Training in progress, step 1790, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db850b67ea7c6e8dfc6fff996630ebca0373e266bdf9a7563852a21a31a27519
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce55cb1e263ea2d5fd546cea9912f84fea357b030bd8375beb2b59d7b235a405
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20abbe0709a08bb0d55ec9e4263a0c87b8cafe4e40118d178fa4cabe0e57626f
|
| 3 |
size 14645
|
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 sha256:46fd591e592870127c67addd89407fd20b2f87ea858f9f3f9640f6e32d088608
|
| 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": 0.
|
| 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,
|
|
@@ -1798,6 +1798,16 @@
|
|
| 1798 |
"mean_token_accuracy": 0.7559246391057968,
|
| 1799 |
"num_tokens": 8252919.0,
|
| 1800 |
"step": 1780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1801 |
}
|
| 1802 |
],
|
| 1803 |
"logging_steps": 10,
|
|
@@ -1817,7 +1827,7 @@
|
|
| 1817 |
"attributes": {}
|
| 1818 |
}
|
| 1819 |
},
|
| 1820 |
-
"total_flos": 3.
|
| 1821 |
"train_batch_size": 4,
|
| 1822 |
"trial_name": null,
|
| 1823 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3818666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1798 |
"mean_token_accuracy": 0.7559246391057968,
|
| 1799 |
"num_tokens": 8252919.0,
|
| 1800 |
"step": 1780
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"entropy": 1.029954968392849,
|
| 1804 |
+
"epoch": 0.3818666666666667,
|
| 1805 |
+
"grad_norm": 0.26953041553497314,
|
| 1806 |
+
"learning_rate": 9.350461613600449e-05,
|
| 1807 |
+
"loss": 1.1169189453125,
|
| 1808 |
+
"mean_token_accuracy": 0.746114706993103,
|
| 1809 |
+
"num_tokens": 8300355.0,
|
| 1810 |
+
"step": 1790
|
| 1811 |
}
|
| 1812 |
],
|
| 1813 |
"logging_steps": 10,
|
|
|
|
| 1827 |
"attributes": {}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
+
"total_flos": 3.94250599831849e+16,
|
| 1831 |
"train_batch_size": 4,
|
| 1832 |
"trial_name": null,
|
| 1833 |
"trial_params": null
|