step=9191 loss=5.5331
Browse files- latest/model.pt +1 -1
- latest/training_state.json +7 -6
latest/model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 211933939
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e85cbd94687c37f2f99edbccc2eafa243fbea39e4dfc418497c70c2100bb361
|
| 3 |
size 211933939
|
latest/training_state.json
CHANGED
|
@@ -1,12 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"global_step":
|
| 3 |
"best_loss": 5.533148889740308,
|
| 4 |
-
"last_save_ts": "2026-03-13T05:
|
| 5 |
-
"tokens_seen":
|
| 6 |
"completed_datasets": [
|
| 7 |
"data/train/000_wikipedia.parquet",
|
| 8 |
-
"data/train/001_fineweb.parquet"
|
|
|
|
| 9 |
],
|
| 10 |
-
"current_dataset": "data/train/
|
| 11 |
-
"current_dataset_tokens":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"global_step": 9191,
|
| 3 |
"best_loss": 5.533148889740308,
|
| 4 |
+
"last_save_ts": "2026-03-13T05:17:13.475963",
|
| 5 |
+
"tokens_seen": 225878016,
|
| 6 |
"completed_datasets": [
|
| 7 |
"data/train/000_wikipedia.parquet",
|
| 8 |
+
"data/train/001_fineweb.parquet",
|
| 9 |
+
"data/train/002_stories.parquet"
|
| 10 |
],
|
| 11 |
+
"current_dataset": "data/train/003_oasst2.parquet",
|
| 12 |
+
"current_dataset_tokens": 25067520
|
| 13 |
}
|