Training in progress, step 6920, 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:d5e5613b164ad3897b5891476c645d23542f68645e0643a66d815a5027ccda09
|
| 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 sha256:3743ec8036dd838338308e9e6de0954135b19503b186c2615bd3e5b47a685b96
|
| 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 sha256:5aa013e89fa35024ec0ce59dc15f7b6e2a2d747d868537e44c6201b1cb99fa76
|
| 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": 53.
|
| 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,
|
|
@@ -12446,6 +12446,24 @@
|
|
| 12446 |
"mean_token_accuracy": 0.6529275476932526,
|
| 12447 |
"num_tokens": 25200618.0,
|
| 12448 |
"step": 6910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12449 |
}
|
| 12450 |
],
|
| 12451 |
"logging_steps": 5,
|
|
@@ -12465,7 +12483,7 @@
|
|
| 12465 |
"attributes": {}
|
| 12466 |
}
|
| 12467 |
},
|
| 12468 |
-
"total_flos": 1.
|
| 12469 |
"train_batch_size": 4,
|
| 12470 |
"trial_name": null,
|
| 12471 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12446 |
"mean_token_accuracy": 0.6529275476932526,
|
| 12447 |
"num_tokens": 25200618.0,
|
| 12448 |
"step": 6910
|
| 12449 |
+
},
|
| 12450 |
+
{
|
| 12451 |
+
"epoch": 53.19230769230769,
|
| 12452 |
+
"grad_norm": 0.0,
|
| 12453 |
+
"learning_rate": 1.543e-05,
|
| 12454 |
+
"loss": 1.8069,
|
| 12455 |
+
"mean_token_accuracy": 0.6347218960523605,
|
| 12456 |
+
"num_tokens": 25218034.0,
|
| 12457 |
+
"step": 6915
|
| 12458 |
+
},
|
| 12459 |
+
{
|
| 12460 |
+
"epoch": 53.23076923076923,
|
| 12461 |
+
"grad_norm": 0.0,
|
| 12462 |
+
"learning_rate": 1.5405e-05,
|
| 12463 |
+
"loss": 1.7021,
|
| 12464 |
+
"mean_token_accuracy": 0.6613812148571014,
|
| 12465 |
+
"num_tokens": 25236653.0,
|
| 12466 |
+
"step": 6920
|
| 12467 |
}
|
| 12468 |
],
|
| 12469 |
"logging_steps": 5,
|
|
|
|
| 12483 |
"attributes": {}
|
| 12484 |
}
|
| 12485 |
},
|
| 12486 |
+
"total_flos": 1.27961971670827e+18,
|
| 12487 |
"train_batch_size": 4,
|
| 12488 |
"trial_name": null,
|
| 12489 |
"trial_params": null
|