Training in progress, step 2530, 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 sha256:3a45812992ca79ee68cf26d796bc9914bf947a540dd89e6eff3590dec8296ce7
|
| 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 sha256:6b3105c9f214d9007567a4c864ea76465b4db88833f11fb3502c131abcba1d5e
|
| 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 sha256:3fd88eabc57d472333fdb623e21bb6d7ad7ef0ea158a1e1605e1fd0470468827
|
| 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": 19.
|
| 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,
|
|
@@ -4544,6 +4544,24 @@
|
|
| 4544 |
"mean_token_accuracy": 0.647335684299469,
|
| 4545 |
"num_tokens": 9190090.0,
|
| 4546 |
"step": 2520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4547 |
}
|
| 4548 |
],
|
| 4549 |
"logging_steps": 5,
|
|
@@ -4563,7 +4581,7 @@
|
|
| 4563 |
"attributes": {}
|
| 4564 |
}
|
| 4565 |
},
|
| 4566 |
-
"total_flos": 4.
|
| 4567 |
"train_batch_size": 4,
|
| 4568 |
"trial_name": null,
|
| 4569 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4544 |
"mean_token_accuracy": 0.647335684299469,
|
| 4545 |
"num_tokens": 9190090.0,
|
| 4546 |
"step": 2520
|
| 4547 |
+
},
|
| 4548 |
+
{
|
| 4549 |
+
"epoch": 19.423076923076923,
|
| 4550 |
+
"grad_norm": 0.0,
|
| 4551 |
+
"learning_rate": 3.7380000000000005e-05,
|
| 4552 |
+
"loss": 1.824,
|
| 4553 |
+
"mean_token_accuracy": 0.6351722240447998,
|
| 4554 |
+
"num_tokens": 9207627.0,
|
| 4555 |
+
"step": 2525
|
| 4556 |
+
},
|
| 4557 |
+
{
|
| 4558 |
+
"epoch": 19.46153846153846,
|
| 4559 |
+
"grad_norm": 0.0,
|
| 4560 |
+
"learning_rate": 3.7355000000000004e-05,
|
| 4561 |
+
"loss": 1.8204,
|
| 4562 |
+
"mean_token_accuracy": 0.6388478010892868,
|
| 4563 |
+
"num_tokens": 9224815.0,
|
| 4564 |
+
"step": 2530
|
| 4565 |
}
|
| 4566 |
],
|
| 4567 |
"logging_steps": 5,
|
|
|
|
| 4581 |
"attributes": {}
|
| 4582 |
}
|
| 4583 |
},
|
| 4584 |
+
"total_flos": 4.6742183087947776e+17,
|
| 4585 |
"train_batch_size": 4,
|
| 4586 |
"trial_name": null,
|
| 4587 |
"trial_params": null
|