Training in progress, step 256
Browse files- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- trainer_log.jsonl +34 -0
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4969539560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53050572e6d32d87f418fb11be50520f613885e4b0708517cfa6e2215b947ed7
|
| 3 |
size 4969539560
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1912795688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f7432c6c2d81986a5ed02165a3855e35a452015578c47719de803e320276e4e
|
| 3 |
size 1912795688
|
trainer_log.jsonl
CHANGED
|
@@ -730,3 +730,37 @@
|
|
| 730 |
{"current_steps": 239, "total_steps": 400, "loss": 0.6136, "lr": 4.7960449073189604e-08, "epoch": 59.872727272727275, "percentage": 59.75, "elapsed_time": "0:29:00", "remaining_time": "0:19:32"}
|
| 731 |
{"current_steps": 240, "total_steps": 400, "loss": 0.7364, "lr": 4.75728577362695e-08, "epoch": 60.0, "percentage": 60.0, "elapsed_time": "0:29:03", "remaining_time": "0:19:22"}
|
| 732 |
{"current_steps": 240, "total_steps": 400, "eval_loss": 0.6488688588142395, "epoch": 60.0, "percentage": 60.0, "elapsed_time": "0:29:04", "remaining_time": "0:19:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 730 |
{"current_steps": 239, "total_steps": 400, "loss": 0.6136, "lr": 4.7960449073189604e-08, "epoch": 59.872727272727275, "percentage": 59.75, "elapsed_time": "0:29:00", "remaining_time": "0:19:32"}
|
| 731 |
{"current_steps": 240, "total_steps": 400, "loss": 0.7364, "lr": 4.75728577362695e-08, "epoch": 60.0, "percentage": 60.0, "elapsed_time": "0:29:03", "remaining_time": "0:19:22"}
|
| 732 |
{"current_steps": 240, "total_steps": 400, "eval_loss": 0.6488688588142395, "epoch": 60.0, "percentage": 60.0, "elapsed_time": "0:29:04", "remaining_time": "0:19:22"}
|
| 733 |
+
{"current_steps": 241, "total_steps": 400, "loss": 0.7386, "lr": 4.718583200498813e-08, "epoch": 60.29090909090909, "percentage": 60.25, "elapsed_time": "0:29:30", "remaining_time": "0:19:28"}
|
| 734 |
+
{"current_steps": 242, "total_steps": 400, "loss": 0.6255, "lr": 4.6799401352853365e-08, "epoch": 60.58181818181818, "percentage": 60.5, "elapsed_time": "0:29:37", "remaining_time": "0:19:20"}
|
| 735 |
+
{"current_steps": 243, "total_steps": 400, "loss": 0.6834, "lr": 4.641359520805548e-08, "epoch": 60.872727272727275, "percentage": 60.75, "elapsed_time": "0:29:43", "remaining_time": "0:19:12"}
|
| 736 |
+
{"current_steps": 244, "total_steps": 400, "loss": 0.5903, "lr": 4.6028442951226135e-08, "epoch": 61.0, "percentage": 61.0, "elapsed_time": "0:29:47", "remaining_time": "0:19:02"}
|
| 737 |
+
{"current_steps": 245, "total_steps": 400, "loss": 0.5871, "lr": 4.564397391320084e-08, "epoch": 61.29090909090909, "percentage": 61.25, "elapsed_time": "0:29:54", "remaining_time": "0:18:54"}
|
| 738 |
+
{"current_steps": 246, "total_steps": 400, "loss": 0.6913, "lr": 4.526021737278537e-08, "epoch": 61.58181818181818, "percentage": 61.5, "elapsed_time": "0:30:00", "remaining_time": "0:18:47"}
|
| 739 |
+
{"current_steps": 247, "total_steps": 400, "loss": 0.7115, "lr": 4.4877202554526084e-08, "epoch": 61.872727272727275, "percentage": 61.75, "elapsed_time": "0:30:07", "remaining_time": "0:18:39"}
|
| 740 |
+
{"current_steps": 248, "total_steps": 400, "loss": 0.687, "lr": 4.449495862648427e-08, "epoch": 62.0, "percentage": 62.0, "elapsed_time": "0:30:10", "remaining_time": "0:18:29"}
|
| 741 |
+
{"current_steps": 249, "total_steps": 400, "loss": 0.6901, "lr": 4.4113514698014955e-08, "epoch": 62.29090909090909, "percentage": 62.25, "elapsed_time": "0:30:17", "remaining_time": "0:18:22"}
|
| 742 |
+
{"current_steps": 250, "total_steps": 400, "loss": 0.631, "lr": 4.373289981755013e-08, "epoch": 62.58181818181818, "percentage": 62.5, "elapsed_time": "0:30:24", "remaining_time": "0:18:14"}
|
| 743 |
+
{"current_steps": 251, "total_steps": 400, "loss": 0.6351, "lr": 4.335314297038656e-08, "epoch": 62.872727272727275, "percentage": 62.75, "elapsed_time": "0:30:30", "remaining_time": "0:18:06"}
|
| 744 |
+
{"current_steps": 252, "total_steps": 400, "loss": 0.7212, "lr": 4.297427307647844e-08, "epoch": 63.0, "percentage": 63.0, "elapsed_time": "0:30:33", "remaining_time": "0:17:56"}
|
| 745 |
+
{"current_steps": 253, "total_steps": 400, "loss": 0.629, "lr": 4.2596318988235035e-08, "epoch": 63.29090909090909, "percentage": 63.25, "elapsed_time": "0:30:40", "remaining_time": "0:17:49"}
|
| 746 |
+
{"current_steps": 254, "total_steps": 400, "loss": 0.6565, "lr": 4.2219309488323486e-08, "epoch": 63.58181818181818, "percentage": 63.5, "elapsed_time": "0:30:47", "remaining_time": "0:17:41"}
|
| 747 |
+
{"current_steps": 255, "total_steps": 400, "loss": 0.6644, "lr": 4.184327328747685e-08, "epoch": 63.872727272727275, "percentage": 63.75, "elapsed_time": "0:30:54", "remaining_time": "0:17:34"}
|
| 748 |
+
{"current_steps": 256, "total_steps": 400, "loss": 0.7706, "lr": 4.1468239022307716e-08, "epoch": 64.0, "percentage": 64.0, "elapsed_time": "0:30:56", "remaining_time": "0:17:24"}
|
| 749 |
+
{"current_steps": 256, "total_steps": 400, "eval_loss": 0.6460027694702148, "epoch": 64.0, "percentage": 64.0, "elapsed_time": "0:30:57", "remaining_time": "0:17:24"}
|
| 750 |
+
{"current_steps": 257, "total_steps": 400, "loss": 0.5848, "lr": 4.1094235253127375e-08, "epoch": 64.2909090909091, "percentage": 64.25, "elapsed_time": "0:31:28", "remaining_time": "0:17:30"}
|
| 751 |
+
{"current_steps": 258, "total_steps": 400, "loss": 0.6438, "lr": 4.072129046177086e-08, "epoch": 64.58181818181818, "percentage": 64.5, "elapsed_time": "0:31:34", "remaining_time": "0:17:22"}
|
| 752 |
+
{"current_steps": 259, "total_steps": 400, "loss": 0.7825, "lr": 4.034943304942796e-08, "epoch": 64.87272727272727, "percentage": 64.75, "elapsed_time": "0:31:41", "remaining_time": "0:17:15"}
|
| 753 |
+
{"current_steps": 260, "total_steps": 400, "loss": 0.7003, "lr": 3.997869133448031e-08, "epoch": 65.0, "percentage": 65.0, "elapsed_time": "0:31:44", "remaining_time": "0:17:05"}
|
| 754 |
+
{"current_steps": 261, "total_steps": 400, "loss": 0.6723, "lr": 3.960909355034491e-08, "epoch": 65.2909090909091, "percentage": 65.25, "elapsed_time": "0:31:51", "remaining_time": "0:16:58"}
|
| 755 |
+
{"current_steps": 262, "total_steps": 400, "loss": 0.6778, "lr": 3.924066784332396e-08, "epoch": 65.58181818181818, "percentage": 65.5, "elapsed_time": "0:31:58", "remaining_time": "0:16:50"}
|
| 756 |
+
{"current_steps": 263, "total_steps": 400, "loss": 0.6196, "lr": 3.8873442270461487e-08, "epoch": 65.87272727272727, "percentage": 65.75, "elapsed_time": "0:32:05", "remaining_time": "0:16:43"}
|
| 757 |
+
{"current_steps": 264, "total_steps": 400, "loss": 0.7125, "lr": 3.850744479740663e-08, "epoch": 66.0, "percentage": 66.0, "elapsed_time": "0:32:08", "remaining_time": "0:16:33"}
|
| 758 |
+
{"current_steps": 265, "total_steps": 400, "loss": 0.6958, "lr": 3.814270329628395e-08, "epoch": 66.2909090909091, "percentage": 66.25, "elapsed_time": "0:32:15", "remaining_time": "0:16:26"}
|
| 759 |
+
{"current_steps": 266, "total_steps": 400, "loss": 0.6089, "lr": 3.777924554357096e-08, "epoch": 66.58181818181818, "percentage": 66.5, "elapsed_time": "0:32:22", "remaining_time": "0:16:18"}
|
| 760 |
+
{"current_steps": 267, "total_steps": 400, "loss": 0.6794, "lr": 3.7417099217982684e-08, "epoch": 66.87272727272727, "percentage": 66.75, "elapsed_time": "0:32:29", "remaining_time": "0:16:11"}
|
| 761 |
+
{"current_steps": 268, "total_steps": 400, "loss": 0.6845, "lr": 3.7056291898363926e-08, "epoch": 67.0, "percentage": 67.0, "elapsed_time": "0:32:32", "remaining_time": "0:16:01"}
|
| 762 |
+
{"current_steps": 269, "total_steps": 400, "loss": 0.6726, "lr": 3.669685106158899e-08, "epoch": 67.2909090909091, "percentage": 67.25, "elapsed_time": "0:32:39", "remaining_time": "0:15:54"}
|
| 763 |
+
{"current_steps": 270, "total_steps": 400, "loss": 0.6597, "lr": 3.633880408046926e-08, "epoch": 67.58181818181818, "percentage": 67.5, "elapsed_time": "0:32:45", "remaining_time": "0:15:46"}
|
| 764 |
+
{"current_steps": 271, "total_steps": 400, "loss": 0.5967, "lr": 3.598217822166854e-08, "epoch": 67.87272727272727, "percentage": 67.75, "elapsed_time": "0:32:53", "remaining_time": "0:15:39"}
|
| 765 |
+
{"current_steps": 272, "total_steps": 400, "loss": 0.7777, "lr": 3.5627000643626705e-08, "epoch": 68.0, "percentage": 68.0, "elapsed_time": "0:32:56", "remaining_time": "0:15:30"}
|
| 766 |
+
{"current_steps": 272, "total_steps": 400, "eval_loss": 0.6440867185592651, "epoch": 68.0, "percentage": 68.0, "elapsed_time": "0:32:57", "remaining_time": "0:15:30"}
|