Training in progress, step 1500
Browse files- model.safetensors +1 -1
- trainer_log.jsonl +10 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3554214752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:309116f056f48d209b69f317787df960f15fd5c99442f34498991e83593b6b9d
|
| 3 |
size 3554214752
|
trainer_log.jsonl
CHANGED
|
@@ -138,3 +138,13 @@
|
|
| 138 |
{"current_steps": 1380, "total_steps": 3235, "loss": 0.0105, "lr": 1.4188924930309232e-05, "epoch": 0.4266501777709074, "percentage": 42.66, "elapsed_time": "22:31:25", "remaining_time": "1 day, 6:16:34"}
|
| 139 |
{"current_steps": 1390, "total_steps": 3235, "loss": 0.011, "lr": 1.4090686371713403e-05, "epoch": 0.42974184572576907, "percentage": 42.97, "elapsed_time": "22:41:10", "remaining_time": "1 day, 6:06:44"}
|
| 140 |
{"current_steps": 1400, "total_steps": 3235, "loss": 0.0111, "lr": 1.3991971374118905e-05, "epoch": 0.4328335136806307, "percentage": 43.28, "elapsed_time": "22:50:53", "remaining_time": "1 day, 5:56:50"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
{"current_steps": 1380, "total_steps": 3235, "loss": 0.0105, "lr": 1.4188924930309232e-05, "epoch": 0.4266501777709074, "percentage": 42.66, "elapsed_time": "22:31:25", "remaining_time": "1 day, 6:16:34"}
|
| 139 |
{"current_steps": 1390, "total_steps": 3235, "loss": 0.011, "lr": 1.4090686371713403e-05, "epoch": 0.42974184572576907, "percentage": 42.97, "elapsed_time": "22:41:10", "remaining_time": "1 day, 6:06:44"}
|
| 140 |
{"current_steps": 1400, "total_steps": 3235, "loss": 0.0111, "lr": 1.3991971374118905e-05, "epoch": 0.4328335136806307, "percentage": 43.28, "elapsed_time": "22:50:53", "remaining_time": "1 day, 5:56:50"}
|
| 141 |
+
{"current_steps": 1410, "total_steps": 3235, "loss": 0.0112, "lr": 1.3892791434783252e-05, "epoch": 0.4359251816354924, "percentage": 43.59, "elapsed_time": "23:01:47", "remaining_time": "1 day, 5:48:28"}
|
| 142 |
+
{"current_steps": 1420, "total_steps": 3235, "loss": 0.011, "lr": 1.379315810511535e-05, "epoch": 0.439016849590354, "percentage": 43.89, "elapsed_time": "23:11:26", "remaining_time": "1 day, 5:38:29"}
|
| 143 |
+
{"current_steps": 1430, "total_steps": 3235, "loss": 0.0105, "lr": 1.3693082989330115e-05, "epoch": 0.44210851754521563, "percentage": 44.2, "elapsed_time": "23:21:09", "remaining_time": "1 day, 5:28:36"}
|
| 144 |
+
{"current_steps": 1440, "total_steps": 3235, "loss": 0.0103, "lr": 1.359257774309695e-05, "epoch": 0.4452001855000773, "percentage": 44.51, "elapsed_time": "23:30:46", "remaining_time": "1 day, 5:18:34"}
|
| 145 |
+
{"current_steps": 1450, "total_steps": 3235, "loss": 0.0104, "lr": 1.3491654072182194e-05, "epoch": 0.44829185345493894, "percentage": 44.82, "elapsed_time": "23:40:32", "remaining_time": "1 day, 5:08:43"}
|
| 146 |
+
{"current_steps": 1460, "total_steps": 3235, "loss": 0.0109, "lr": 1.33903237310858e-05, "epoch": 0.4513835214098006, "percentage": 45.13, "elapsed_time": "23:50:15", "remaining_time": "1 day, 4:58:50"}
|
| 147 |
+
{"current_steps": 1470, "total_steps": 3235, "loss": 0.0107, "lr": 1.3288598521672249e-05, "epoch": 0.45447518936466225, "percentage": 45.44, "elapsed_time": "1 day, 0:00:00", "remaining_time": "1 day, 4:48:59"}
|
| 148 |
+
{"current_steps": 1480, "total_steps": 3235, "loss": 0.0108, "lr": 1.3186490291796046e-05, "epoch": 0.4575668573195239, "percentage": 45.75, "elapsed_time": "1 day, 0:09:43", "remaining_time": "1 day, 4:39:06"}
|
| 149 |
+
{"current_steps": 1490, "total_steps": 3235, "loss": 0.0111, "lr": 1.3084010933921768e-05, "epoch": 0.46065852527438556, "percentage": 46.06, "elapsed_time": "1 day, 0:19:30", "remaining_time": "1 day, 4:29:17"}
|
| 150 |
+
{"current_steps": 1500, "total_steps": 3235, "loss": 0.0103, "lr": 1.298117238373898e-05, "epoch": 0.46375019322924715, "percentage": 46.37, "elapsed_time": "1 day, 0:29:14", "remaining_time": "1 day, 4:19:25"}
|