Training in progress, step 450, 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:bc159d244403f58b1edb8000fcca24f96ef9884befc8b4a9f4eae1aead0a326b
|
| 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 sha256:3f6fb5af7bfc06f61d5a06914c0841669f8d74d95b292437325ca8d79b4ce24a
|
| 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 sha256:61837fbd4031c846229a56f487d24d85789ffc73d167c9342f16b80fb60f8050
|
| 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": 3.
|
| 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,
|
|
@@ -800,6 +800,24 @@
|
|
| 800 |
"mean_token_accuracy": 0.6636441439390183,
|
| 801 |
"num_tokens": 1605918.0,
|
| 802 |
"step": 440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 803 |
}
|
| 804 |
],
|
| 805 |
"logging_steps": 5,
|
|
@@ -819,7 +837,7 @@
|
|
| 819 |
"attributes": {}
|
| 820 |
}
|
| 821 |
},
|
| 822 |
-
"total_flos": 8.
|
| 823 |
"train_batch_size": 4,
|
| 824 |
"trial_name": null,
|
| 825 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.4615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 800 |
"mean_token_accuracy": 0.6636441439390183,
|
| 801 |
"num_tokens": 1605918.0,
|
| 802 |
"step": 440
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 3.423076923076923,
|
| 806 |
+
"grad_norm": 0.0,
|
| 807 |
+
"learning_rate": 4.778e-05,
|
| 808 |
+
"loss": 1.7238,
|
| 809 |
+
"mean_token_accuracy": 0.6505128175020218,
|
| 810 |
+
"num_tokens": 1624275.0,
|
| 811 |
+
"step": 445
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 3.4615384615384617,
|
| 815 |
+
"grad_norm": 0.0,
|
| 816 |
+
"learning_rate": 4.7755e-05,
|
| 817 |
+
"loss": 1.684,
|
| 818 |
+
"mean_token_accuracy": 0.6628347337245941,
|
| 819 |
+
"num_tokens": 1642694.0,
|
| 820 |
+
"step": 450
|
| 821 |
}
|
| 822 |
],
|
| 823 |
"logging_steps": 5,
|
|
|
|
| 837 |
"attributes": {}
|
| 838 |
}
|
| 839 |
},
|
| 840 |
+
"total_flos": 8.315311522332672e+16,
|
| 841 |
"train_batch_size": 4,
|
| 842 |
"trial_name": null,
|
| 843 |
"trial_params": null
|