Training in progress, step 1030, 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 sha256:3575a999e797fc5155b79274b4093c9c818c5fd61950baa0bb86e93f0eb70ea7
|
| 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 sha256:543fda8f6c9cab078ada3ac64dbdb165b92616a9d67c0b93daa5bba89ba8fd37
|
| 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 sha256:251bd5f36fbadbb095d0a85d64fa03d515a0c8e3017761f97432bf0276b02e56
|
| 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": 7.
|
| 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,
|
|
@@ -1844,6 +1844,24 @@
|
|
| 1844 |
"mean_token_accuracy": 0.6682931154966354,
|
| 1845 |
"num_tokens": 3720280.0,
|
| 1846 |
"step": 1020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1847 |
}
|
| 1848 |
],
|
| 1849 |
"logging_steps": 5,
|
|
@@ -1863,7 +1881,7 @@
|
|
| 1863 |
"attributes": {}
|
| 1864 |
}
|
| 1865 |
},
|
| 1866 |
-
"total_flos": 1.
|
| 1867 |
"train_batch_size": 4,
|
| 1868 |
"trial_name": null,
|
| 1869 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1844 |
"mean_token_accuracy": 0.6682931154966354,
|
| 1845 |
"num_tokens": 3720280.0,
|
| 1846 |
"step": 1020
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 7.884615384615385,
|
| 1850 |
+
"grad_norm": 0.0,
|
| 1851 |
+
"learning_rate": 4.488e-05,
|
| 1852 |
+
"loss": 1.7144,
|
| 1853 |
+
"mean_token_accuracy": 0.6550876766443252,
|
| 1854 |
+
"num_tokens": 3738885.0,
|
| 1855 |
+
"step": 1025
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 7.923076923076923,
|
| 1859 |
+
"grad_norm": 0.0,
|
| 1860 |
+
"learning_rate": 4.4855e-05,
|
| 1861 |
+
"loss": 1.6457,
|
| 1862 |
+
"mean_token_accuracy": 0.6694303750991821,
|
| 1863 |
+
"num_tokens": 3757638.0,
|
| 1864 |
+
"step": 1030
|
| 1865 |
}
|
| 1866 |
],
|
| 1867 |
"logging_steps": 5,
|
|
|
|
| 1881 |
"attributes": {}
|
| 1882 |
}
|
| 1883 |
},
|
| 1884 |
+
"total_flos": 1.9054593124909056e+17,
|
| 1885 |
"train_batch_size": 4,
|
| 1886 |
"trial_name": null,
|
| 1887 |
"trial_params": null
|