Training in progress, step 8640, 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 sha256:362d75d4a053ec541b16e8c624ddd8d2287597589ed9ef3a530730f36e25b7cf
|
| 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 sha256:30f3cb9b7f6adefdd8e8c4ec8c8129641edef38bec97e47c851025c377cd4785
|
| 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 sha256:309ad5ce1e0e919c247bf97717080cf9e05d2600937d97dd82886953c52f4fd6
|
| 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": 66.
|
| 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,
|
|
@@ -15542,6 +15542,24 @@
|
|
| 15542 |
"mean_token_accuracy": 0.6450399339199067,
|
| 15543 |
"num_tokens": 31474686.0,
|
| 15544 |
"step": 8630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15545 |
}
|
| 15546 |
],
|
| 15547 |
"logging_steps": 5,
|
|
@@ -15561,7 +15579,7 @@
|
|
| 15561 |
"attributes": {}
|
| 15562 |
}
|
| 15563 |
},
|
| 15564 |
-
"total_flos": 1.
|
| 15565 |
"train_batch_size": 4,
|
| 15566 |
"trial_name": null,
|
| 15567 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15542 |
"mean_token_accuracy": 0.6450399339199067,
|
| 15543 |
"num_tokens": 31474686.0,
|
| 15544 |
"step": 8630
|
| 15545 |
+
},
|
| 15546 |
+
{
|
| 15547 |
+
"epoch": 66.42307692307692,
|
| 15548 |
+
"grad_norm": 0.0,
|
| 15549 |
+
"learning_rate": 6.830000000000001e-06,
|
| 15550 |
+
"loss": 1.7736,
|
| 15551 |
+
"mean_token_accuracy": 0.6471458494663238,
|
| 15552 |
+
"num_tokens": 31492406.0,
|
| 15553 |
+
"step": 8635
|
| 15554 |
+
},
|
| 15555 |
+
{
|
| 15556 |
+
"epoch": 66.46153846153847,
|
| 15557 |
+
"grad_norm": 0.0,
|
| 15558 |
+
"learning_rate": 6.805e-06,
|
| 15559 |
+
"loss": 1.6584,
|
| 15560 |
+
"mean_token_accuracy": 0.6657146126031875,
|
| 15561 |
+
"num_tokens": 31511342.0,
|
| 15562 |
+
"step": 8640
|
| 15563 |
}
|
| 15564 |
],
|
| 15565 |
"logging_steps": 5,
|
|
|
|
| 15579 |
"attributes": {}
|
| 15580 |
}
|
| 15581 |
},
|
| 15582 |
+
"total_flos": 1.5978486923019878e+18,
|
| 15583 |
"train_batch_size": 4,
|
| 15584 |
"trial_name": null,
|
| 15585 |
"trial_params": null
|