step=3445 loss=5.8021
Browse files
checkpoints/ckpt_20260307_054702/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a4cf6e667cb30738203c9d7cc3c2306dd42550a83264a230d6e197f518f9c94
|
| 3 |
+
size 185473163
|
checkpoints/ckpt_20260307_054702/training_state.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 3445,
|
| 3 |
+
"best_loss": 5.8020863980054855,
|
| 4 |
+
"last_save_ts": null,
|
| 5 |
+
"tokens_seen": 84664320,
|
| 6 |
+
"completed_datasets": [],
|
| 7 |
+
"current_dataset": "data/train/000_wikipedia.parquet",
|
| 8 |
+
"current_dataset_tokens": 84664320
|
| 9 |
+
}
|