step=6777 loss=4.9622
Browse files
checkpoints/ckpt_20260304_110925/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ded3e9a9f2cb8f74b45fa5210550289b8e76ae54f20200073ec788659127c90f
|
| 3 |
+
size 193606235
|
checkpoints/ckpt_20260304_110925/training_state.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 6773,
|
| 3 |
+
"best_loss": 4.962232932448387,
|
| 4 |
+
"last_save_ts": null,
|
| 5 |
+
"tokens_seen": 110968832,
|
| 6 |
+
"completed_datasets": [],
|
| 7 |
+
"current_dataset": "data/train/000_wikitext2.parquet",
|
| 8 |
+
"current_dataset_tokens": 110968832
|
| 9 |
+
}
|