Training in progress, step 3700, 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 31466288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c169cce3b0f663a5f2b6c371f0316c0fb74184c18fe5a0d0b282b3e997c0cba2
|
3 |
size 31466288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62950917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2985119935791e3e3e13ae825f74c7ee00883f099270dfdb09c0ea788ac950c0
|
3 |
size 62950917
|
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:ba9a87a902271a6450035455dc1f4df77fd809173f0ab0e7e6c52c6771e76140
|
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:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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,
|
@@ -511,13 +511,27 @@
|
|
511 |
"eval_samples_per_second": 11.294,
|
512 |
"eval_steps_per_second": 1.413,
|
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": 9.
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
523 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1857892274856567,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3700",
|
4 |
+
"epoch": 2.6958105646630237,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
511 |
"eval_samples_per_second": 11.294,
|
512 |
"eval_steps_per_second": 1.413,
|
513 |
"step": 3600
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.7,
|
517 |
+
"learning_rate": 0.0002,
|
518 |
+
"loss": 1.1142,
|
519 |
+
"step": 3700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 2.7,
|
523 |
+
"eval_loss": 1.1857892274856567,
|
524 |
+
"eval_runtime": 556.0273,
|
525 |
+
"eval_samples_per_second": 11.284,
|
526 |
+
"eval_steps_per_second": 1.412,
|
527 |
+
"step": 3700
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 100,
|
531 |
"max_steps": 4116,
|
532 |
"num_train_epochs": 3,
|
533 |
"save_steps": 100,
|
534 |
+
"total_flos": 9.631053618584617e+17,
|
535 |
"trial_name": null,
|
536 |
"trial_params": null
|
537 |
}
|