Training in progress, step 1810, 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 sha256:7d5c5c75b6a428f6efda135271a92a5a1f4a68cda7cd32df21d8d34f8b5de4cd
|
| 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 sha256:658626deef1d83bddc1b185e6f1766cb44e81213db1eab78802bf96994fe7543
|
| 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:d67075d20afbf5a016a52f76b259b2a5e591e87dcd548f40d73e0c86f8a70711
|
| 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 sha256:7502f1bfbc6986292b05274178f485a7ad444610331bfb3c33a5847fca767785
|
| 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,
|
|
@@ -1818,6 +1818,16 @@
|
|
| 1818 |
"mean_token_accuracy": 0.7640544638037682,
|
| 1819 |
"num_tokens": 8346150.0,
|
| 1820 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1821 |
}
|
| 1822 |
],
|
| 1823 |
"logging_steps": 10,
|
|
@@ -1837,7 +1847,7 @@
|
|
| 1837 |
"attributes": {}
|
| 1838 |
}
|
| 1839 |
},
|
| 1840 |
-
"total_flos": 3.
|
| 1841 |
"train_batch_size": 4,
|
| 1842 |
"trial_name": null,
|
| 1843 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.38613333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1818 |
"mean_token_accuracy": 0.7640544638037682,
|
| 1819 |
"num_tokens": 8346150.0,
|
| 1820 |
"step": 1800
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"entropy": 0.960440730303526,
|
| 1824 |
+
"epoch": 0.38613333333333333,
|
| 1825 |
+
"grad_norm": 0.2441101223230362,
|
| 1826 |
+
"learning_rate": 9.333296506763505e-05,
|
| 1827 |
+
"loss": 1.059675121307373,
|
| 1828 |
+
"mean_token_accuracy": 0.7603183135390281,
|
| 1829 |
+
"num_tokens": 8393408.0,
|
| 1830 |
+
"step": 1810
|
| 1831 |
}
|
| 1832 |
],
|
| 1833 |
"logging_steps": 10,
|
|
|
|
| 1847 |
"attributes": {}
|
| 1848 |
}
|
| 1849 |
},
|
| 1850 |
+
"total_flos": 3.988529611626394e+16,
|
| 1851 |
"train_batch_size": 4,
|
| 1852 |
"trial_name": null,
|
| 1853 |
"trial_params": null
|