Training in progress, step 1050, 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 sha256:064ce789c85d3acf222974689c1f908efbefcb77a0ab6a1f0e2bb1c833157b0d
|
| 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:caf0ed58f9a442e3c1c210c35f1d222175902615c476da1c5e45a70f763c66bf
|
| 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:bb819a7ac28c52724a9b8db6c870e72478b3ac0156462fa8b2180c6054e60be7
|
| 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": 8.
|
| 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,
|
|
@@ -1880,6 +1880,24 @@
|
|
| 1880 |
"mean_token_accuracy": 0.6487736940383911,
|
| 1881 |
"num_tokens": 3792840.0,
|
| 1882 |
"step": 1040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1883 |
}
|
| 1884 |
],
|
| 1885 |
"logging_steps": 5,
|
|
@@ -1899,7 +1917,7 @@
|
|
| 1899 |
"attributes": {}
|
| 1900 |
}
|
| 1901 |
},
|
| 1902 |
-
"total_flos": 1.
|
| 1903 |
"train_batch_size": 4,
|
| 1904 |
"trial_name": null,
|
| 1905 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1880 |
"mean_token_accuracy": 0.6487736940383911,
|
| 1881 |
"num_tokens": 3792840.0,
|
| 1882 |
"step": 1040
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 8.038461538461538,
|
| 1886 |
+
"grad_norm": 0.0,
|
| 1887 |
+
"learning_rate": 4.478e-05,
|
| 1888 |
+
"loss": 1.7554,
|
| 1889 |
+
"mean_token_accuracy": 0.6465101599693298,
|
| 1890 |
+
"num_tokens": 3810513.0,
|
| 1891 |
+
"step": 1045
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 8.076923076923077,
|
| 1895 |
+
"grad_norm": 0.0,
|
| 1896 |
+
"learning_rate": 4.4755e-05,
|
| 1897 |
+
"loss": 1.7955,
|
| 1898 |
+
"mean_token_accuracy": 0.6376824468374253,
|
| 1899 |
+
"num_tokens": 3828269.0,
|
| 1900 |
+
"step": 1050
|
| 1901 |
}
|
| 1902 |
],
|
| 1903 |
"logging_steps": 5,
|
|
|
|
| 1917 |
"attributes": {}
|
| 1918 |
}
|
| 1919 |
},
|
| 1920 |
+
"total_flos": 1.9408750010597376e+17,
|
| 1921 |
"train_batch_size": 4,
|
| 1922 |
"trial_name": null,
|
| 1923 |
"trial_params": null
|