Training in progress, step 1010, 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:cf2d1c44bfaf15c37a3a9ff5effa1005e8e4ed901cdddaab409b9e62f4eae3ce
|
| 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:df294d6a059b1a124e40c4b6587d7fd486d62837e7d97ddee2457d4fbe0c0fd4
|
| 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 sha256:6235fb2b90c58ebb53ab772ea05b0c574b9ce485ef1733c54336da3dd6db2add
|
| 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,
|
|
@@ -1808,6 +1808,24 @@
|
|
| 1808 |
"mean_token_accuracy": 0.6652253627777099,
|
| 1809 |
"num_tokens": 3646594.0,
|
| 1810 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1811 |
}
|
| 1812 |
],
|
| 1813 |
"logging_steps": 5,
|
|
@@ -1827,7 +1845,7 @@
|
|
| 1827 |
"attributes": {}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
-
"total_flos": 1.
|
| 1831 |
"train_batch_size": 4,
|
| 1832 |
"trial_name": null,
|
| 1833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1808 |
"mean_token_accuracy": 0.6652253627777099,
|
| 1809 |
"num_tokens": 3646594.0,
|
| 1810 |
"step": 1000
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 7.730769230769231,
|
| 1814 |
+
"grad_norm": 0.0,
|
| 1815 |
+
"learning_rate": 4.498e-05,
|
| 1816 |
+
"loss": 1.8077,
|
| 1817 |
+
"mean_token_accuracy": 0.6364081174135208,
|
| 1818 |
+
"num_tokens": 3664583.0,
|
| 1819 |
+
"step": 1005
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 7.769230769230769,
|
| 1823 |
+
"grad_norm": 0.0,
|
| 1824 |
+
"learning_rate": 4.4955000000000006e-05,
|
| 1825 |
+
"loss": 1.7589,
|
| 1826 |
+
"mean_token_accuracy": 0.6449447929859161,
|
| 1827 |
+
"num_tokens": 3682471.0,
|
| 1828 |
+
"step": 1010
|
| 1829 |
}
|
| 1830 |
],
|
| 1831 |
"logging_steps": 5,
|
|
|
|
| 1845 |
"attributes": {}
|
| 1846 |
}
|
| 1847 |
},
|
| 1848 |
+
"total_flos": 1.866790239215616e+17,
|
| 1849 |
"train_batch_size": 4,
|
| 1850 |
"trial_name": null,
|
| 1851 |
"trial_params": null
|