Training in progress, step 8610, 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:c9810e253de8c0d2e9a41f4a99ac66ba93281c9e1ff3eb23f5ab0927bd8ffee5
|
| 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 sha256:9e1c6f6beca181b14bcdf67bc94b62e98e00280fb592280fdfe7521b6b8a941a
|
| 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 sha256:4163a06d9d90bae999e261d434ee41eae8a5e3bcb8e47cb69c5694877f62cdff
|
| 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": 66.
|
| 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,
|
|
@@ -15488,6 +15488,24 @@
|
|
| 15488 |
"mean_token_accuracy": 0.6564001739025116,
|
| 15489 |
"num_tokens": 31364569.0,
|
| 15490 |
"step": 8600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15491 |
}
|
| 15492 |
],
|
| 15493 |
"logging_steps": 5,
|
|
@@ -15507,7 +15525,7 @@
|
|
| 15507 |
"attributes": {}
|
| 15508 |
}
|
| 15509 |
},
|
| 15510 |
-
"total_flos": 1.
|
| 15511 |
"train_batch_size": 4,
|
| 15512 |
"trial_name": null,
|
| 15513 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15488 |
"mean_token_accuracy": 0.6564001739025116,
|
| 15489 |
"num_tokens": 31364569.0,
|
| 15490 |
"step": 8600
|
| 15491 |
+
},
|
| 15492 |
+
{
|
| 15493 |
+
"epoch": 66.1923076923077,
|
| 15494 |
+
"grad_norm": 0.0,
|
| 15495 |
+
"learning_rate": 6.98e-06,
|
| 15496 |
+
"loss": 1.7538,
|
| 15497 |
+
"mean_token_accuracy": 0.6477825731039047,
|
| 15498 |
+
"num_tokens": 31382670.0,
|
| 15499 |
+
"step": 8605
|
| 15500 |
+
},
|
| 15501 |
+
{
|
| 15502 |
+
"epoch": 66.23076923076923,
|
| 15503 |
+
"grad_norm": 0.0,
|
| 15504 |
+
"learning_rate": 6.955e-06,
|
| 15505 |
+
"loss": 1.7799,
|
| 15506 |
+
"mean_token_accuracy": 0.6439489036798477,
|
| 15507 |
+
"num_tokens": 31400493.0,
|
| 15508 |
+
"step": 8610
|
| 15509 |
}
|
| 15510 |
],
|
| 15511 |
"logging_steps": 5,
|
|
|
|
| 15525 |
"attributes": {}
|
| 15526 |
}
|
| 15527 |
},
|
| 15528 |
+
"total_flos": 1.592150585080873e+18,
|
| 15529 |
"train_batch_size": 4,
|
| 15530 |
"trial_name": null,
|
| 15531 |
"trial_params": null
|