Training in progress, step 400
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 sha256:08faa1a852860ee55b01d090ee38df73f3d1520897379244d02cec76db5423f1
|
| 3 |
size 3554214752
|
trainer_log.jsonl
CHANGED
|
@@ -28,3 +28,13 @@
|
|
| 28 |
{"current_steps": 280, "total_steps": 3235, "loss": 0.0212, "lr": 1.7222222222222224e-05, "epoch": 0.08656670273612614, "percentage": 8.66, "elapsed_time": "4:34:14", "remaining_time": "2 days, 0:14:16"}
|
| 29 |
{"current_steps": 290, "total_steps": 3235, "loss": 0.0215, "lr": 1.7839506172839506e-05, "epoch": 0.08965837069098778, "percentage": 8.96, "elapsed_time": "4:43:57", "remaining_time": "2 days, 0:03:40"}
|
| 30 |
{"current_steps": 300, "total_steps": 3235, "loss": 0.021, "lr": 1.8456790123456792e-05, "epoch": 0.09275003864584944, "percentage": 9.27, "elapsed_time": "4:53:40", "remaining_time": "1 day, 23:53:08"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
{"current_steps": 280, "total_steps": 3235, "loss": 0.0212, "lr": 1.7222222222222224e-05, "epoch": 0.08656670273612614, "percentage": 8.66, "elapsed_time": "4:34:14", "remaining_time": "2 days, 0:14:16"}
|
| 29 |
{"current_steps": 290, "total_steps": 3235, "loss": 0.0215, "lr": 1.7839506172839506e-05, "epoch": 0.08965837069098778, "percentage": 8.96, "elapsed_time": "4:43:57", "remaining_time": "2 days, 0:03:40"}
|
| 30 |
{"current_steps": 300, "total_steps": 3235, "loss": 0.021, "lr": 1.8456790123456792e-05, "epoch": 0.09275003864584944, "percentage": 9.27, "elapsed_time": "4:53:40", "remaining_time": "1 day, 23:53:08"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 3235, "loss": 0.0207, "lr": 1.9074074074074075e-05, "epoch": 0.09584170660071108, "percentage": 9.58, "elapsed_time": "5:04:32", "remaining_time": "1 day, 23:53:34"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 3235, "loss": 0.02, "lr": 1.969135802469136e-05, "epoch": 0.09893337455557273, "percentage": 9.89, "elapsed_time": "5:14:10", "remaining_time": "1 day, 23:41:55"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 3235, "loss": 0.0195, "lr": 1.99998544124312e-05, "epoch": 0.10202504251043439, "percentage": 10.2, "elapsed_time": "5:23:46", "remaining_time": "1 day, 23:30:15"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 3235, "loss": 0.0201, "lr": 1.9998689737315552e-05, "epoch": 0.10511671046529603, "percentage": 10.51, "elapsed_time": "5:33:32", "remaining_time": "1 day, 23:20:00"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 3235, "loss": 0.0197, "lr": 1.9996360522733042e-05, "epoch": 0.10820837842015768, "percentage": 10.82, "elapsed_time": "5:43:14", "remaining_time": "1 day, 23:09:15"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 3235, "loss": 0.0196, "lr": 1.9992867039965446e-05, "epoch": 0.11130004637501932, "percentage": 11.13, "elapsed_time": "5:52:55", "remaining_time": "1 day, 22:58:27"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 3235, "loss": 0.0179, "lr": 1.9988209695895934e-05, "epoch": 0.11439171432988098, "percentage": 11.44, "elapsed_time": "6:02:40", "remaining_time": "1 day, 22:48:13"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 3235, "loss": 0.0181, "lr": 1.9982389032961674e-05, "epoch": 0.11748338228474262, "percentage": 11.75, "elapsed_time": "6:12:12", "remaining_time": "1 day, 22:36:29"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 3235, "loss": 0.0188, "lr": 1.9975405729090672e-05, "epoch": 0.12057505023960427, "percentage": 12.06, "elapsed_time": "6:21:57", "remaining_time": "1 day, 22:26:17"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 3235, "loss": 0.0183, "lr": 1.9967260597622783e-05, "epoch": 0.12366671819446591, "percentage": 12.36, "elapsed_time": "6:31:35", "remaining_time": "1 day, 22:15:24"}
|