Training in progress, step 6470, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b731083b57ab23a49d25a50bce75b4c67e764484049c90d5a91db4c9fcc6ef3
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f0cbd25d6ecf495ff1f622a40d2c51675073654864e7121c8f959126a8c55b
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2272ac3bb9a7fa7c136e4c57afe654388bed0aafde0c967d7fe62cb6f833cdd
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 49.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -11636,6 +11636,24 @@
|
|
| 11636 |
"mean_token_accuracy": 0.6557675808668136,
|
| 11637 |
"num_tokens": 23559830.0,
|
| 11638 |
"step": 6460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11639 |
}
|
| 11640 |
],
|
| 11641 |
"logging_steps": 5,
|
|
@@ -11655,7 +11673,7 @@
|
|
| 11655 |
"attributes": {}
|
| 11656 |
}
|
| 11657 |
},
|
| 11658 |
-
"total_flos": 1.
|
| 11659 |
"train_batch_size": 4,
|
| 11660 |
"trial_name": null,
|
| 11661 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11636 |
"mean_token_accuracy": 0.6557675808668136,
|
| 11637 |
"num_tokens": 23559830.0,
|
| 11638 |
"step": 6460
|
| 11639 |
+
},
|
| 11640 |
+
{
|
| 11641 |
+
"epoch": 49.73076923076923,
|
| 11642 |
+
"grad_norm": 0.0,
|
| 11643 |
+
"learning_rate": 1.7680000000000004e-05,
|
| 11644 |
+
"loss": 1.7611,
|
| 11645 |
+
"mean_token_accuracy": 0.6487846702337265,
|
| 11646 |
+
"num_tokens": 23578070.0,
|
| 11647 |
+
"step": 6465
|
| 11648 |
+
},
|
| 11649 |
+
{
|
| 11650 |
+
"epoch": 49.76923076923077,
|
| 11651 |
+
"grad_norm": 0.0,
|
| 11652 |
+
"learning_rate": 1.7655000000000003e-05,
|
| 11653 |
+
"loss": 1.7967,
|
| 11654 |
+
"mean_token_accuracy": 0.639831280708313,
|
| 11655 |
+
"num_tokens": 23596069.0,
|
| 11656 |
+
"step": 6470
|
| 11657 |
}
|
| 11658 |
],
|
| 11659 |
"logging_steps": 5,
|
|
|
|
| 11673 |
"attributes": {}
|
| 11674 |
}
|
| 11675 |
},
|
| 11676 |
+
"total_flos": 1.1961539653459968e+18,
|
| 11677 |
"train_batch_size": 4,
|
| 11678 |
"trial_name": null,
|
| 11679 |
"trial_params": null
|