Training in progress, step 760, 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:b61e639daf8257b450734dde575943cbb28c16807f6d54b412a9169cb98302b4
|
| 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 sha256:46abcb12fceb1a18599d949d1f8176e0983d2cb632777d17c673f9c6db163c6e
|
| 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:aaa5bf999af491adfda83a24f55a7a482c289639f30844801b5a09cef7e58eb1
|
| 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 sha256:9ee219d0f4408ed9b4286a66a6b9f33bf2c6758ea01303339bdb8d42db7c01de
|
| 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,
|
|
@@ -768,6 +768,16 @@
|
|
| 768 |
"mean_token_accuracy": 0.7434881895780563,
|
| 769 |
"num_tokens": 3482687.0,
|
| 770 |
"step": 750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 771 |
}
|
| 772 |
],
|
| 773 |
"logging_steps": 10,
|
|
@@ -787,7 +797,7 @@
|
|
| 787 |
"attributes": {}
|
| 788 |
}
|
| 789 |
},
|
| 790 |
-
"total_flos": 1.
|
| 791 |
"train_batch_size": 4,
|
| 792 |
"trial_name": null,
|
| 793 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.16213333333333332,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 768 |
"mean_token_accuracy": 0.7434881895780563,
|
| 769 |
"num_tokens": 3482687.0,
|
| 770 |
"step": 750
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 1.008715095371008,
|
| 774 |
+
"epoch": 0.16213333333333332,
|
| 775 |
+
"grad_norm": 0.24042253196239471,
|
| 776 |
+
"learning_rate": 9.937025838443397e-05,
|
| 777 |
+
"loss": 1.0921018600463868,
|
| 778 |
+
"mean_token_accuracy": 0.7544152162969112,
|
| 779 |
+
"num_tokens": 3528140.0,
|
| 780 |
+
"step": 760
|
| 781 |
}
|
| 782 |
],
|
| 783 |
"logging_steps": 10,
|
|
|
|
| 797 |
"attributes": {}
|
| 798 |
}
|
| 799 |
},
|
| 800 |
+
"total_flos": 1.6687105994437632e+16,
|
| 801 |
"train_batch_size": 4,
|
| 802 |
"trial_name": null,
|
| 803 |
"trial_params": null
|