Training in progress, step 30500, 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 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e852541a3bdbda667af57bef25a244802ab71d7466fd75c8fec114df0482d63
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d8f57321300cc95ce6d5fd628d35150e6814e99d016b62436452364c8995f99
|
3 |
size 484163514
|
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:abd55818fbfe606bc7bd34cc9d3685ded1f5c0adb9be12f4f14b7db75e0c5b19
|
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 sha256:2588958225089ef1df8e05d17c23ac3bf7ed001b161eece9c26f7d299960396b
|
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": 4.
|
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,
|
@@ -407,13 +407,19 @@
|
|
407 |
"learning_rate": 7.955801104972376e-05,
|
408 |
"loss": 0.4533,
|
409 |
"step": 30000
|
|
|
|
|
|
|
|
|
|
|
|
|
410 |
}
|
411 |
],
|
412 |
"logging_steps": 500,
|
413 |
"max_steps": 32580,
|
414 |
"num_train_epochs": 5,
|
415 |
"save_steps": 500,
|
416 |
-
"total_flos": 1.
|
417 |
"trial_name": null,
|
418 |
"trial_params": null
|
419 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.680785758133824,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 30500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
407 |
"learning_rate": 7.955801104972376e-05,
|
408 |
"loss": 0.4533,
|
409 |
"step": 30000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 4.68,
|
413 |
+
"learning_rate": 6.424186617556783e-05,
|
414 |
+
"loss": 0.4495,
|
415 |
+
"step": 30500
|
416 |
}
|
417 |
],
|
418 |
"logging_steps": 500,
|
419 |
"max_steps": 32580,
|
420 |
"num_train_epochs": 5,
|
421 |
"save_steps": 500,
|
422 |
+
"total_flos": 1.6171742321442816e+16,
|
423 |
"trial_name": null,
|
424 |
"trial_params": null
|
425 |
}
|