Training in progress, step 610, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1980e9d513046749104f51d129c38cf0c83397055629e08ef9bf07eaab0951f3
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea179640ae26abb1f6b655e9477a7f8d2041cb5ccddd0777813faddfc772078
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68443901778d0fcd7a67d39423203107772649973a82bb59d560e31f3a6fd7e
|
| 3 |
size 14645
|
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 sha256:3123c3a3cbd19b5762f539402f90431bc51bf235aea93b08293175f902d0c081
|
| 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": 0.
|
| 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,
|
|
@@ -618,6 +618,16 @@
|
|
| 618 |
"mean_token_accuracy": 0.7530097424983978,
|
| 619 |
"num_tokens": 2780314.0,
|
| 620 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 621 |
}
|
| 622 |
],
|
| 623 |
"logging_steps": 10,
|
|
@@ -637,7 +647,7 @@
|
|
| 637 |
"attributes": {}
|
| 638 |
}
|
| 639 |
},
|
| 640 |
-
"total_flos": 1.
|
| 641 |
"train_batch_size": 4,
|
| 642 |
"trial_name": null,
|
| 643 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.13013333333333332,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 618 |
"mean_token_accuracy": 0.7530097424983978,
|
| 619 |
"num_tokens": 2780314.0,
|
| 620 |
"step": 600
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.9936468213796615,
|
| 624 |
+
"epoch": 0.13013333333333332,
|
| 625 |
+
"grad_norm": 0.1984289288520813,
|
| 626 |
+
"learning_rate": 9.971427142847718e-05,
|
| 627 |
+
"loss": 1.0992106437683105,
|
| 628 |
+
"mean_token_accuracy": 0.7568746477365493,
|
| 629 |
+
"num_tokens": 2827832.0,
|
| 630 |
+
"step": 610
|
| 631 |
}
|
| 632 |
],
|
| 633 |
"logging_steps": 10,
|
|
|
|
| 647 |
"attributes": {}
|
| 648 |
}
|
| 649 |
},
|
| 650 |
+
"total_flos": 1.345012387427328e+16,
|
| 651 |
"train_batch_size": 4,
|
| 652 |
"trial_name": null,
|
| 653 |
"trial_params": null
|