Training in progress, step 1610, 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 sha256:75d3175b5b83cd61f10f363a66d7eef087f7215a6fc206450fe23180d5a9c994
|
| 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 sha256:31cb4509e4ac1b4d067ce8c8a9ff8b92909379c9774b4a1692febcd822e8061a
|
| 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 sha256:95cf6a8101fc02e7850b4d62827486a380b129bfc18322c742f3b3739823d03f
|
| 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": 12.
|
| 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,
|
|
@@ -2888,6 +2888,24 @@
|
|
| 2888 |
"mean_token_accuracy": 0.6511879444122315,
|
| 2889 |
"num_tokens": 5831416.0,
|
| 2890 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2891 |
}
|
| 2892 |
],
|
| 2893 |
"logging_steps": 5,
|
|
@@ -2907,7 +2925,7 @@
|
|
| 2907 |
"attributes": {}
|
| 2908 |
}
|
| 2909 |
},
|
| 2910 |
-
"total_flos": 2.
|
| 2911 |
"train_batch_size": 4,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2888 |
"mean_token_accuracy": 0.6511879444122315,
|
| 2889 |
"num_tokens": 5831416.0,
|
| 2890 |
"step": 1600
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 12.346153846153847,
|
| 2894 |
+
"grad_norm": 0.0,
|
| 2895 |
+
"learning_rate": 4.198e-05,
|
| 2896 |
+
"loss": 1.7307,
|
| 2897 |
+
"mean_token_accuracy": 0.6532302528619767,
|
| 2898 |
+
"num_tokens": 5850125.0,
|
| 2899 |
+
"step": 1605
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 12.384615384615385,
|
| 2903 |
+
"grad_norm": 0.0,
|
| 2904 |
+
"learning_rate": 4.1955e-05,
|
| 2905 |
+
"loss": 1.7729,
|
| 2906 |
+
"mean_token_accuracy": 0.6425417333841323,
|
| 2907 |
+
"num_tokens": 5868205.0,
|
| 2908 |
+
"step": 1610
|
| 2909 |
}
|
| 2910 |
],
|
| 2911 |
"logging_steps": 5,
|
|
|
|
| 2925 |
"attributes": {}
|
| 2926 |
}
|
| 2927 |
},
|
| 2928 |
+
"total_flos": 2.971207171134259e+17,
|
| 2929 |
"train_batch_size": 4,
|
| 2930 |
"trial_name": null,
|
| 2931 |
"trial_params": null
|