Training in progress, step 680, 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 sha256:62fa0dae9180b8e9cf91b61b9b0567019ae5925eeaa05eadbc254e528f7a2648
|
| 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 sha256:929396c762c2458f69fce4eee4ff4f8bdbe90788d9ee70d2fce722708de74c60
|
| 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:d875597fcb96668619d5dfe31a66ddf6368794a8fc9781b7cc0c3d1a9465e866
|
| 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 sha256:3ead9e97463c05478511a6c80978c58c03ec8da4f5aacb879ebc6eb4dc33296d
|
| 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,
|
|
@@ -688,6 +688,16 @@
|
|
| 688 |
"mean_token_accuracy": 0.7364178076386452,
|
| 689 |
"num_tokens": 3101650.0,
|
| 690 |
"step": 670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 691 |
}
|
| 692 |
],
|
| 693 |
"logging_steps": 10,
|
|
@@ -707,7 +717,7 @@
|
|
| 707 |
"attributes": {}
|
| 708 |
}
|
| 709 |
},
|
| 710 |
-
"total_flos": 1.
|
| 711 |
"train_batch_size": 4,
|
| 712 |
"trial_name": null,
|
| 713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.14506666666666668,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 688 |
"mean_token_accuracy": 0.7364178076386452,
|
| 689 |
"num_tokens": 3101650.0,
|
| 690 |
"step": 670
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 0.8284098848700523,
|
| 694 |
+
"epoch": 0.14506666666666668,
|
| 695 |
+
"grad_norm": 0.3110564053058624,
|
| 696 |
+
"learning_rate": 9.957035847679749e-05,
|
| 697 |
+
"loss": 0.905357551574707,
|
| 698 |
+
"mean_token_accuracy": 0.7894617035984993,
|
| 699 |
+
"num_tokens": 3143357.0,
|
| 700 |
+
"step": 680
|
| 701 |
}
|
| 702 |
],
|
| 703 |
"logging_steps": 10,
|
|
|
|
| 717 |
"attributes": {}
|
| 718 |
}
|
| 719 |
},
|
| 720 |
+
"total_flos": 1.4888787600940032e+16,
|
| 721 |
"train_batch_size": 4,
|
| 722 |
"trial_name": null,
|
| 723 |
"trial_params": null
|