Training in progress, step 2120, 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:c8815956b338b9ea3edf3df57b3d08c8294b97b9075d4784c7ce6665f61a7c7f
|
| 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:b2c4f541cbfce7a927d22bcb2afd88cb1f03bea75f66a4d700ab4c6199300664
|
| 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 sha256:3a27c077084510aa4a909a831c319cf58d575e7b690a8770575c689ae223cf5b
|
| 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": 16.
|
| 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,
|
|
@@ -3806,6 +3806,24 @@
|
|
| 3806 |
"mean_token_accuracy": 0.65393525660038,
|
| 3807 |
"num_tokens": 7695148.0,
|
| 3808 |
"step": 2110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3809 |
}
|
| 3810 |
],
|
| 3811 |
"logging_steps": 5,
|
|
@@ -3825,7 +3843,7 @@
|
|
| 3825 |
"attributes": {}
|
| 3826 |
}
|
| 3827 |
},
|
| 3828 |
-
"total_flos": 3.
|
| 3829 |
"train_batch_size": 4,
|
| 3830 |
"trial_name": null,
|
| 3831 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3806 |
"mean_token_accuracy": 0.65393525660038,
|
| 3807 |
"num_tokens": 7695148.0,
|
| 3808 |
"step": 2110
|
| 3809 |
+
},
|
| 3810 |
+
{
|
| 3811 |
+
"epoch": 16.26923076923077,
|
| 3812 |
+
"grad_norm": 0.0,
|
| 3813 |
+
"learning_rate": 3.943e-05,
|
| 3814 |
+
"loss": 1.7343,
|
| 3815 |
+
"mean_token_accuracy": 0.6496871590614319,
|
| 3816 |
+
"num_tokens": 7713440.0,
|
| 3817 |
+
"step": 2115
|
| 3818 |
+
},
|
| 3819 |
+
{
|
| 3820 |
+
"epoch": 16.307692307692307,
|
| 3821 |
+
"grad_norm": 0.0,
|
| 3822 |
+
"learning_rate": 3.9405e-05,
|
| 3823 |
+
"loss": 1.7737,
|
| 3824 |
+
"mean_token_accuracy": 0.6332459360361099,
|
| 3825 |
+
"num_tokens": 7731634.0,
|
| 3826 |
+
"step": 2120
|
| 3827 |
}
|
| 3828 |
],
|
| 3829 |
"logging_steps": 5,
|
|
|
|
| 3843 |
"attributes": {}
|
| 3844 |
}
|
| 3845 |
},
|
| 3846 |
+
"total_flos": 3.916795735277568e+17,
|
| 3847 |
"train_batch_size": 4,
|
| 3848 |
"trial_name": null,
|
| 3849 |
"trial_params": null
|