Training in progress, step 1000, 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 sha256:4a34672ff03787ba1c0fcd389d1527a0b90c4dc3bf28179edd43912d1e9c9682
|
| 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 sha256:254526096e99b96d838a3e636e9c75f0cf7ee92fe3f56bf68898101abf85fe09
|
| 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 sha256:53d1532a1a6c7fc2b097e5ecb1378517edd8100b754ecee6c6dbc0e0293db021
|
| 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,
|
|
@@ -1790,6 +1790,24 @@
|
|
| 1790 |
"mean_token_accuracy": 0.6438402742147445,
|
| 1791 |
"num_tokens": 3610243.0,
|
| 1792 |
"step": 990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1793 |
}
|
| 1794 |
],
|
| 1795 |
"logging_steps": 5,
|
|
@@ -1809,7 +1827,7 @@
|
|
| 1809 |
"attributes": {}
|
| 1810 |
}
|
| 1811 |
},
|
| 1812 |
-
"total_flos": 1.
|
| 1813 |
"train_batch_size": 4,
|
| 1814 |
"trial_name": null,
|
| 1815 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1790 |
"mean_token_accuracy": 0.6438402742147445,
|
| 1791 |
"num_tokens": 3610243.0,
|
| 1792 |
"step": 990
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 7.653846153846154,
|
| 1796 |
+
"grad_norm": 0.0,
|
| 1797 |
+
"learning_rate": 4.503e-05,
|
| 1798 |
+
"loss": 1.7926,
|
| 1799 |
+
"mean_token_accuracy": 0.6445695728063583,
|
| 1800 |
+
"num_tokens": 3627858.0,
|
| 1801 |
+
"step": 995
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.6923076923076925,
|
| 1805 |
+
"grad_norm": 0.0,
|
| 1806 |
+
"learning_rate": 4.5005e-05,
|
| 1807 |
+
"loss": 1.679,
|
| 1808 |
+
"mean_token_accuracy": 0.6652253627777099,
|
| 1809 |
+
"num_tokens": 3646594.0,
|
| 1810 |
+
"step": 1000
|
| 1811 |
}
|
| 1812 |
],
|
| 1813 |
"logging_steps": 5,
|
|
|
|
| 1827 |
"attributes": {}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
+
"total_flos": 1.84854651531264e+17,
|
| 1831 |
"train_batch_size": 4,
|
| 1832 |
"trial_name": null,
|
| 1833 |
"trial_params": null
|