Training in progress, step 7690, 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:fffdd4d26edfb2329373bf86bc9c85fbcdf48ae348f8c278d7c0275e36f88712
|
| 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:cfc140f3b266344695b2330e388d5c93a606d36821db5827522560044babdc73
|
| 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 sha256:617d061b6ac8a0e213c2e2a24d7af70cf6a236a27af6c467b006add402510a6d
|
| 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": 59.
|
| 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,
|
|
@@ -13832,6 +13832,24 @@
|
|
| 13832 |
"mean_token_accuracy": 0.6570581525564194,
|
| 13833 |
"num_tokens": 28007876.0,
|
| 13834 |
"step": 7680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13835 |
}
|
| 13836 |
],
|
| 13837 |
"logging_steps": 5,
|
|
@@ -13851,7 +13869,7 @@
|
|
| 13851 |
"attributes": {}
|
| 13852 |
}
|
| 13853 |
},
|
| 13854 |
-
"total_flos": 1.
|
| 13855 |
"train_batch_size": 4,
|
| 13856 |
"trial_name": null,
|
| 13857 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13832 |
"mean_token_accuracy": 0.6570581525564194,
|
| 13833 |
"num_tokens": 28007876.0,
|
| 13834 |
"step": 7680
|
| 13835 |
+
},
|
| 13836 |
+
{
|
| 13837 |
+
"epoch": 59.11538461538461,
|
| 13838 |
+
"grad_norm": 0.0,
|
| 13839 |
+
"learning_rate": 1.1580000000000001e-05,
|
| 13840 |
+
"loss": 1.6764,
|
| 13841 |
+
"mean_token_accuracy": 0.6651537865400314,
|
| 13842 |
+
"num_tokens": 28026168.0,
|
| 13843 |
+
"step": 7685
|
| 13844 |
+
},
|
| 13845 |
+
{
|
| 13846 |
+
"epoch": 59.15384615384615,
|
| 13847 |
+
"grad_norm": 0.0,
|
| 13848 |
+
"learning_rate": 1.1555e-05,
|
| 13849 |
+
"loss": 1.7593,
|
| 13850 |
+
"mean_token_accuracy": 0.6441430777311326,
|
| 13851 |
+
"num_tokens": 28044444.0,
|
| 13852 |
+
"step": 7690
|
| 13853 |
}
|
| 13854 |
],
|
| 13855 |
"logging_steps": 5,
|
|
|
|
| 13869 |
"attributes": {}
|
| 13870 |
}
|
| 13871 |
},
|
| 13872 |
+
"total_flos": 1.4218921829051597e+18,
|
| 13873 |
"train_batch_size": 4,
|
| 13874 |
"trial_name": null,
|
| 13875 |
"trial_params": null
|