step=6966 loss=4.8346
Browse files
checkpoints/ckpt_20260305_063507/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fd61b137f953a72c3f731883f335c3d97b1dd172addbe569a339f5e00e583bd
|
| 3 |
+
size 184272651
|
checkpoints/ckpt_20260305_063507/training_state.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 6966,
|
| 3 |
+
"best_loss": 4.834585823118687,
|
| 4 |
+
"last_save_ts": "2026-03-05T06:23:40.911586",
|
| 5 |
+
"tokens_seen": 114130944,
|
| 6 |
+
"completed_datasets": [],
|
| 7 |
+
"current_dataset": "data/train/000_wikitext2.parquet",
|
| 8 |
+
"current_dataset_tokens": 114130944
|
| 9 |
+
}
|