Training in progress, step 6880, 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 sha256:85ab0d30512f507c0b1a948e17bdd3a2cb3e2b0fc684024905a5a060db4bb947
|
| 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 sha256:0352bec5fb605c2cefb076281ea38f30494123c97163511d393051395ff775ed
|
| 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 sha256:4a79611ac8b070324c2314b1dcc594604e4df82a998d73b8b318fec7a0fcbc0f
|
| 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": 52.
|
| 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,
|
|
@@ -12374,6 +12374,24 @@
|
|
| 12374 |
"mean_token_accuracy": 0.6501509785652161,
|
| 12375 |
"num_tokens": 25055025.0,
|
| 12376 |
"step": 6870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12377 |
}
|
| 12378 |
],
|
| 12379 |
"logging_steps": 5,
|
|
@@ -12393,7 +12411,7 @@
|
|
| 12393 |
"attributes": {}
|
| 12394 |
}
|
| 12395 |
},
|
| 12396 |
-
"total_flos": 1.
|
| 12397 |
"train_batch_size": 4,
|
| 12398 |
"trial_name": null,
|
| 12399 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12374 |
"mean_token_accuracy": 0.6501509785652161,
|
| 12375 |
"num_tokens": 25055025.0,
|
| 12376 |
"step": 6870
|
| 12377 |
+
},
|
| 12378 |
+
{
|
| 12379 |
+
"epoch": 52.88461538461539,
|
| 12380 |
+
"grad_norm": 0.0,
|
| 12381 |
+
"learning_rate": 1.563e-05,
|
| 12382 |
+
"loss": 1.739,
|
| 12383 |
+
"mean_token_accuracy": 0.6465972781181335,
|
| 12384 |
+
"num_tokens": 25073502.0,
|
| 12385 |
+
"step": 6875
|
| 12386 |
+
},
|
| 12387 |
+
{
|
| 12388 |
+
"epoch": 52.92307692307692,
|
| 12389 |
+
"grad_norm": 0.0,
|
| 12390 |
+
"learning_rate": 1.5605e-05,
|
| 12391 |
+
"loss": 1.7514,
|
| 12392 |
+
"mean_token_accuracy": 0.6448877215385437,
|
| 12393 |
+
"num_tokens": 25092178.0,
|
| 12394 |
+
"step": 6880
|
| 12395 |
}
|
| 12396 |
],
|
| 12397 |
"logging_steps": 5,
|
|
|
|
| 12411 |
"attributes": {}
|
| 12412 |
}
|
| 12413 |
},
|
| 12414 |
+
"total_flos": 1.2722017137750835e+18,
|
| 12415 |
"train_batch_size": 4,
|
| 12416 |
"trial_name": null,
|
| 12417 |
"trial_params": null
|