Training in progress, step 640, 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 sha256:51dd734530cde416a6bc5d2b6cd555828693264cc1cc46aeeecee9f81d0c52bd
|
| 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:ea0c3af9a9f1a63074486c3c8e171866d98c3c53377d97e296b715e48782fba6
|
| 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 sha256:02d488df1edbef1d3d4d686f2ade3e4d4cafbb2ad64ace71441881733f52db9b
|
| 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 sha256:99a26b47fd98de9029ba62a9e893f466571afe281f2deba5f59a50e0ac0b1f13
|
| 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,
|
|
@@ -648,6 +648,16 @@
|
|
| 648 |
"mean_token_accuracy": 0.7586069479584694,
|
| 649 |
"num_tokens": 2913600.0,
|
| 650 |
"step": 630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 651 |
}
|
| 652 |
],
|
| 653 |
"logging_steps": 10,
|
|
@@ -667,7 +677,7 @@
|
|
| 667 |
"attributes": {}
|
| 668 |
}
|
| 669 |
},
|
| 670 |
-
"total_flos": 1.
|
| 671 |
"train_batch_size": 4,
|
| 672 |
"trial_name": null,
|
| 673 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.13653333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 648 |
"mean_token_accuracy": 0.7586069479584694,
|
| 649 |
"num_tokens": 2913600.0,
|
| 650 |
"step": 630
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 1.0591406509280206,
|
| 654 |
+
"epoch": 0.13653333333333334,
|
| 655 |
+
"grad_norm": 0.23842781782150269,
|
| 656 |
+
"learning_rate": 9.965616364580636e-05,
|
| 657 |
+
"loss": 1.1297724723815918,
|
| 658 |
+
"mean_token_accuracy": 0.7443821474909782,
|
| 659 |
+
"num_tokens": 2962337.0,
|
| 660 |
+
"step": 640
|
| 661 |
}
|
| 662 |
],
|
| 663 |
"logging_steps": 10,
|
|
|
|
| 677 |
"attributes": {}
|
| 678 |
}
|
| 679 |
},
|
| 680 |
+
"total_flos": 1.404896254752768e+16,
|
| 681 |
"train_batch_size": 4,
|
| 682 |
"trial_name": null,
|
| 683 |
"trial_params": null
|