Training in progress, step 1930, 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 sha256:0378f611e8a065b7ee1ea1ad54f54197056aeafe00b1fd190c29a6720d29649a
|
| 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 sha256:76a3579b4498d7f7beffb3aef2f09038449e3b1feb7d72ae97773bb4b60bf6ff
|
| 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 sha256:204e0c5340216a4c64df160eb09d77b70d0c1cdc73dd8d721c2c1e06a5297e4d
|
| 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,
|
|
@@ -3464,6 +3464,24 @@
|
|
| 3464 |
"mean_token_accuracy": 0.6336044192314148,
|
| 3465 |
"num_tokens": 7001378.0,
|
| 3466 |
"step": 1920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3467 |
}
|
| 3468 |
],
|
| 3469 |
"logging_steps": 5,
|
|
@@ -3483,7 +3501,7 @@
|
|
| 3483 |
"attributes": {}
|
| 3484 |
}
|
| 3485 |
},
|
| 3486 |
-
"total_flos": 3.
|
| 3487 |
"train_batch_size": 4,
|
| 3488 |
"trial_name": null,
|
| 3489 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3464 |
"mean_token_accuracy": 0.6336044192314148,
|
| 3465 |
"num_tokens": 7001378.0,
|
| 3466 |
"step": 1920
|
| 3467 |
+
},
|
| 3468 |
+
{
|
| 3469 |
+
"epoch": 14.807692307692308,
|
| 3470 |
+
"grad_norm": 0.0,
|
| 3471 |
+
"learning_rate": 4.038e-05,
|
| 3472 |
+
"loss": 1.7307,
|
| 3473 |
+
"mean_token_accuracy": 0.6568962961435318,
|
| 3474 |
+
"num_tokens": 7019494.0,
|
| 3475 |
+
"step": 1925
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 14.846153846153847,
|
| 3479 |
+
"grad_norm": 0.0,
|
| 3480 |
+
"learning_rate": 4.0355e-05,
|
| 3481 |
+
"loss": 1.7421,
|
| 3482 |
+
"mean_token_accuracy": 0.6525963991880417,
|
| 3483 |
+
"num_tokens": 7037790.0,
|
| 3484 |
+
"step": 1930
|
| 3485 |
}
|
| 3486 |
],
|
| 3487 |
"logging_steps": 5,
|
|
|
|
| 3501 |
"attributes": {}
|
| 3502 |
}
|
| 3503 |
},
|
| 3504 |
+
"total_flos": 3.566346342653952e+17,
|
| 3505 |
"train_batch_size": 4,
|
| 3506 |
"trial_name": null,
|
| 3507 |
"trial_params": null
|