Training in progress, step 1920, 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 sha256:02d89a8901623e0d0f26afe4849c5a27c492aba8d75071517f96290f12408c26
|
| 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 sha256:70d05fdcc194b27ded6effd377984509c0e86601a3d4fc4f41deec2992af4f73
|
| 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:c743e71e5374fa23d4a0e1f601c2cec53d3e32da98b3b83bab1f965eca9af7c1
|
| 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": 14.
|
| 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,
|
|
@@ -3446,6 +3446,24 @@
|
|
| 3446 |
"mean_token_accuracy": 0.6516493141651154,
|
| 3447 |
"num_tokens": 6966319.0,
|
| 3448 |
"step": 1910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3449 |
}
|
| 3450 |
],
|
| 3451 |
"logging_steps": 5,
|
|
@@ -3465,7 +3483,7 @@
|
|
| 3465 |
"attributes": {}
|
| 3466 |
}
|
| 3467 |
},
|
| 3468 |
-
"total_flos": 3.
|
| 3469 |
"train_batch_size": 4,
|
| 3470 |
"trial_name": null,
|
| 3471 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3446 |
"mean_token_accuracy": 0.6516493141651154,
|
| 3447 |
"num_tokens": 6966319.0,
|
| 3448 |
"step": 1910
|
| 3449 |
+
},
|
| 3450 |
+
{
|
| 3451 |
+
"epoch": 14.73076923076923,
|
| 3452 |
+
"grad_norm": 0.0,
|
| 3453 |
+
"learning_rate": 4.0430000000000004e-05,
|
| 3454 |
+
"loss": 1.7763,
|
| 3455 |
+
"mean_token_accuracy": 0.6418019294738769,
|
| 3456 |
+
"num_tokens": 6984403.0,
|
| 3457 |
+
"step": 1915
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 14.76923076923077,
|
| 3461 |
+
"grad_norm": 0.0,
|
| 3462 |
+
"learning_rate": 4.0405000000000004e-05,
|
| 3463 |
+
"loss": 1.8325,
|
| 3464 |
+
"mean_token_accuracy": 0.6336044192314148,
|
| 3465 |
+
"num_tokens": 7001378.0,
|
| 3466 |
+
"step": 1920
|
| 3467 |
}
|
| 3468 |
],
|
| 3469 |
"logging_steps": 5,
|
|
|
|
| 3483 |
"attributes": {}
|
| 3484 |
}
|
| 3485 |
},
|
| 3486 |
+
"total_flos": 3.5482359932338176e+17,
|
| 3487 |
"train_batch_size": 4,
|
| 3488 |
"trial_name": null,
|
| 3489 |
"trial_params": null
|