Training in progress, step 340, 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 sha256:6bc56360c1b29b141026fdc5e0ceef93f17cc2c22adc87613110a3a4b40a774e
|
| 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 sha256:9aa970abc81c889e0cbb314cb0f05a63e24ecb67acb8cd83e48137aaac534371
|
| 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:ccc3f16750dd96edf7044ac2df8ef38aea6b9bfc6d0d65807078122f7275fd13
|
| 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": 2.
|
| 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,
|
|
@@ -602,6 +602,24 @@
|
|
| 602 |
"mean_token_accuracy": 0.6520386338233948,
|
| 603 |
"num_tokens": 1204773.0,
|
| 604 |
"step": 330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 605 |
}
|
| 606 |
],
|
| 607 |
"logging_steps": 5,
|
|
@@ -621,7 +639,7 @@
|
|
| 621 |
"attributes": {}
|
| 622 |
}
|
| 623 |
},
|
| 624 |
-
"total_flos": 6.
|
| 625 |
"train_batch_size": 4,
|
| 626 |
"trial_name": null,
|
| 627 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.6153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 602 |
"mean_token_accuracy": 0.6520386338233948,
|
| 603 |
"num_tokens": 1204773.0,
|
| 604 |
"step": 330
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.5769230769230766,
|
| 608 |
+
"grad_norm": 0.0,
|
| 609 |
+
"learning_rate": 4.833e-05,
|
| 610 |
+
"loss": 1.8146,
|
| 611 |
+
"mean_token_accuracy": 0.63519766330719,
|
| 612 |
+
"num_tokens": 1222245.0,
|
| 613 |
+
"step": 335
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.6153846153846154,
|
| 617 |
+
"grad_norm": 0.0,
|
| 618 |
+
"learning_rate": 4.8305e-05,
|
| 619 |
+
"loss": 1.7304,
|
| 620 |
+
"mean_token_accuracy": 0.6472829192876816,
|
| 621 |
+
"num_tokens": 1240309.0,
|
| 622 |
+
"step": 340
|
| 623 |
}
|
| 624 |
],
|
| 625 |
"logging_steps": 5,
|
|
|
|
| 639 |
"attributes": {}
|
| 640 |
}
|
| 641 |
},
|
| 642 |
+
"total_flos": 6.28376410202112e+16,
|
| 643 |
"train_batch_size": 4,
|
| 644 |
"trial_name": null,
|
| 645 |
"trial_params": null
|