bhuvanmdev
commited on
Training in progress, step 900, 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 sha256:1df5141e8ddeb3a52fde5e36fc601b5e98a35a760b21dad4d770c16f1eab93ed
|
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 sha256:93ead4589f80294e6843eb8b95d2991b1dc0bd7f68680239a89942448b55a764
|
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:c4e6c6b149a116cec483f2a17b2bb809f7cc6274383aca9dd5c6e24801ded5e5
|
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:d71dd396b34c87932ecfea63e93418697d0d152f826f8e27acd4064174d59bd1
|
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,
|
@@ -711,14 +711,30 @@
|
|
711 |
"loss": 0.4139,
|
712 |
"num_input_tokens_seen": 587384,
|
713 |
"step": 880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
714 |
}
|
715 |
],
|
716 |
"logging_steps": 10,
|
717 |
"max_steps": 2795,
|
718 |
-
"num_input_tokens_seen":
|
719 |
"num_train_epochs": 1,
|
720 |
"save_steps": 20,
|
721 |
-
"total_flos": 1.
|
722 |
"train_batch_size": 1,
|
723 |
"trial_name": null,
|
724 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3220035778175313,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
711 |
"loss": 0.4139,
|
712 |
"num_input_tokens_seen": 587384,
|
713 |
"step": 880
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.3184257602862254,
|
717 |
+
"grad_norm": 0.30183765292167664,
|
718 |
+
"learning_rate": 0.00013631484794275492,
|
719 |
+
"loss": 0.4412,
|
720 |
+
"num_input_tokens_seen": 594626,
|
721 |
+
"step": 890
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.3220035778175313,
|
725 |
+
"grad_norm": 0.24405309557914734,
|
726 |
+
"learning_rate": 0.00013559928443649375,
|
727 |
+
"loss": 0.4217,
|
728 |
+
"num_input_tokens_seen": 601425,
|
729 |
+
"step": 900
|
730 |
}
|
731 |
],
|
732 |
"logging_steps": 10,
|
733 |
"max_steps": 2795,
|
734 |
+
"num_input_tokens_seen": 601425,
|
735 |
"num_train_epochs": 1,
|
736 |
"save_steps": 20,
|
737 |
+
"total_flos": 1.35239243825664e+16,
|
738 |
"train_batch_size": 1,
|
739 |
"trial_name": null,
|
740 |
"trial_params": null
|