Training in progress, step 6010, 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:d1543c5dd78d112682b196d81d0098d6ab1ebd226de2df495a422b352494eb10
|
| 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 sha256:177538da147e87ebdd257bfa98610fd490cf07e1a23f58775b74b75f153cd240
|
| 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:cbdee1a9a1023a7679a461a2c2bab47552b01ed93198bd6af122c8bcdf289f32
|
| 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": 46.
|
| 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,
|
|
@@ -10808,6 +10808,24 @@
|
|
| 10808 |
"mean_token_accuracy": 0.6578894317150116,
|
| 10809 |
"num_tokens": 21880938.0,
|
| 10810 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10811 |
}
|
| 10812 |
],
|
| 10813 |
"logging_steps": 5,
|
|
@@ -10827,7 +10845,7 @@
|
|
| 10827 |
"attributes": {}
|
| 10828 |
}
|
| 10829 |
},
|
| 10830 |
-
"total_flos": 1.
|
| 10831 |
"train_batch_size": 4,
|
| 10832 |
"trial_name": null,
|
| 10833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10808 |
"mean_token_accuracy": 0.6578894317150116,
|
| 10809 |
"num_tokens": 21880938.0,
|
| 10810 |
"step": 6000
|
| 10811 |
+
},
|
| 10812 |
+
{
|
| 10813 |
+
"epoch": 46.19230769230769,
|
| 10814 |
+
"grad_norm": 0.0,
|
| 10815 |
+
"learning_rate": 1.9980000000000002e-05,
|
| 10816 |
+
"loss": 1.7818,
|
| 10817 |
+
"mean_token_accuracy": 0.641998165845871,
|
| 10818 |
+
"num_tokens": 21899058.0,
|
| 10819 |
+
"step": 6005
|
| 10820 |
+
},
|
| 10821 |
+
{
|
| 10822 |
+
"epoch": 46.23076923076923,
|
| 10823 |
+
"grad_norm": 0.0,
|
| 10824 |
+
"learning_rate": 1.9955e-05,
|
| 10825 |
+
"loss": 1.7064,
|
| 10826 |
+
"mean_token_accuracy": 0.6609808683395386,
|
| 10827 |
+
"num_tokens": 21917113.0,
|
| 10828 |
+
"step": 6010
|
| 10829 |
}
|
| 10830 |
],
|
| 10831 |
"logging_steps": 5,
|
|
|
|
| 10845 |
"attributes": {}
|
| 10846 |
}
|
| 10847 |
},
|
| 10848 |
+
"total_flos": 1.1107607939275162e+18,
|
| 10849 |
"train_batch_size": 4,
|
| 10850 |
"trial_name": null,
|
| 10851 |
"trial_params": null
|