Training in progress, step 8040, 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 sha256:9096e454372ce75d7277cc6a680910fb941cf5b9393fdcf6b9e51a80ba6e7d36
|
| 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 sha256:27d33796e2ce773f0b6b6cc0b934a755f39afb32c984fd14676b0bfca1fe76cb
|
| 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 sha256:98cd602c9d245e8fbe4a7d576e8f5b82ecb7ea3fd22bbc1503e388105a64157b
|
| 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": 61.
|
| 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,
|
|
@@ -14462,6 +14462,24 @@
|
|
| 14462 |
"mean_token_accuracy": 0.6486380189657212,
|
| 14463 |
"num_tokens": 29284235.0,
|
| 14464 |
"step": 8030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14465 |
}
|
| 14466 |
],
|
| 14467 |
"logging_steps": 5,
|
|
@@ -14481,7 +14499,7 @@
|
|
| 14481 |
"attributes": {}
|
| 14482 |
}
|
| 14483 |
},
|
| 14484 |
-
"total_flos": 1.
|
| 14485 |
"train_batch_size": 4,
|
| 14486 |
"trial_name": null,
|
| 14487 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14462 |
"mean_token_accuracy": 0.6486380189657212,
|
| 14463 |
"num_tokens": 29284235.0,
|
| 14464 |
"step": 8030
|
| 14465 |
+
},
|
| 14466 |
+
{
|
| 14467 |
+
"epoch": 61.80769230769231,
|
| 14468 |
+
"grad_norm": 0.0,
|
| 14469 |
+
"learning_rate": 9.83e-06,
|
| 14470 |
+
"loss": 1.7202,
|
| 14471 |
+
"mean_token_accuracy": 0.6530221402645111,
|
| 14472 |
+
"num_tokens": 29302328.0,
|
| 14473 |
+
"step": 8035
|
| 14474 |
+
},
|
| 14475 |
+
{
|
| 14476 |
+
"epoch": 61.84615384615385,
|
| 14477 |
+
"grad_norm": 0.0,
|
| 14478 |
+
"learning_rate": 9.805e-06,
|
| 14479 |
+
"loss": 1.7455,
|
| 14480 |
+
"mean_token_accuracy": 0.6459253072738648,
|
| 14481 |
+
"num_tokens": 29320675.0,
|
| 14482 |
+
"step": 8040
|
| 14483 |
}
|
| 14484 |
],
|
| 14485 |
"logging_steps": 5,
|
|
|
|
| 14499 |
"attributes": {}
|
| 14500 |
}
|
| 14501 |
},
|
| 14502 |
+
"total_flos": 1.4865865872615014e+18,
|
| 14503 |
"train_batch_size": 4,
|
| 14504 |
"trial_name": null,
|
| 14505 |
"trial_params": null
|