Training in progress, step 9730, 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:b077fb7d2485dd0e1b3e6dc40a6f8b2a75a966d0c2186a368ebb04544742ed5e
|
| 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 sha256:986b84436b9baccf26ca905306a12bd64f9b25095c7969df596d3585568c6933
|
| 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:c913a63889c8be0872e44cc0fddd08ebf6198972fa13dd96d91a8f1bf9fd7595
|
| 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": 74.
|
| 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,
|
|
@@ -17504,6 +17504,24 @@
|
|
| 17504 |
"mean_token_accuracy": 0.658492824435234,
|
| 17505 |
"num_tokens": 35448518.0,
|
| 17506 |
"step": 9720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17507 |
}
|
| 17508 |
],
|
| 17509 |
"logging_steps": 5,
|
|
@@ -17523,7 +17541,7 @@
|
|
| 17523 |
"attributes": {}
|
| 17524 |
}
|
| 17525 |
},
|
| 17526 |
-
"total_flos": 1.
|
| 17527 |
"train_batch_size": 4,
|
| 17528 |
"trial_name": null,
|
| 17529 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17504 |
"mean_token_accuracy": 0.658492824435234,
|
| 17505 |
"num_tokens": 35448518.0,
|
| 17506 |
"step": 9720
|
| 17507 |
+
},
|
| 17508 |
+
{
|
| 17509 |
+
"epoch": 74.8076923076923,
|
| 17510 |
+
"grad_norm": 0.0,
|
| 17511 |
+
"learning_rate": 1.3800000000000001e-06,
|
| 17512 |
+
"loss": 1.7531,
|
| 17513 |
+
"mean_token_accuracy": 0.6465422600507736,
|
| 17514 |
+
"num_tokens": 35466311.0,
|
| 17515 |
+
"step": 9725
|
| 17516 |
+
},
|
| 17517 |
+
{
|
| 17518 |
+
"epoch": 74.84615384615384,
|
| 17519 |
+
"grad_norm": 0.0,
|
| 17520 |
+
"learning_rate": 1.355e-06,
|
| 17521 |
+
"loss": 1.7721,
|
| 17522 |
+
"mean_token_accuracy": 0.6479380965232849,
|
| 17523 |
+
"num_tokens": 35484088.0,
|
| 17524 |
+
"step": 9730
|
| 17525 |
}
|
| 17526 |
],
|
| 17527 |
"logging_steps": 5,
|
|
|
|
| 17541 |
"attributes": {}
|
| 17542 |
}
|
| 17543 |
},
|
| 17544 |
+
"total_flos": 1.7994735972591206e+18,
|
| 17545 |
"train_batch_size": 4,
|
| 17546 |
"trial_name": null,
|
| 17547 |
"trial_params": null
|