Training in progress, step 3260, 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:b44f1f21c05adee80d57b5cbefb10a60af1279bbe1f77a7837b0b4b7e686780b
|
| 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 sha256:15f3d681217099a5d1d521358edbbec39787b5f4ede34a61cd4addd72e3694f3
|
| 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 sha256:69aa97ccfec106620d8b726bcb0a2b830daa3cb0135bf0b21185120f34ab85ae
|
| 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": 25.
|
| 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,
|
|
@@ -5858,6 +5858,24 @@
|
|
| 5858 |
"mean_token_accuracy": 0.6547602891921998,
|
| 5859 |
"num_tokens": 11852625.0,
|
| 5860 |
"step": 3250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5861 |
}
|
| 5862 |
],
|
| 5863 |
"logging_steps": 5,
|
|
@@ -5877,7 +5895,7 @@
|
|
| 5877 |
"attributes": {}
|
| 5878 |
}
|
| 5879 |
},
|
| 5880 |
-
"total_flos": 6.
|
| 5881 |
"train_batch_size": 4,
|
| 5882 |
"trial_name": null,
|
| 5883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5858 |
"mean_token_accuracy": 0.6547602891921998,
|
| 5859 |
"num_tokens": 11852625.0,
|
| 5860 |
"step": 3250
|
| 5861 |
+
},
|
| 5862 |
+
{
|
| 5863 |
+
"epoch": 25.03846153846154,
|
| 5864 |
+
"grad_norm": 0.0,
|
| 5865 |
+
"learning_rate": 3.373e-05,
|
| 5866 |
+
"loss": 1.7518,
|
| 5867 |
+
"mean_token_accuracy": 0.6456693172454834,
|
| 5868 |
+
"num_tokens": 11870498.0,
|
| 5869 |
+
"step": 3255
|
| 5870 |
+
},
|
| 5871 |
+
{
|
| 5872 |
+
"epoch": 25.076923076923077,
|
| 5873 |
+
"grad_norm": 0.0,
|
| 5874 |
+
"learning_rate": 3.3705000000000003e-05,
|
| 5875 |
+
"loss": 1.734,
|
| 5876 |
+
"mean_token_accuracy": 0.6480823725461959,
|
| 5877 |
+
"num_tokens": 11888806.0,
|
| 5878 |
+
"step": 3260
|
| 5879 |
}
|
| 5880 |
],
|
| 5881 |
"logging_steps": 5,
|
|
|
|
| 5895 |
"attributes": {}
|
| 5896 |
}
|
| 5897 |
},
|
| 5898 |
+
"total_flos": 6.02396172398592e+17,
|
| 5899 |
"train_batch_size": 4,
|
| 5900 |
"trial_name": null,
|
| 5901 |
"trial_params": null
|