Training in progress, step 60, 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 59827904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:442056b193506f0923e55d71f13786ca5d305aa6e80eaa9aa5ed6a15eae7cbcb
|
3 |
size 59827904
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30875540
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:131e213365f2f3e5edfa0c531365ccd80dff05a2edb9ad491742153431792436
|
3 |
size 30875540
|
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 sha256:7dfa3332294a25a14a5137921fc31f24176a29def678e629a1769ffeb46f154b
|
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 sha256:78248a64468e8e03af894427063f3f9a858b670b67d13949fb12f06211d294f4
|
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": 0.
|
5 |
"eval_steps": 34,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -408,6 +408,41 @@
|
|
408 |
"learning_rate": 0.00018951632913550626,
|
409 |
"loss": 7.9659,
|
410 |
"step": 55
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
411 |
}
|
412 |
],
|
413 |
"logging_steps": 1,
|
@@ -427,7 +462,7 @@
|
|
427 |
"attributes": {}
|
428 |
}
|
429 |
},
|
430 |
-
"total_flos": 1.
|
431 |
"train_batch_size": 3,
|
432 |
"trial_name": null,
|
433 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.029341646799926645,
|
5 |
"eval_steps": 34,
|
6 |
+
"global_step": 60,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
408 |
"learning_rate": 0.00018951632913550626,
|
409 |
"loss": 7.9659,
|
410 |
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.02738553701326487,
|
414 |
+
"grad_norm": Infinity,
|
415 |
+
"learning_rate": 0.0001886773685920062,
|
416 |
+
"loss": 8.8214,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.027874564459930314,
|
421 |
+
"grad_norm": Infinity,
|
422 |
+
"learning_rate": 0.0001878081248083698,
|
423 |
+
"loss": 8.2246,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.028363591906595757,
|
428 |
+
"grad_norm": Infinity,
|
429 |
+
"learning_rate": 0.00018690889463055283,
|
430 |
+
"loss": 9.1047,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.0288526193532612,
|
435 |
+
"grad_norm": Infinity,
|
436 |
+
"learning_rate": 0.00018597998514483725,
|
437 |
+
"loss": 7.35,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.029341646799926645,
|
442 |
+
"grad_norm": Infinity,
|
443 |
+
"learning_rate": 0.00018502171357296144,
|
444 |
+
"loss": 9.0214,
|
445 |
+
"step": 60
|
446 |
}
|
447 |
],
|
448 |
"logging_steps": 1,
|
|
|
462 |
"attributes": {}
|
463 |
}
|
464 |
},
|
465 |
+
"total_flos": 1.3226878055743488e+17,
|
466 |
"train_batch_size": 3,
|
467 |
"trial_name": null,
|
468 |
"trial_params": null
|