Training in progress, step 1410, 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:c3b292520ad0aaa0e9a5a545a330be29a2d063ccf8cd3992dc7b7a574e237ada
|
| 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:b61bc9c6ad2afce0d08f8b03a8242c67da06aed20b318d28548a6e3365580ffc
|
| 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 sha256:668af48c560282594cdd03c7321bda6b920e2a2db23b3d10ad39081839362652
|
| 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": 10.
|
| 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,
|
|
@@ -2528,6 +2528,24 @@
|
|
| 2528 |
"mean_token_accuracy": 0.6442721575498581,
|
| 2529 |
"num_tokens": 5107960.0,
|
| 2530 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2531 |
}
|
| 2532 |
],
|
| 2533 |
"logging_steps": 5,
|
|
@@ -2547,7 +2565,7 @@
|
|
| 2547 |
"attributes": {}
|
| 2548 |
}
|
| 2549 |
},
|
| 2550 |
-
"total_flos": 2.
|
| 2551 |
"train_batch_size": 4,
|
| 2552 |
"trial_name": null,
|
| 2553 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2528 |
"mean_token_accuracy": 0.6442721575498581,
|
| 2529 |
"num_tokens": 5107960.0,
|
| 2530 |
"step": 1400
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 10.807692307692308,
|
| 2534 |
+
"grad_norm": 0.0,
|
| 2535 |
+
"learning_rate": 4.2980000000000005e-05,
|
| 2536 |
+
"loss": 1.7286,
|
| 2537 |
+
"mean_token_accuracy": 0.6496645718812942,
|
| 2538 |
+
"num_tokens": 5126317.0,
|
| 2539 |
+
"step": 1405
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 10.846153846153847,
|
| 2543 |
+
"grad_norm": 0.0,
|
| 2544 |
+
"learning_rate": 4.2955e-05,
|
| 2545 |
+
"loss": 1.7809,
|
| 2546 |
+
"mean_token_accuracy": 0.6493318378925323,
|
| 2547 |
+
"num_tokens": 5143608.0,
|
| 2548 |
+
"step": 1410
|
| 2549 |
}
|
| 2550 |
],
|
| 2551 |
"logging_steps": 5,
|
|
|
|
| 2565 |
"attributes": {}
|
| 2566 |
}
|
| 2567 |
},
|
| 2568 |
+
"total_flos": 2.6058150730579968e+17,
|
| 2569 |
"train_batch_size": 4,
|
| 2570 |
"trial_name": null,
|
| 2571 |
"trial_params": null
|