Training in progress, step 4910, 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 sha256:21f059aa0ca80d88548a068e2c934bf7d0c60eb7219bb02bb615767d9b2b02e9
|
| 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 sha256:66fc73e81798977d3f6f35f0e02c5a86e43863ea81f15b75dc86f149f22aa47a
|
| 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 sha256:6682accf42c6235bed645ccd5ef08edf0e0e25abb93e5a2817d3177ea0671e81
|
| 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": 37.
|
| 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,
|
|
@@ -8828,6 +8828,24 @@
|
|
| 8828 |
"mean_token_accuracy": 0.650345778465271,
|
| 8829 |
"num_tokens": 17869722.0,
|
| 8830 |
"step": 4900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8831 |
}
|
| 8832 |
],
|
| 8833 |
"logging_steps": 5,
|
|
@@ -8847,7 +8865,7 @@
|
|
| 8847 |
"attributes": {}
|
| 8848 |
}
|
| 8849 |
},
|
| 8850 |
-
"total_flos": 9.
|
| 8851 |
"train_batch_size": 4,
|
| 8852 |
"trial_name": null,
|
| 8853 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8828 |
"mean_token_accuracy": 0.650345778465271,
|
| 8829 |
"num_tokens": 17869722.0,
|
| 8830 |
"step": 4900
|
| 8831 |
+
},
|
| 8832 |
+
{
|
| 8833 |
+
"epoch": 37.73076923076923,
|
| 8834 |
+
"grad_norm": 0.0,
|
| 8835 |
+
"learning_rate": 2.5480000000000003e-05,
|
| 8836 |
+
"loss": 1.6724,
|
| 8837 |
+
"mean_token_accuracy": 0.661380472779274,
|
| 8838 |
+
"num_tokens": 17888580.0,
|
| 8839 |
+
"step": 4905
|
| 8840 |
+
},
|
| 8841 |
+
{
|
| 8842 |
+
"epoch": 37.76923076923077,
|
| 8843 |
+
"grad_norm": 0.0,
|
| 8844 |
+
"learning_rate": 2.5455e-05,
|
| 8845 |
+
"loss": 1.7188,
|
| 8846 |
+
"mean_token_accuracy": 0.6543963342905045,
|
| 8847 |
+
"num_tokens": 17907123.0,
|
| 8848 |
+
"step": 4910
|
| 8849 |
}
|
| 8850 |
],
|
| 8851 |
"logging_steps": 5,
|
|
|
|
| 8865 |
"attributes": {}
|
| 8866 |
}
|
| 8867 |
},
|
| 8868 |
+
"total_flos": 9.074798224751002e+17,
|
| 8869 |
"train_batch_size": 4,
|
| 8870 |
"trial_name": null,
|
| 8871 |
"trial_params": null
|