Commit
•
b86bb5f
1
Parent(s):
c15189c
Training in progress, step 3900, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49f9868e4d1cd21d90596284b88521aacdf829dc439af2b6b38673ec9ca76abf
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d638a7e1318513481edad79747bbd9d85854414852c1a384c0c1190d66d2abd
|
3 |
size 100693001
|
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 sha256:44f7a23b7a631b1fe28c32f80339cec68c940273b7a37ff68a8e64f1b9f09a97
|
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 sha256:794a0a668693664bb45fb10418080981a1873b71841f3a55ed72c5aa6d455597
|
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,
|
@@ -539,13 +539,27 @@
|
|
539 |
"eval_samples_per_second": 43.689,
|
540 |
"eval_steps_per_second": 5.466,
|
541 |
"step": 3800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
542 |
}
|
543 |
],
|
544 |
"logging_steps": 100,
|
545 |
"max_steps": 4116,
|
546 |
"num_train_epochs": 3,
|
547 |
"save_steps": 100,
|
548 |
-
"total_flos": 2.
|
549 |
"trial_name": null,
|
550 |
"trial_params": null
|
551 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3290683031082153,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3900",
|
4 |
+
"epoch": 2.841530054644809,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
539 |
"eval_samples_per_second": 43.689,
|
540 |
"eval_steps_per_second": 5.466,
|
541 |
"step": 3800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.84,
|
545 |
+
"learning_rate": 0.0002,
|
546 |
+
"loss": 1.3154,
|
547 |
+
"step": 3900
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 2.84,
|
551 |
+
"eval_loss": 1.3290683031082153,
|
552 |
+
"eval_runtime": 143.5227,
|
553 |
+
"eval_samples_per_second": 43.714,
|
554 |
+
"eval_steps_per_second": 5.47,
|
555 |
+
"step": 3900
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 100,
|
559 |
"max_steps": 4116,
|
560 |
"num_train_epochs": 3,
|
561 |
"save_steps": 100,
|
562 |
+
"total_flos": 2.322136123818148e+17,
|
563 |
"trial_name": null,
|
564 |
"trial_params": null
|
565 |
}
|