Training in progress, step 5210, 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 sha256:80dc983820491995a4ca06870b3bdde1c261874938dec1a432e0e7c0a9363554
|
| 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 sha256:10a472de914b944db6f5a375c76209601d2493c1089be7f4690fb167d0cac733
|
| 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 sha256:253f4f97c5f96fed6e49d8359ddc9400c5682ecdbfec38e627671482ce4ef94c
|
| 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": 40.
|
| 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,
|
|
@@ -9368,6 +9368,24 @@
|
|
| 9368 |
"mean_token_accuracy": 0.6535427123308182,
|
| 9369 |
"num_tokens": 18964200.0,
|
| 9370 |
"step": 5200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9371 |
}
|
| 9372 |
],
|
| 9373 |
"logging_steps": 5,
|
|
@@ -9387,7 +9405,7 @@
|
|
| 9387 |
"attributes": {}
|
| 9388 |
}
|
| 9389 |
},
|
| 9390 |
-
"total_flos": 9.
|
| 9391 |
"train_batch_size": 4,
|
| 9392 |
"trial_name": null,
|
| 9393 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9368 |
"mean_token_accuracy": 0.6535427123308182,
|
| 9369 |
"num_tokens": 18964200.0,
|
| 9370 |
"step": 5200
|
| 9371 |
+
},
|
| 9372 |
+
{
|
| 9373 |
+
"epoch": 40.03846153846154,
|
| 9374 |
+
"grad_norm": 0.0,
|
| 9375 |
+
"learning_rate": 2.398e-05,
|
| 9376 |
+
"loss": 1.6565,
|
| 9377 |
+
"mean_token_accuracy": 0.6654837459325791,
|
| 9378 |
+
"num_tokens": 18982763.0,
|
| 9379 |
+
"step": 5205
|
| 9380 |
+
},
|
| 9381 |
+
{
|
| 9382 |
+
"epoch": 40.07692307692308,
|
| 9383 |
+
"grad_norm": 0.0,
|
| 9384 |
+
"learning_rate": 2.3955000000000004e-05,
|
| 9385 |
+
"loss": 1.7472,
|
| 9386 |
+
"mean_token_accuracy": 0.6510910272598267,
|
| 9387 |
+
"num_tokens": 19000451.0,
|
| 9388 |
+
"step": 5210
|
| 9389 |
}
|
| 9390 |
],
|
| 9391 |
"logging_steps": 5,
|
|
|
|
| 9405 |
"attributes": {}
|
| 9406 |
}
|
| 9407 |
},
|
| 9408 |
+
"total_flos": 9.628194358724198e+17,
|
| 9409 |
"train_batch_size": 4,
|
| 9410 |
"trial_name": null,
|
| 9411 |
"trial_params": null
|