Training in progress, step 1460, 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 sha256:9621a30446b95a32ceb61484acaf93026ceebf8a48e1ea1623410fe611fb4f08
|
| 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 sha256:3c0f7a66f38eb995a6c9564631e88316a5f75bd50f316b8e2c130e4af8b5257f
|
| 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:c4edcbbcaed5861b740ce4d7f5745385da32e12ff49d19663ae2334672d72039
|
| 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": 11.
|
| 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,
|
|
@@ -2618,6 +2618,24 @@
|
|
| 2618 |
"mean_token_accuracy": 0.6530660510063171,
|
| 2619 |
"num_tokens": 5287928.0,
|
| 2620 |
"step": 1450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2621 |
}
|
| 2622 |
],
|
| 2623 |
"logging_steps": 5,
|
|
@@ -2637,7 +2655,7 @@
|
|
| 2637 |
"attributes": {}
|
| 2638 |
}
|
| 2639 |
},
|
| 2640 |
-
"total_flos": 2.
|
| 2641 |
"train_batch_size": 4,
|
| 2642 |
"trial_name": null,
|
| 2643 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2618 |
"mean_token_accuracy": 0.6530660510063171,
|
| 2619 |
"num_tokens": 5287928.0,
|
| 2620 |
"step": 1450
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 11.192307692307692,
|
| 2624 |
+
"grad_norm": 0.0,
|
| 2625 |
+
"learning_rate": 4.2730000000000006e-05,
|
| 2626 |
+
"loss": 1.7704,
|
| 2627 |
+
"mean_token_accuracy": 0.6498903334140778,
|
| 2628 |
+
"num_tokens": 5305899.0,
|
| 2629 |
+
"step": 1455
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 11.23076923076923,
|
| 2633 |
+
"grad_norm": 0.0,
|
| 2634 |
+
"learning_rate": 4.2705e-05,
|
| 2635 |
+
"loss": 1.8094,
|
| 2636 |
+
"mean_token_accuracy": 0.6360325515270233,
|
| 2637 |
+
"num_tokens": 5323814.0,
|
| 2638 |
+
"step": 1460
|
| 2639 |
}
|
| 2640 |
],
|
| 2641 |
"logging_steps": 5,
|
|
|
|
| 2655 |
"attributes": {}
|
| 2656 |
}
|
| 2657 |
},
|
| 2658 |
+
"total_flos": 2.6977815423516672e+17,
|
| 2659 |
"train_batch_size": 4,
|
| 2660 |
"trial_name": null,
|
| 2661 |
"trial_params": null
|