Training in progress, step 8790, 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 sha256:3f5719b49c985e99447815b6b3001dcba30277a29573a88a40d27b865e1c4f56
|
| 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 sha256:60b191938c8f31d4fef1cf5fed78065b4323c489da59ab05689d87892e9875ed
|
| 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 sha256:4404ecd15d394ad464005ce3f748ae71faa509ab95d5a9abfb24e1679dcb2df4
|
| 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": 67.
|
| 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,
|
|
@@ -15812,6 +15812,24 @@
|
|
| 15812 |
"mean_token_accuracy": 0.651617681980133,
|
| 15813 |
"num_tokens": 32019131.0,
|
| 15814 |
"step": 8780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15815 |
}
|
| 15816 |
],
|
| 15817 |
"logging_steps": 5,
|
|
@@ -15831,7 +15849,7 @@
|
|
| 15831 |
"attributes": {}
|
| 15832 |
}
|
| 15833 |
},
|
| 15834 |
-
"total_flos": 1.
|
| 15835 |
"train_batch_size": 4,
|
| 15836 |
"trial_name": null,
|
| 15837 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15812 |
"mean_token_accuracy": 0.651617681980133,
|
| 15813 |
"num_tokens": 32019131.0,
|
| 15814 |
"step": 8780
|
| 15815 |
+
},
|
| 15816 |
+
{
|
| 15817 |
+
"epoch": 67.57692307692308,
|
| 15818 |
+
"grad_norm": 0.0,
|
| 15819 |
+
"learning_rate": 6.08e-06,
|
| 15820 |
+
"loss": 1.7092,
|
| 15821 |
+
"mean_token_accuracy": 0.6570148169994354,
|
| 15822 |
+
"num_tokens": 32037428.0,
|
| 15823 |
+
"step": 8785
|
| 15824 |
+
},
|
| 15825 |
+
{
|
| 15826 |
+
"epoch": 67.61538461538461,
|
| 15827 |
+
"grad_norm": 0.0,
|
| 15828 |
+
"learning_rate": 6.0550000000000005e-06,
|
| 15829 |
+
"loss": 1.7594,
|
| 15830 |
+
"mean_token_accuracy": 0.6468034237623215,
|
| 15831 |
+
"num_tokens": 32055491.0,
|
| 15832 |
+
"step": 8790
|
| 15833 |
}
|
| 15834 |
],
|
| 15835 |
"logging_steps": 5,
|
|
|
|
| 15849 |
"attributes": {}
|
| 15850 |
}
|
| 15851 |
},
|
| 15852 |
+
"total_flos": 1.6254608621705626e+18,
|
| 15853 |
"train_batch_size": 4,
|
| 15854 |
"trial_name": null,
|
| 15855 |
"trial_params": null
|