stefania-radu
commited on
Commit
•
63bd7a2
1
Parent(s):
c45440c
Training in progress, step 50000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893440890
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b6e0063168d01e8d9ad637627df35c664793162761ded8ac5e14cee0a39fa4b
|
3 |
size 893440890
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
|
3 |
size 454197066
|
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 sha256:832b02611c12b9ad0dcde16a2bc02988c4f2b0b885960cfa4b9125a284bdeb99
|
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 sha256:2cfba27d7b6929b849933e9ae7d0e075a396ddca1f7f2a518e796268cde14302
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -302,11 +302,85 @@
|
|
302 |
"eval_samples_per_second": 111.653,
|
303 |
"eval_steps_per_second": 13.957,
|
304 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
305 |
}
|
306 |
],
|
307 |
"max_steps": 1000000,
|
308 |
"num_train_epochs": 9223372036854775807,
|
309 |
-
"total_flos":
|
310 |
"trial_name": null,
|
311 |
"trial_params": null
|
312 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05,
|
5 |
+
"global_step": 50000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
302 |
"eval_samples_per_second": 111.653,
|
303 |
"eval_steps_per_second": 13.957,
|
304 |
"step": 40000
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.04,
|
308 |
+
"learning_rate": 1.5374999999999998e-05,
|
309 |
+
"loss": 0.5352,
|
310 |
+
"step": 41000
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.04,
|
314 |
+
"learning_rate": 1.5749999999999997e-05,
|
315 |
+
"loss": 0.5329,
|
316 |
+
"step": 42000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.04,
|
320 |
+
"learning_rate": 1.6125e-05,
|
321 |
+
"loss": 0.5304,
|
322 |
+
"step": 43000
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.04,
|
326 |
+
"learning_rate": 1.6499999999999998e-05,
|
327 |
+
"loss": 0.5232,
|
328 |
+
"step": 44000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.04,
|
332 |
+
"learning_rate": 1.6875e-05,
|
333 |
+
"loss": 0.5164,
|
334 |
+
"step": 45000
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.04,
|
338 |
+
"eval_runtime": 3334.4968,
|
339 |
+
"eval_samples_per_second": 101.86,
|
340 |
+
"eval_steps_per_second": 12.733,
|
341 |
+
"step": 45000
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.05,
|
345 |
+
"learning_rate": 1.725e-05,
|
346 |
+
"loss": 0.5133,
|
347 |
+
"step": 46000
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.05,
|
351 |
+
"learning_rate": 1.7624999999999998e-05,
|
352 |
+
"loss": 0.5104,
|
353 |
+
"step": 47000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.05,
|
357 |
+
"learning_rate": 1.7999999999999997e-05,
|
358 |
+
"loss": 0.507,
|
359 |
+
"step": 48000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.05,
|
363 |
+
"learning_rate": 1.8375e-05,
|
364 |
+
"loss": 0.5034,
|
365 |
+
"step": 49000
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.05,
|
369 |
+
"learning_rate": 1.875e-05,
|
370 |
+
"loss": 0.5007,
|
371 |
+
"step": 50000
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.05,
|
375 |
+
"eval_runtime": 3361.5856,
|
376 |
+
"eval_samples_per_second": 101.039,
|
377 |
+
"eval_steps_per_second": 12.63,
|
378 |
+
"step": 50000
|
379 |
}
|
380 |
],
|
381 |
"max_steps": 1000000,
|
382 |
"num_train_epochs": 9223372036854775807,
|
383 |
+
"total_flos": 4.427305086615552e+20,
|
384 |
"trial_name": null,
|
385 |
"trial_params": null
|
386 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bcf9f6920ad5ded398eb8f93116f71e8adc7c3a91f6cd5c0da8e0f651bc8faf
|
3 |
size 454197066
|