Training in progress, step 1880, 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:f372a924a68994a472e1cb7878ae2f6f35ce08141ef445af3b3bbaa6cd0c3965
|
| 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:d78580411d4210c6dc1478d2410769f6d09011b13fa8771cd5f0496e8ec0c9eb
|
| 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:aaafb075e0b1ac5157044a7b625fc04aabd046728cbe91e993d827bec270e865
|
| 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,
|
|
@@ -3374,6 +3374,24 @@
|
|
| 3374 |
"mean_token_accuracy": 0.6466529428958893,
|
| 3375 |
"num_tokens": 6821867.0,
|
| 3376 |
"step": 1870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3377 |
}
|
| 3378 |
],
|
| 3379 |
"logging_steps": 5,
|
|
@@ -3393,7 +3411,7 @@
|
|
| 3393 |
"attributes": {}
|
| 3394 |
}
|
| 3395 |
},
|
| 3396 |
-
"total_flos": 3.
|
| 3397 |
"train_batch_size": 4,
|
| 3398 |
"trial_name": null,
|
| 3399 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3374 |
"mean_token_accuracy": 0.6466529428958893,
|
| 3375 |
"num_tokens": 6821867.0,
|
| 3376 |
"step": 1870
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 14.423076923076923,
|
| 3380 |
+
"grad_norm": 0.0,
|
| 3381 |
+
"learning_rate": 4.063e-05,
|
| 3382 |
+
"loss": 1.8023,
|
| 3383 |
+
"mean_token_accuracy": 0.6425188779830933,
|
| 3384 |
+
"num_tokens": 6839252.0,
|
| 3385 |
+
"step": 1875
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 14.461538461538462,
|
| 3389 |
+
"grad_norm": 0.0,
|
| 3390 |
+
"learning_rate": 4.0605e-05,
|
| 3391 |
+
"loss": 1.7618,
|
| 3392 |
+
"mean_token_accuracy": 0.6461942523717881,
|
| 3393 |
+
"num_tokens": 6857208.0,
|
| 3394 |
+
"step": 1880
|
| 3395 |
}
|
| 3396 |
],
|
| 3397 |
"logging_steps": 5,
|
|
|
|
| 3411 |
"attributes": {}
|
| 3412 |
}
|
| 3413 |
},
|
| 3414 |
+
"total_flos": 3.474606927539405e+17,
|
| 3415 |
"train_batch_size": 4,
|
| 3416 |
"trial_name": null,
|
| 3417 |
"trial_params": null
|