Training in progress, step 820, 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 100697728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8266c5ce2daff311c6b7f99a82121a7d104c99faa78c3777323bc8fb69e449a
|
3 |
size 100697728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201541754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba87eaf9f2c58fb6d0b0a1c2263a7833cdee74039a7d283d9e26e781413fe8ff
|
3 |
size 201541754
|
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:f7526970e790becb006619bd780f0a177e541ca6e1e03e8171224f11d2b3cdea
|
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 sha256:38f6fcd2abad4866e3102113773264731c828e1e13009602886e42cd304ea258
|
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": 0.
|
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,
|
@@ -647,14 +647,30 @@
|
|
647 |
"loss": 0.4144,
|
648 |
"num_input_tokens_seen": 535308,
|
649 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
650 |
}
|
651 |
],
|
652 |
"logging_steps": 10,
|
653 |
"max_steps": 2795,
|
654 |
-
"num_input_tokens_seen":
|
655 |
"num_train_epochs": 1,
|
656 |
"save_steps": 20,
|
657 |
-
"total_flos": 1.
|
658 |
"train_batch_size": 1,
|
659 |
"trial_name": null,
|
660 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.29338103756708406,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 820,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
647 |
"loss": 0.4144,
|
648 |
"num_input_tokens_seen": 535308,
|
649 |
"step": 800
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.2898032200357782,
|
653 |
+
"grad_norm": 0.24462071061134338,
|
654 |
+
"learning_rate": 0.00014203935599284436,
|
655 |
+
"loss": 0.3984,
|
656 |
+
"num_input_tokens_seen": 542297,
|
657 |
+
"step": 810
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.29338103756708406,
|
661 |
+
"grad_norm": 0.4308456480503082,
|
662 |
+
"learning_rate": 0.0001413237924865832,
|
663 |
+
"loss": 0.4142,
|
664 |
+
"num_input_tokens_seen": 548183,
|
665 |
+
"step": 820
|
666 |
}
|
667 |
],
|
668 |
"logging_steps": 10,
|
669 |
"max_steps": 2795,
|
670 |
+
"num_input_tokens_seen": 548183,
|
671 |
"num_train_epochs": 1,
|
672 |
"save_steps": 20,
|
673 |
+
"total_flos": 1.2326699820939264e+16,
|
674 |
"train_batch_size": 1,
|
675 |
"trial_name": null,
|
676 |
"trial_params": null
|