Training in progress, step 2690, 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:d5eb2ee973879112097d1758432b9b2e61786fee31e6bd869380647709b83ef3
|
| 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 sha256:53b11da829c5f5458da3adbc60f1c036d0dde99453994139b78ffe2e40ce6886
|
| 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 sha256:2c2f4f1b1d31d7a26a28599e389b397c7f30000aa564ac18d3b8159b626b2933
|
| 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:d31de6314a1235f5b5377eb57bfa8665def9dea6396aa59075ea46f0656add58
|
| 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,
|
|
@@ -2698,6 +2698,16 @@
|
|
| 2698 |
"mean_token_accuracy": 0.7650713473558426,
|
| 2699 |
"num_tokens": 12451365.0,
|
| 2700 |
"step": 2680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2701 |
}
|
| 2702 |
],
|
| 2703 |
"logging_steps": 10,
|
|
@@ -2717,7 +2727,7 @@
|
|
| 2717 |
"attributes": {}
|
| 2718 |
}
|
| 2719 |
},
|
| 2720 |
-
"total_flos": 5.
|
| 2721 |
"train_batch_size": 4,
|
| 2722 |
"trial_name": null,
|
| 2723 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5738666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2698 |
"mean_token_accuracy": 0.7650713473558426,
|
| 2699 |
"num_tokens": 12451365.0,
|
| 2700 |
"step": 2680
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"entropy": 0.8713853091001511,
|
| 2704 |
+
"epoch": 0.5738666666666666,
|
| 2705 |
+
"grad_norm": 0.2360270470380783,
|
| 2706 |
+
"learning_rate": 8.385670600289302e-05,
|
| 2707 |
+
"loss": 0.9726097106933593,
|
| 2708 |
+
"mean_token_accuracy": 0.7823046505451202,
|
| 2709 |
+
"num_tokens": 12496420.0,
|
| 2710 |
+
"step": 2690
|
| 2711 |
}
|
| 2712 |
],
|
| 2713 |
"logging_steps": 10,
|
|
|
|
| 2727 |
"attributes": {}
|
| 2728 |
}
|
| 2729 |
},
|
| 2730 |
+
"total_flos": 5.922995712273101e+16,
|
| 2731 |
"train_batch_size": 4,
|
| 2732 |
"trial_name": null,
|
| 2733 |
"trial_params": null
|