Training in progress, step 27500, 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:b64bf1ebf51d694fdeb9bca1a73e68a759d5f8f5c94a4f4197023b270a5f74b6
|
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 sha256:219fc53d62837117473847c70028456e7d7441f74f337dc27b72ae302eb20251
|
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 sha256:8c52f344ac7ec92d77a075d151f1a470c012f516bcc11d7f83acfeb94aba37af
|
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 sha256:7a9597bf6b4c68d872ba3fdb9fcdf4f05ecc611643dfedee62c13aced510caee
|
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,
|
@@ -371,13 +371,19 @@
|
|
371 |
"learning_rate": 0.00017160834868017188,
|
372 |
"loss": 0.4495,
|
373 |
"step": 27000
|
|
|
|
|
|
|
|
|
|
|
|
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 500,
|
377 |
"max_steps": 32580,
|
378 |
"num_train_epochs": 5,
|
379 |
"save_steps": 500,
|
380 |
-
"total_flos": 1.
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.220380601596071,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 27500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
371 |
"learning_rate": 0.00017160834868017188,
|
372 |
"loss": 0.4495,
|
373 |
"step": 27000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.22,
|
377 |
+
"learning_rate": 0.00015626151012891346,
|
378 |
+
"loss": 0.454,
|
379 |
+
"step": 27500
|
380 |
}
|
381 |
],
|
382 |
"logging_steps": 500,
|
383 |
"max_steps": 32580,
|
384 |
"num_train_epochs": 5,
|
385 |
"save_steps": 500,
|
386 |
+
"total_flos": 1.4580021229780992e+16,
|
387 |
"trial_name": null,
|
388 |
"trial_params": null
|
389 |
}
|