step=4449 loss=5.5776
Browse files
checkpoints/ckpt_20260313_044616/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539dbd4e4bf6c029767112fca422d1a94b1fd9ea0542656aa7e5849a565dbb84
|
| 3 |
+
size 211933939
|
checkpoints/ckpt_20260313_044616/training_state.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 4449,
|
| 3 |
+
"best_loss": 5.577604631582896,
|
| 4 |
+
"last_save_ts": "2026-03-13T04:41:55.523212",
|
| 5 |
+
"tokens_seen": 109338624,
|
| 6 |
+
"completed_datasets": [],
|
| 7 |
+
"current_dataset": "data/train/000_wikipedia.parquet",
|
| 8 |
+
"current_dataset_tokens": 109338624
|
| 9 |
+
}
|