Training in progress, step 3600, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14996b62fe27415b02721ba65ec488d1b4487436581638be026ed7f27eb3daad
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8d475c2a1103de721f29e2dfad702ea53081e64c48e067eaecd6138bce09f2d
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfe63e551ea8e601e6b37db6f5c29b9e1b4d893ef2a031f35638bcd71863bbde
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -497,13 +497,27 @@
|
|
497 |
"eval_samples_per_second": 30.442,
|
498 |
"eval_steps_per_second": 3.809,
|
499 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 100,
|
503 |
"max_steps": 4116,
|
504 |
"num_train_epochs": 3,
|
505 |
"save_steps": 100,
|
506 |
-
"total_flos": 1.
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.0079221725463867,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3600",
|
4 |
+
"epoch": 2.6229508196721314,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
497 |
"eval_samples_per_second": 30.442,
|
498 |
"eval_steps_per_second": 3.809,
|
499 |
"step": 3500
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.62,
|
503 |
+
"learning_rate": 0.0002,
|
504 |
+
"loss": 1.9797,
|
505 |
+
"step": 3600
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 2.62,
|
509 |
+
"eval_loss": 2.0079221725463867,
|
510 |
+
"eval_runtime": 205.9217,
|
511 |
+
"eval_samples_per_second": 30.468,
|
512 |
+
"eval_steps_per_second": 3.812,
|
513 |
+
"step": 3600
|
514 |
}
|
515 |
],
|
516 |
"logging_steps": 100,
|
517 |
"max_steps": 4116,
|
518 |
"num_train_epochs": 3,
|
519 |
"save_steps": 100,
|
520 |
+
"total_flos": 1.057199681212416e+17,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
523 |
}
|