Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2682482800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fba763fb8888ba5c8a603c22a1728782a7a3200087942cf09f75f5a709ad1b61
|
| 3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5365108834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20712b6b92889d488c99c3b3736a8f37dd21d76f182dc9eaa4de963608bf3ad5
|
| 3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7534e5272fdf5e3c7ce49bed1d9a5e0c548594625151bb6b21d90cfb8bba58c
|
| 3 |
size 15006
|
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 sha256:24db8a1f164f634f9cadad0eb9bfc58044056240c42dd1955b51b2b3447077f1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -202,6 +202,111 @@
|
|
| 202 |
"eval_samples_per_second": 41.402,
|
| 203 |
"eval_steps_per_second": 20.701,
|
| 204 |
"step": 650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
}
|
| 206 |
],
|
| 207 |
"logging_steps": 50,
|
|
@@ -221,7 +326,7 @@
|
|
| 221 |
"attributes": {}
|
| 222 |
}
|
| 223 |
},
|
| 224 |
-
"total_flos":
|
| 225 |
"train_batch_size": 2,
|
| 226 |
"trial_name": null,
|
| 227 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9979996362975085,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 1029,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 202 |
"eval_samples_per_second": 41.402,
|
| 203 |
"eval_steps_per_second": 20.701,
|
| 204 |
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.0407346790325516,
|
| 208 |
+
"grad_norm": 96.50550842285156,
|
| 209 |
+
"learning_rate": 8.979591836734695e-05,
|
| 210 |
+
"loss": 1.0918,
|
| 211 |
+
"step": 700
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.0407346790325516,
|
| 215 |
+
"eval_loss": 1.0332311391830444,
|
| 216 |
+
"eval_runtime": 117.5493,
|
| 217 |
+
"eval_samples_per_second": 41.055,
|
| 218 |
+
"eval_steps_per_second": 20.528,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.186215675577378,
|
| 223 |
+
"grad_norm": 83.90518188476562,
|
| 224 |
+
"learning_rate": 8.9067055393586e-05,
|
| 225 |
+
"loss": 1.06,
|
| 226 |
+
"step": 750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.186215675577378,
|
| 230 |
+
"eval_loss": 1.020917534828186,
|
| 231 |
+
"eval_runtime": 116.365,
|
| 232 |
+
"eval_samples_per_second": 41.473,
|
| 233 |
+
"eval_steps_per_second": 20.736,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.331696672122204,
|
| 238 |
+
"grad_norm": 59.09587860107422,
|
| 239 |
+
"learning_rate": 8.833819241982508e-05,
|
| 240 |
+
"loss": 1.0556,
|
| 241 |
+
"step": 800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.331696672122204,
|
| 245 |
+
"eval_loss": 1.0105912685394287,
|
| 246 |
+
"eval_runtime": 116.7111,
|
| 247 |
+
"eval_samples_per_second": 41.35,
|
| 248 |
+
"eval_steps_per_second": 20.675,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.4771776686670304,
|
| 253 |
+
"grad_norm": 41.396785736083984,
|
| 254 |
+
"learning_rate": 8.760932944606415e-05,
|
| 255 |
+
"loss": 1.046,
|
| 256 |
+
"step": 850
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.4771776686670304,
|
| 260 |
+
"eval_loss": 1.002454161643982,
|
| 261 |
+
"eval_runtime": 116.4653,
|
| 262 |
+
"eval_samples_per_second": 41.437,
|
| 263 |
+
"eval_steps_per_second": 20.719,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.6226586652118566,
|
| 268 |
+
"grad_norm": 49.805667877197266,
|
| 269 |
+
"learning_rate": 8.688046647230322e-05,
|
| 270 |
+
"loss": 1.036,
|
| 271 |
+
"step": 900
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.6226586652118566,
|
| 275 |
+
"eval_loss": 0.9919629096984863,
|
| 276 |
+
"eval_runtime": 116.6035,
|
| 277 |
+
"eval_samples_per_second": 41.388,
|
| 278 |
+
"eval_steps_per_second": 20.694,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.768139661756683,
|
| 283 |
+
"grad_norm": 39.228797912597656,
|
| 284 |
+
"learning_rate": 8.615160349854227e-05,
|
| 285 |
+
"loss": 1.0333,
|
| 286 |
+
"step": 950
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.768139661756683,
|
| 290 |
+
"eval_loss": 0.9831019639968872,
|
| 291 |
+
"eval_runtime": 116.7019,
|
| 292 |
+
"eval_samples_per_second": 41.353,
|
| 293 |
+
"eval_steps_per_second": 20.677,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.913620658301509,
|
| 298 |
+
"grad_norm": 85.81388854980469,
|
| 299 |
+
"learning_rate": 8.542274052478134e-05,
|
| 300 |
+
"loss": 1.0256,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.913620658301509,
|
| 305 |
+
"eval_loss": 0.976150631904602,
|
| 306 |
+
"eval_runtime": 116.6678,
|
| 307 |
+
"eval_samples_per_second": 41.365,
|
| 308 |
+
"eval_steps_per_second": 20.683,
|
| 309 |
+
"step": 1000
|
| 310 |
}
|
| 311 |
],
|
| 312 |
"logging_steps": 50,
|
|
|
|
| 326 |
"attributes": {}
|
| 327 |
}
|
| 328 |
},
|
| 329 |
+
"total_flos": 2.6801365303322214e+17,
|
| 330 |
"train_batch_size": 2,
|
| 331 |
"trial_name": null,
|
| 332 |
"trial_params": null
|