.5398858785629272,
|
| 159 |
+
"learning_rate": 2.9999892980750297e-05,
|
| 160 |
+
"loss": 0.6588,
|
| 161 |
+
"step": 160
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.391304347826087,
|
| 165 |
+
"grad_norm": 1.3466821908950806,
|
| 166 |
+
"learning_rate": 2.9999854334972675e-05,
|
| 167 |
+
"loss": 0.7387,
|
| 168 |
+
"step": 170
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.826086956521739,
|
| 172 |
+
"grad_norm": 1.7265022993087769,
|
| 173 |
+
"learning_rate": 2.999980974373204e-05,
|
| 174 |
+
"loss": 0.7293,
|
| 175 |
+
"step": 180
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 8.26086956521739,
|
| 179 |
+
"grad_norm": 1.5390920639038086,
|
| 180 |
+
"learning_rate": 2.9999759207046075e-05,
|
| 181 |
+
"loss": 0.6246,
|
| 182 |
+
"step": 190
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.695652173913043,
|
| 186 |
+
"grad_norm": 1.741837501525879,
|
| 187 |
+
"learning_rate": 2.9999702724934804e-05,
|
| 188 |
+
"loss": 0.6763,
|
| 189 |
+
"step": 200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 9.130434782608695,
|
| 193 |
+
"grad_norm": 1.0418298244476318,
|
| 194 |
+
"learning_rate": 2.999964029742062e-05,
|
| 195 |
+
"loss": 0.652,
|
| 196 |
+
"step": 210
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 9.565217391304348,
|
| 200 |
+
"grad_norm": 1.2192714214324951,
|
| 201 |
+
"learning_rate": 2.9999571924528263e-05,
|
| 202 |
+
"loss": 0.5594,
|
| 203 |
+
"step": 220
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 10.0,
|
| 207 |
+
"grad_norm": 1.5348883867263794,
|
| 208 |
+
"learning_rate": 2.9999497606284837e-05,
|
| 209 |
+
"loss": 0.7558,
|
| 210 |
+
"step": 230
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 10.434782608695652,
|
| 214 |
+
"grad_norm": 1.4283764362335205,
|
| 215 |
+
"learning_rate": 2.9999417342719796e-05,
|
| 216 |
+
"loss": 0.7116,
|
| 217 |
+
"step": 240
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 10.869565217391305,
|
| 221 |
+
"grad_norm": 0.9756546020507812,
|
| 222 |
+
"learning_rate": 2.9999331133864956e-05,
|
| 223 |
+
"loss": 0.5897,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 11.304347826086957,
|
| 228 |
+
"grad_norm": 1.1936676502227783,
|
| 229 |
+
"learning_rate": 2.9999238979754485e-05,
|
| 230 |
+
"loss": 0.6549,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 11.73913043478261,
|
| 235 |
+
"grad_norm": 1.0490339994430542,
|
| 236 |
+
"learning_rate": 2.999914088042492e-05,
|
| 237 |
+
"loss": 0.6475,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 12.173913043478262,
|
| 242 |
+
"grad_norm": 1.3118759393692017,
|
| 243 |
+
"learning_rate": 2.9999036835915132e-05,
|
| 244 |
+
"loss": 0.5939,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 12.608695652173914,
|
| 249 |
+
"grad_norm": 1.0843631029129028,
|
| 250 |
+
"learning_rate": 2.9998926846266365e-05,
|
| 251 |
+
"loss": 0.6327,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.043478260869565,
|
| 256 |
+
"grad_norm": 1.3878614902496338,
|
| 257 |
+
"learning_rate": 2.9998810911522213e-05,
|
| 258 |
+
"loss": 0.5806,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 13.043478260869565,
|
| 263 |
+
"eval_loss": 0.7306283712387085,
|
| 264 |
+
"eval_runtime": 0.4835,
|
| 265 |
+
"eval_samples_per_second": 20.682,
|
| 266 |
+
"eval_steps_per_second": 20.682,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"Start_State_loss": 0.8603047132492065,
|
| 271 |
+
"Start_State_runtime": 0.4005,
|
| 272 |
+
"Start_State_samples_per_second": 24.967,
|
| 273 |
+
"Start_State_steps_per_second": 24.967,
|
| 274 |
+
"epoch": 13.043478260869565,
|
| 275 |
+
"step": 300
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"Raw_Model_loss": 0.7306283712387085,
|
| 279 |
+
"Raw_Model_runtime": 0.4064,
|
| 280 |
+
"Raw_Model_samples_per_second": 24.606,
|
| 281 |
+
"Raw_Model_steps_per_second": 24.606,
|
| 282 |
+
"epoch": 13.043478260869565,
|
| 283 |
+
"step": 300
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"SWA_loss": 0.7750393152236938,
|
| 287 |
+
"SWA_runtime": 0.3955,
|
| 288 |
+
"SWA_samples_per_second": 25.283,
|
| 289 |
+
"SWA_steps_per_second": 25.283,
|
| 290 |
+
"epoch": 13.043478260869565,
|
| 291 |
+
"step": 300
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"EMA_loss": 0.8608482480049133,
|
| 295 |
+
"EMA_runtime": 0.5237,
|
| 296 |
+
"EMA_samples_per_second": 19.095,
|
| 297 |
+
"EMA_steps_per_second": 19.095,
|
| 298 |
+
"epoch": 13.043478260869565,
|
| 299 |
+
"step": 300
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 13.478260869565217,
|
| 303 |
+
"grad_norm": 1.7818219661712646,
|
| 304 |
+
"learning_rate": 2.9998689031728636e-05,
|
| 305 |
+
"loss": 0.5145,
|
| 306 |
+
"step": 310
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 13.91304347826087,
|
| 310 |
+
"grad_norm": 1.5318005084991455,
|
| 311 |
+
"learning_rate": 2.9998561206933938e-05,
|
| 312 |
+
"loss": 0.6498,
|
| 313 |
+
"step": 320
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 14.347826086956522,
|
| 317 |
+
"grad_norm": 1.4785107374191284,
|
| 318 |
+
"learning_rate": 2.9998427437188786e-05,
|
| 319 |
+
"loss": 0.5741,
|
| 320 |
+
"step": 330
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 14.782608695652174,
|
| 324 |
+
"grad_norm": 1.316670298576355,
|
| 325 |
+
"learning_rate": 2.99982877225462e-05,
|
| 326 |
+
"loss": 0.601,
|
| 327 |
+
"step": 340
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 15.217391304347826,
|
| 331 |
+
"grad_norm": 0.9790920615196228,
|
| 332 |
+
"learning_rate": 2.9998142063061564e-05,
|
| 333 |
+
"loss": 0.4988,
|
| 334 |
+
"step": 350
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 15.652173913043478,
|
| 338 |
+
"grad_norm": 1.6420996189117432,
|
| 339 |
+
"learning_rate": 2.9997990458792603e-05,
|
| 340 |
+
"loss": 0.5628,
|
| 341 |
+
"step": 360
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 16.08695652173913,
|
| 345 |
+
"grad_norm": 1.634116530418396,
|
| 346 |
+
"learning_rate": 2.9997832909799417e-05,
|
| 347 |
+
"loss": 0.6675,
|
| 348 |
+
"step": 370
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 16.52173913043478,
|
| 352 |
+
"grad_norm": 0.9527355432510376,
|
| 353 |
+
"learning_rate": 2.9997669416144452e-05,
|
| 354 |
+
"loss": 0.513,
|
| 355 |
+
"step": 380
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 16.956521739130434,
|
| 359 |
+
"grad_norm": 0.935023307800293,
|
| 360 |
+
"learning_rate": 2.999749997789251e-05,
|
| 361 |
+
"loss": 0.5796,
|
| 362 |
+
"step": 390
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 17.391304347826086,
|
| 366 |
+
"grad_norm": 1.1128907203674316,
|
| 367 |
+
"learning_rate": 2.9997324595110743e-05,
|
| 368 |
+
"loss": 0.518,
|
| 369 |
+
"step": 400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 17.82608695652174,
|
| 373 |
+
"grad_norm": 1.284473180770874,
|
| 374 |
+
"learning_rate": 2.9997143267868683e-05,
|
| 375 |
+
"loss": 0.5879,
|
| 376 |
+
"step": 410
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 18.26086956521739,
|
| 380 |
+
"grad_norm": 1.1633063554763794,
|
| 381 |
+
"learning_rate": 2.9996955996238192e-05,
|
| 382 |
+
"loss": 0.5056,
|
| 383 |
+
"step": 420
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 18.695652173913043,
|
| 387 |
+
"grad_norm": 1.2012042999267578,
|
| 388 |
+
"learning_rate": 2.9996762780293503e-05,
|
| 389 |
+
"loss": 0.5312,
|
| 390 |
+
"step": 430
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 19.130434782608695,
|
| 394 |
+
"grad_norm": 1.21055006980896,
|
| 395 |
+
"learning_rate": 2.9996563620111197e-05,
|
| 396 |
+
"loss": 0.5337,
|
| 397 |
+
"step": 440
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 19.565217391304348,
|
| 401 |
+
"grad_norm": 1.4241245985031128,
|
| 402 |
+
"learning_rate": 2.9996358515770218e-05,
|
| 403 |
+
"loss": 0.5676,
|
| 404 |
+
"step": 450
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 19.565217391304348,
|
| 408 |
+
"eval_loss": 0.7163676619529724,
|
| 409 |
+
"eval_runtime": 0.4066,
|
| 410 |
+
"eval_samples_per_second": 24.595,
|
| 411 |
+
"eval_steps_per_second": 24.595,
|
| 412 |
+
"step": 450
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"Start_State_loss": 0.8603047132492065,
|
| 416 |
+
"Start_State_runtime": 0.3916,
|
| 417 |
+
"Start_State_samples_per_second": 25.534,
|
| 418 |
+
"Start_State_steps_per_second": 25.534,
|
| 419 |
+
"epoch": 19.565217391304348,
|
| 420 |
+
"step": 450
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"Raw_Model_loss": 0.7163676619529724,
|
| 424 |
+
"Raw_Model_runtime": 0.4047,
|
| 425 |
+
"Raw_Model_samples_per_second": 24.71,
|
| 426 |
+
"Raw_Model_steps_per_second": 24.71,
|
| 427 |
+
"epoch": 19.565217391304348,
|
| 428 |
+
"step": 450
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"SWA_loss": 0.7558408975601196,
|
| 432 |
+
"SWA_runtime": 0.3909,
|
| 433 |
+
"SWA_samples_per_second": 25.583,
|
| 434 |
+
"SWA_steps_per_second": 25.583,
|
| 435 |
+
"epoch": 19.565217391304348,
|
| 436 |
+
"step": 450
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"EMA_loss": 0.8608372807502747,
|
| 440 |
+
"EMA_runtime": 0.3933,
|
| 441 |
+
"EMA_samples_per_second": 25.426,
|
| 442 |
+
"EMA_steps_per_second": 25.426,
|
| 443 |
+
"epoch": 19.565217391304348,
|
| 444 |
+
"step": 450
|
| 445 |
}
|
| 446 |
],
|
| 447 |
"logging_steps": 10,
|
|
|
|
| 461 |
"attributes": {}
|
| 462 |
}
|
| 463 |
},
|
| 464 |
+
"total_flos": 1.1591800814075904e+16,
|
| 465 |
"train_batch_size": 4,
|
| 466 |
"trial_name": null,
|
| 467 |
"trial_params": null
|