Training in progress, step 2650, 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:df2af7b278014781a1638c9e0d43f4fd1f22205f9a1d47e1823c55a04920a940
|
| 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 sha256:50e2a54735eb8cf392f843b4ca345e651749e88420d06314fade1899c18cd608
|
| 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 sha256:7284ecfd155617c16a7c438c925d8d666f50626b3863231652b162becace7850
|
| 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 sha256:4413f079b5a916ef56df9b83416e8145e5cbab75e88df3311028064282b6191f
|
| 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,
|
|
@@ -2658,6 +2658,16 @@
|
|
| 2658 |
"mean_token_accuracy": 0.7567313954234123,
|
| 2659 |
"num_tokens": 12274057.0,
|
| 2660 |
"step": 2640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2661 |
}
|
| 2662 |
],
|
| 2663 |
"logging_steps": 10,
|
|
@@ -2677,7 +2687,7 @@
|
|
| 2677 |
"attributes": {}
|
| 2678 |
}
|
| 2679 |
},
|
| 2680 |
-
"total_flos": 5.
|
| 2681 |
"train_batch_size": 4,
|
| 2682 |
"trial_name": null,
|
| 2683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5653333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2658 |
"mean_token_accuracy": 0.7567313954234123,
|
| 2659 |
"num_tokens": 12274057.0,
|
| 2660 |
"step": 2640
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"entropy": 0.9988928638398648,
|
| 2664 |
+
"epoch": 0.5653333333333334,
|
| 2665 |
+
"grad_norm": 0.25330716371536255,
|
| 2666 |
+
"learning_rate": 8.436286966602903e-05,
|
| 2667 |
+
"loss": 1.0961190223693849,
|
| 2668 |
+
"mean_token_accuracy": 0.7484898209571839,
|
| 2669 |
+
"num_tokens": 12319765.0,
|
| 2670 |
+
"step": 2650
|
| 2671 |
}
|
| 2672 |
],
|
| 2673 |
"logging_steps": 10,
|
|
|
|
| 2687 |
"attributes": {}
|
| 2688 |
}
|
| 2689 |
},
|
| 2690 |
+
"total_flos": 5.839613397385421e+16,
|
| 2691 |
"train_batch_size": 4,
|
| 2692 |
"trial_name": null,
|
| 2693 |
"trial_params": null
|