Training in progress, step 2150, 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 sha256:53d8065e411f3f33661905330f8759ba7a2051037d9bcbe5b98a456eea55a5c3
|
| 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 sha256:2c00193496aeb047814f0dcb310e277354561d46005dd12b75bee0f9154e8324
|
| 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 sha256:5384ad90e05e62332fdacc2a202457d110a1adff7da3139d6819f856c2f74c70
|
| 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,
|
|
@@ -3860,6 +3860,24 @@
|
|
| 3860 |
"mean_token_accuracy": 0.6505914777517319,
|
| 3861 |
"num_tokens": 7805096.0,
|
| 3862 |
"step": 2140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3863 |
}
|
| 3864 |
],
|
| 3865 |
"logging_steps": 5,
|
|
@@ -3879,7 +3897,7 @@
|
|
| 3879 |
"attributes": {}
|
| 3880 |
}
|
| 3881 |
},
|
| 3882 |
-
"total_flos": 3.
|
| 3883 |
"train_batch_size": 4,
|
| 3884 |
"trial_name": null,
|
| 3885 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3860 |
"mean_token_accuracy": 0.6505914777517319,
|
| 3861 |
"num_tokens": 7805096.0,
|
| 3862 |
"step": 2140
|
| 3863 |
+
},
|
| 3864 |
+
{
|
| 3865 |
+
"epoch": 16.5,
|
| 3866 |
+
"grad_norm": 0.0,
|
| 3867 |
+
"learning_rate": 3.9280000000000003e-05,
|
| 3868 |
+
"loss": 1.7297,
|
| 3869 |
+
"mean_token_accuracy": 0.6588895499706269,
|
| 3870 |
+
"num_tokens": 7823436.0,
|
| 3871 |
+
"step": 2145
|
| 3872 |
+
},
|
| 3873 |
+
{
|
| 3874 |
+
"epoch": 16.53846153846154,
|
| 3875 |
+
"grad_norm": 0.0,
|
| 3876 |
+
"learning_rate": 3.9255e-05,
|
| 3877 |
+
"loss": 1.6984,
|
| 3878 |
+
"mean_token_accuracy": 0.6600228071212768,
|
| 3879 |
+
"num_tokens": 7842178.0,
|
| 3880 |
+
"step": 2150
|
| 3881 |
}
|
| 3882 |
],
|
| 3883 |
"logging_steps": 5,
|
|
|
|
| 3897 |
"attributes": {}
|
| 3898 |
}
|
| 3899 |
},
|
| 3900 |
+
"total_flos": 3.9729178123075584e+17,
|
| 3901 |
"train_batch_size": 4,
|
| 3902 |
"trial_name": null,
|
| 3903 |
"trial_params": null
|