youdiniplays
commited on
Training in progress, step 32000, 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 sha256:57d7a601ee782b9d27bdd0272b36437c0d8e38c7b0f9e01039668e5400b27f8b
|
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 sha256:22bd62f7708b73fefc3e10fefa40f4aad0442834e9084bc05d9f75adfe6f9dbd
|
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 sha256:85ead622339363f87905b93332d83623341915786e174b111c4607f7fbab63e7
|
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 sha256:2e2baebdf44f798afbd3a09a301f0c46c787657a8c030735544e47d813021276
|
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,
|
@@ -425,13 +425,19 @@
|
|
425 |
"learning_rate": 3.3548189073050956e-05,
|
426 |
"loss": 0.4563,
|
427 |
"step": 31500
|
|
|
|
|
|
|
|
|
|
|
|
|
428 |
}
|
429 |
],
|
430 |
"logging_steps": 500,
|
431 |
"max_steps": 32580,
|
432 |
"num_train_epochs": 5,
|
433 |
"save_steps": 500,
|
434 |
-
"total_flos": 1.
|
435 |
"trial_name": null,
|
436 |
"trial_params": null
|
437 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.910988336402701,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 32000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
425 |
"learning_rate": 3.3548189073050956e-05,
|
426 |
"loss": 0.4563,
|
427 |
"step": 31500
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 4.91,
|
431 |
+
"learning_rate": 1.820135052179251e-05,
|
432 |
+
"loss": 0.4563,
|
433 |
+
"step": 32000
|
434 |
}
|
435 |
],
|
436 |
"logging_steps": 500,
|
437 |
"max_steps": 32580,
|
438 |
"num_train_epochs": 5,
|
439 |
"save_steps": 500,
|
440 |
+
"total_flos": 1.6969603388276736e+16,
|
441 |
"trial_name": null,
|
442 |
"trial_params": null
|
443 |
}
|