Training in progress, step 1470, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b242e1cbc4d2e4c2796b4de732ed1aa0a6936f0748501208ef65d3dbb0f9213a
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a90b4d15fb63c411ecc64ee3cb12fad260fc86c672f8ccb78acc050745d5e25
|
| 3 |
size 14709
|
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 sha256:2fe8d8ebc11c6a1259a4f03fc3ec0983c4f839069b06d5b9a3b6a44c6912b038
|
| 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": 11.
|
| 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,
|
|
@@ -2636,6 +2636,24 @@
|
|
| 2636 |
"mean_token_accuracy": 0.6360325515270233,
|
| 2637 |
"num_tokens": 5323814.0,
|
| 2638 |
"step": 1460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2639 |
}
|
| 2640 |
],
|
| 2641 |
"logging_steps": 5,
|
|
@@ -2655,7 +2673,7 @@
|
|
| 2655 |
"attributes": {}
|
| 2656 |
}
|
| 2657 |
},
|
| 2658 |
-
"total_flos": 2.
|
| 2659 |
"train_batch_size": 4,
|
| 2660 |
"trial_name": null,
|
| 2661 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2636 |
"mean_token_accuracy": 0.6360325515270233,
|
| 2637 |
"num_tokens": 5323814.0,
|
| 2638 |
"step": 1460
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 11.26923076923077,
|
| 2642 |
+
"grad_norm": 0.0,
|
| 2643 |
+
"learning_rate": 4.2680000000000005e-05,
|
| 2644 |
+
"loss": 1.7991,
|
| 2645 |
+
"mean_token_accuracy": 0.6365718424320221,
|
| 2646 |
+
"num_tokens": 5341443.0,
|
| 2647 |
+
"step": 1465
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 11.307692307692308,
|
| 2651 |
+
"grad_norm": 0.0,
|
| 2652 |
+
"learning_rate": 4.2655e-05,
|
| 2653 |
+
"loss": 1.6735,
|
| 2654 |
+
"mean_token_accuracy": 0.6595575481653213,
|
| 2655 |
+
"num_tokens": 5361091.0,
|
| 2656 |
+
"step": 1470
|
| 2657 |
}
|
| 2658 |
],
|
| 2659 |
"logging_steps": 5,
|
|
|
|
| 2673 |
"attributes": {}
|
| 2674 |
}
|
| 2675 |
},
|
| 2676 |
+
"total_flos": 2.716647680507904e+17,
|
| 2677 |
"train_batch_size": 4,
|
| 2678 |
"trial_name": null,
|
| 2679 |
"trial_params": null
|