Training in progress, step 7030, 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 sha256:5d0bdcff861b0cfb65bd2822e4578884496d8625f756d5e292232b978c13ad1d
|
| 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 sha256:6e72474b11152c2470a8c77c2c7d58df27fb65927167a852daa483eb3e92ede1
|
| 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:d659250c4cd27f8d95a5d51a39b46dc1aed36cf15db17a7eaf339f33952fc897
|
| 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": 54.
|
| 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,
|
|
@@ -12644,6 +12644,24 @@
|
|
| 12644 |
"mean_token_accuracy": 0.6570352196693421,
|
| 12645 |
"num_tokens": 25601670.0,
|
| 12646 |
"step": 7020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12647 |
}
|
| 12648 |
],
|
| 12649 |
"logging_steps": 5,
|
|
@@ -12663,7 +12681,7 @@
|
|
| 12663 |
"attributes": {}
|
| 12664 |
}
|
| 12665 |
},
|
| 12666 |
-
"total_flos": 1.
|
| 12667 |
"train_batch_size": 4,
|
| 12668 |
"trial_name": null,
|
| 12669 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12644 |
"mean_token_accuracy": 0.6570352196693421,
|
| 12645 |
"num_tokens": 25601670.0,
|
| 12646 |
"step": 7020
|
| 12647 |
+
},
|
| 12648 |
+
{
|
| 12649 |
+
"epoch": 54.03846153846154,
|
| 12650 |
+
"grad_norm": 0.0,
|
| 12651 |
+
"learning_rate": 1.488e-05,
|
| 12652 |
+
"loss": 1.7228,
|
| 12653 |
+
"mean_token_accuracy": 0.6555858552455902,
|
| 12654 |
+
"num_tokens": 25620461.0,
|
| 12655 |
+
"step": 7025
|
| 12656 |
+
},
|
| 12657 |
+
{
|
| 12658 |
+
"epoch": 54.07692307692308,
|
| 12659 |
+
"grad_norm": 0.0,
|
| 12660 |
+
"learning_rate": 1.4855e-05,
|
| 12661 |
+
"loss": 1.817,
|
| 12662 |
+
"mean_token_accuracy": 0.6386265754699707,
|
| 12663 |
+
"num_tokens": 25637942.0,
|
| 12664 |
+
"step": 7030
|
| 12665 |
}
|
| 12666 |
],
|
| 12667 |
"logging_steps": 5,
|
|
|
|
| 12681 |
"attributes": {}
|
| 12682 |
}
|
| 12683 |
},
|
| 12684 |
+
"total_flos": 1.2999270931749274e+18,
|
| 12685 |
"train_batch_size": 4,
|
| 12686 |
"trial_name": null,
|
| 12687 |
"trial_params": null
|