Training in progress, step 8630, 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:d3dc126c902752e59eb4832198c8b2b4085c106cb08e6b9ab5c41545e144fd69
|
| 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 sha256:1aeaef8f39356b156d8fb71efff69a9ed678f81b6f3213fcdd678b7b4a89c165
|
| 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:a4a67a3088f2ee3d2193dfd8ec015086197b93e9a84600d5f8e37b882520ddf7
|
| 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,
|
|
@@ -15524,6 +15524,24 @@
|
|
| 15524 |
"mean_token_accuracy": 0.6766410171985626,
|
| 15525 |
"num_tokens": 31439373.0,
|
| 15526 |
"step": 8620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15527 |
}
|
| 15528 |
],
|
| 15529 |
"logging_steps": 5,
|
|
@@ -15543,7 +15561,7 @@
|
|
| 15543 |
"attributes": {}
|
| 15544 |
}
|
| 15545 |
},
|
| 15546 |
-
"total_flos": 1.
|
| 15547 |
"train_batch_size": 4,
|
| 15548 |
"trial_name": null,
|
| 15549 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15524 |
"mean_token_accuracy": 0.6766410171985626,
|
| 15525 |
"num_tokens": 31439373.0,
|
| 15526 |
"step": 8620
|
| 15527 |
+
},
|
| 15528 |
+
{
|
| 15529 |
+
"epoch": 66.34615384615384,
|
| 15530 |
+
"grad_norm": 0.0,
|
| 15531 |
+
"learning_rate": 6.88e-06,
|
| 15532 |
+
"loss": 1.7701,
|
| 15533 |
+
"mean_token_accuracy": 0.6451247215270997,
|
| 15534 |
+
"num_tokens": 31457394.0,
|
| 15535 |
+
"step": 8625
|
| 15536 |
+
},
|
| 15537 |
+
{
|
| 15538 |
+
"epoch": 66.38461538461539,
|
| 15539 |
+
"grad_norm": 0.0,
|
| 15540 |
+
"learning_rate": 6.8550000000000004e-06,
|
| 15541 |
+
"loss": 1.7894,
|
| 15542 |
+
"mean_token_accuracy": 0.6450399339199067,
|
| 15543 |
+
"num_tokens": 31474686.0,
|
| 15544 |
+
"step": 8630
|
| 15545 |
}
|
| 15546 |
],
|
| 15547 |
"logging_steps": 5,
|
|
|
|
| 15561 |
"attributes": {}
|
| 15562 |
}
|
| 15563 |
},
|
| 15564 |
+
"total_flos": 1.5959962160028058e+18,
|
| 15565 |
"train_batch_size": 4,
|
| 15566 |
"trial_name": null,
|
| 15567 |
"trial_params": null
|