Training in progress, step 2780, 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 sha256:446933e758674bdbeab8254eda223f066b9052a14ea7eab235c0581a4dd1a724
|
| 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 sha256:1693d202a270b5264eabf82b65cfd8ab43c97dbd641cadb285d6d279606ca776
|
| 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 sha256:18d915098765590b6ff28cf2ed5c38caee02cbbcd9e668d39f3795cc44640341
|
| 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:e7dde02378f849a5f969ad88bdffeead677640fc459b4249505e9f49c2e07b50
|
| 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,
|
|
@@ -2788,6 +2788,16 @@
|
|
| 2788 |
"mean_token_accuracy": 0.7454183496534824,
|
| 2789 |
"num_tokens": 12874281.0,
|
| 2790 |
"step": 2770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2791 |
}
|
| 2792 |
],
|
| 2793 |
"logging_steps": 10,
|
|
@@ -2807,7 +2817,7 @@
|
|
| 2807 |
"attributes": {}
|
| 2808 |
}
|
| 2809 |
},
|
| 2810 |
-
"total_flos": 6.
|
| 2811 |
"train_batch_size": 4,
|
| 2812 |
"trial_name": null,
|
| 2813 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5930666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2788 |
"mean_token_accuracy": 0.7454183496534824,
|
| 2789 |
"num_tokens": 12874281.0,
|
| 2790 |
"step": 2770
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"entropy": 0.8854779146611691,
|
| 2794 |
+
"epoch": 0.5930666666666666,
|
| 2795 |
+
"grad_norm": 0.19881795346736908,
|
| 2796 |
+
"learning_rate": 8.26942572312912e-05,
|
| 2797 |
+
"loss": 0.9492866516113281,
|
| 2798 |
+
"mean_token_accuracy": 0.7723072916269302,
|
| 2799 |
+
"num_tokens": 12921599.0,
|
| 2800 |
+
"step": 2780
|
| 2801 |
}
|
| 2802 |
],
|
| 2803 |
"logging_steps": 10,
|
|
|
|
| 2817 |
"attributes": {}
|
| 2818 |
}
|
| 2819 |
},
|
| 2820 |
+
"total_flos": 6.123599007724954e+16,
|
| 2821 |
"train_batch_size": 4,
|
| 2822 |
"trial_name": null,
|
| 2823 |
"trial_params": null
|