Training in progress, step 2800, 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 sha256:4c8cbe71740290cc970ab8d5ec8ae6c73125df8936c67dea4142bc462d0245dd
|
| 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:a4f9779f1a5d91b00d4248a9b931a1d48046fd311d85a06132f6c4e82da1fee8
|
| 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:b21e48f955adfb27cd16dd7ba96fbc344639dc4554ea36992618f83094fa5fd5
|
| 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 sha256:64c213455cab2785998b959751e34bb8b907ebbb24ce24b1da1152b62522e147
|
| 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,
|
|
@@ -2808,6 +2808,16 @@
|
|
| 2808 |
"mean_token_accuracy": 0.7538750320672989,
|
| 2809 |
"num_tokens": 12969810.0,
|
| 2810 |
"step": 2790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2811 |
}
|
| 2812 |
],
|
| 2813 |
"logging_steps": 10,
|
|
@@ -2827,7 +2837,7 @@
|
|
| 2827 |
"attributes": {}
|
| 2828 |
}
|
| 2829 |
},
|
| 2830 |
-
"total_flos": 6.
|
| 2831 |
"train_batch_size": 4,
|
| 2832 |
"trial_name": null,
|
| 2833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5973333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2808 |
"mean_token_accuracy": 0.7538750320672989,
|
| 2809 |
"num_tokens": 12969810.0,
|
| 2810 |
"step": 2790
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"entropy": 0.9516462504863739,
|
| 2814 |
+
"epoch": 0.5973333333333334,
|
| 2815 |
+
"grad_norm": 0.27765893936157227,
|
| 2816 |
+
"learning_rate": 8.243158631907382e-05,
|
| 2817 |
+
"loss": 1.0368030548095704,
|
| 2818 |
+
"mean_token_accuracy": 0.7694585740566253,
|
| 2819 |
+
"num_tokens": 13015439.0,
|
| 2820 |
+
"step": 2800
|
| 2821 |
}
|
| 2822 |
],
|
| 2823 |
"logging_steps": 10,
|
|
|
|
| 2837 |
"attributes": {}
|
| 2838 |
}
|
| 2839 |
},
|
| 2840 |
+
"total_flos": 6.168558319342694e+16,
|
| 2841 |
"train_batch_size": 4,
|
| 2842 |
"trial_name": null,
|
| 2843 |
"trial_params": null
|