Training in progress, step 7550, 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 sha256:1e7c6c74390536ded43a8fda0cb6f49549f2f718914045b462e24d6028d015ca
|
| 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 sha256:0d77a0c3e0ea126a0a787b64355bd2e7e73cca05b4b6b238eac2af60f6547500
|
| 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 sha256:8c6f73ce85b31a5d4d4cadf3f51c6cac5da917bd38fa5d7cc819d94e7279d160
|
| 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": 58.
|
| 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,
|
|
@@ -13580,6 +13580,24 @@
|
|
| 13580 |
"mean_token_accuracy": 0.6375920951366425,
|
| 13581 |
"num_tokens": 27498090.0,
|
| 13582 |
"step": 7540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13583 |
}
|
| 13584 |
],
|
| 13585 |
"logging_steps": 5,
|
|
@@ -13599,7 +13617,7 @@
|
|
| 13599 |
"attributes": {}
|
| 13600 |
}
|
| 13601 |
},
|
| 13602 |
-
"total_flos": 1.
|
| 13603 |
"train_batch_size": 4,
|
| 13604 |
"trial_name": null,
|
| 13605 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13580 |
"mean_token_accuracy": 0.6375920951366425,
|
| 13581 |
"num_tokens": 27498090.0,
|
| 13582 |
"step": 7540
|
| 13583 |
+
},
|
| 13584 |
+
{
|
| 13585 |
+
"epoch": 58.03846153846154,
|
| 13586 |
+
"grad_norm": 0.0,
|
| 13587 |
+
"learning_rate": 1.2280000000000001e-05,
|
| 13588 |
+
"loss": 1.7156,
|
| 13589 |
+
"mean_token_accuracy": 0.6615946650505066,
|
| 13590 |
+
"num_tokens": 27516714.0,
|
| 13591 |
+
"step": 7545
|
| 13592 |
+
},
|
| 13593 |
+
{
|
| 13594 |
+
"epoch": 58.07692307692308,
|
| 13595 |
+
"grad_norm": 0.0,
|
| 13596 |
+
"learning_rate": 1.2255e-05,
|
| 13597 |
+
"loss": 1.8136,
|
| 13598 |
+
"mean_token_accuracy": 0.6379787772893906,
|
| 13599 |
+
"num_tokens": 27534566.0,
|
| 13600 |
+
"step": 7550
|
| 13601 |
}
|
| 13602 |
],
|
| 13603 |
"logging_steps": 5,
|
|
|
|
| 13617 |
"attributes": {}
|
| 13618 |
}
|
| 13619 |
},
|
| 13620 |
+
"total_flos": 1.3959729162937958e+18,
|
| 13621 |
"train_batch_size": 4,
|
| 13622 |
"trial_name": null,
|
| 13623 |
"trial_params": null
|