Training in progress, step 1980, 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:ee9f032c650ebbc766a1466b46f6afc0824f97d775eebca0781ee985c7eb116b
|
| 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 sha256:92e44a21764abef3946e69a8a79167be3055a5488635c644ea3da39b0a86d47e
|
| 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 sha256:309e9721b58294c4b76d0f34970b4c25c0f750ed7701749ee426117164b7054f
|
| 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": 15.
|
| 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,
|
|
@@ -3554,6 +3554,24 @@
|
|
| 3554 |
"mean_token_accuracy": 0.6483392864465714,
|
| 3555 |
"num_tokens": 7183723.0,
|
| 3556 |
"step": 1970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3557 |
}
|
| 3558 |
],
|
| 3559 |
"logging_steps": 5,
|
|
@@ -3573,7 +3591,7 @@
|
|
| 3573 |
"attributes": {}
|
| 3574 |
}
|
| 3575 |
},
|
| 3576 |
-
"total_flos": 3.
|
| 3577 |
"train_batch_size": 4,
|
| 3578 |
"trial_name": null,
|
| 3579 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3554 |
"mean_token_accuracy": 0.6483392864465714,
|
| 3555 |
"num_tokens": 7183723.0,
|
| 3556 |
"step": 1970
|
| 3557 |
+
},
|
| 3558 |
+
{
|
| 3559 |
+
"epoch": 15.192307692307692,
|
| 3560 |
+
"grad_norm": 0.0,
|
| 3561 |
+
"learning_rate": 4.0130000000000004e-05,
|
| 3562 |
+
"loss": 1.7712,
|
| 3563 |
+
"mean_token_accuracy": 0.6451886177062989,
|
| 3564 |
+
"num_tokens": 7200954.0,
|
| 3565 |
+
"step": 1975
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 15.23076923076923,
|
| 3569 |
+
"grad_norm": 0.0,
|
| 3570 |
+
"learning_rate": 4.0105e-05,
|
| 3571 |
+
"loss": 1.7852,
|
| 3572 |
+
"mean_token_accuracy": 0.6437583029270172,
|
| 3573 |
+
"num_tokens": 7218897.0,
|
| 3574 |
+
"step": 1980
|
| 3575 |
}
|
| 3576 |
],
|
| 3577 |
"logging_steps": 5,
|
|
|
|
| 3591 |
"attributes": {}
|
| 3592 |
}
|
| 3593 |
},
|
| 3594 |
+
"total_flos": 3.6568885630058496e+17,
|
| 3595 |
"train_batch_size": 4,
|
| 3596 |
"trial_name": null,
|
| 3597 |
"trial_params": null
|