3N3G commited on
Commit
5728b80
·
verified ·
1 Parent(s): 870d82b

Training in progress, step 112

Browse files
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5696b0909841c30ce657da7fef89d416fda37a2d1d0a8e66831a5ea7676d6e4
3
  size 4969539560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47b82aa2abc24774e65bf3c840b73254af400c018b54a4b74076c10b7aa50f1
3
  size 4969539560
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a7223ea8f99f7b799b24686be78454f9f72e8d03fef9f83c56d83584086be14
3
  size 1912795688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3948e1712d66e4846b20e1f82e841d2b592341e95b95f7284d25901e27823131
3
  size 1912795688
trainer_log.jsonl CHANGED
@@ -577,3 +577,37 @@
577
  {"current_steps": 95, "total_steps": 400, "loss": 0.7533, "lr": 9.509529358847655e-08, "epoch": 23.87272727272727, "percentage": 23.75, "elapsed_time": "0:11:15", "remaining_time": "0:36:07"}
578
  {"current_steps": 96, "total_steps": 400, "loss": 0.8112, "lr": 9.491548749301997e-08, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:18", "remaining_time": "0:35:48"}
579
  {"current_steps": 96, "total_steps": 400, "eval_loss": 0.7388671040534973, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:19", "remaining_time": "0:35:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
577
  {"current_steps": 95, "total_steps": 400, "loss": 0.7533, "lr": 9.509529358847655e-08, "epoch": 23.87272727272727, "percentage": 23.75, "elapsed_time": "0:11:15", "remaining_time": "0:36:07"}
578
  {"current_steps": 96, "total_steps": 400, "loss": 0.8112, "lr": 9.491548749301997e-08, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:18", "remaining_time": "0:35:48"}
579
  {"current_steps": 96, "total_steps": 400, "eval_loss": 0.7388671040534973, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:19", "remaining_time": "0:35:50"}
580
+ {"current_steps": 97, "total_steps": 400, "loss": 0.779, "lr": 9.473264167865172e-08, "epoch": 24.29090909090909, "percentage": 24.25, "elapsed_time": "0:11:44", "remaining_time": "0:36:41"}
581
+ {"current_steps": 98, "total_steps": 400, "loss": 0.7427, "lr": 9.454677006978843e-08, "epoch": 24.581818181818182, "percentage": 24.5, "elapsed_time": "0:11:51", "remaining_time": "0:36:32"}
582
+ {"current_steps": 99, "total_steps": 400, "loss": 0.7749, "lr": 9.435788682127281e-08, "epoch": 24.87272727272727, "percentage": 24.75, "elapsed_time": "0:11:58", "remaining_time": "0:36:24"}
583
+ {"current_steps": 100, "total_steps": 400, "loss": 0.8413, "lr": 9.416600631729548e-08, "epoch": 25.0, "percentage": 25.0, "elapsed_time": "0:12:01", "remaining_time": "0:36:03"}
584
+ {"current_steps": 101, "total_steps": 400, "loss": 0.7987, "lr": 9.397114317029974e-08, "epoch": 25.29090909090909, "percentage": 25.25, "elapsed_time": "0:12:08", "remaining_time": "0:35:56"}
585
+ {"current_steps": 102, "total_steps": 400, "loss": 0.7579, "lr": 9.377331221986867e-08, "epoch": 25.581818181818182, "percentage": 25.5, "elapsed_time": "0:12:14", "remaining_time": "0:35:47"}
586
+ {"current_steps": 103, "total_steps": 400, "loss": 0.7138, "lr": 9.357252853159505e-08, "epoch": 25.87272727272727, "percentage": 25.75, "elapsed_time": "0:12:21", "remaining_time": "0:35:38"}
587
+ {"current_steps": 104, "total_steps": 400, "loss": 0.8143, "lr": 9.336880739593415e-08, "epoch": 26.0, "percentage": 26.0, "elapsed_time": "0:12:24", "remaining_time": "0:35:20"}
588
+ {"current_steps": 105, "total_steps": 400, "loss": 0.7595, "lr": 9.316216432703917e-08, "epoch": 26.29090909090909, "percentage": 26.25, "elapsed_time": "0:12:31", "remaining_time": "0:35:12"}
589
+ {"current_steps": 106, "total_steps": 400, "loss": 0.6892, "lr": 9.295261506157986e-08, "epoch": 26.581818181818182, "percentage": 26.5, "elapsed_time": "0:12:38", "remaining_time": "0:35:03"}
590
+ {"current_steps": 107, "total_steps": 400, "loss": 0.7828, "lr": 9.274017555754408e-08, "epoch": 26.87272727272727, "percentage": 26.75, "elapsed_time": "0:12:44", "remaining_time": "0:34:54"}
591
+ {"current_steps": 108, "total_steps": 400, "loss": 0.8267, "lr": 9.252486199302256e-08, "epoch": 27.0, "percentage": 27.0, "elapsed_time": "0:12:48", "remaining_time": "0:34:37"}
592
+ {"current_steps": 109, "total_steps": 400, "loss": 0.7837, "lr": 9.230669076497686e-08, "epoch": 27.29090909090909, "percentage": 27.25, "elapsed_time": "0:12:55", "remaining_time": "0:34:29"}
593
+ {"current_steps": 110, "total_steps": 400, "loss": 0.7629, "lr": 9.20856784879907e-08, "epoch": 27.581818181818182, "percentage": 27.5, "elapsed_time": "0:13:01", "remaining_time": "0:34:20"}
594
+ {"current_steps": 111, "total_steps": 400, "loss": 0.732, "lr": 9.186184199300463e-08, "epoch": 27.87272727272727, "percentage": 27.75, "elapsed_time": "0:13:09", "remaining_time": "0:34:14"}
595
+ {"current_steps": 112, "total_steps": 400, "loss": 0.708, "lr": 9.163519832603437e-08, "epoch": 28.0, "percentage": 28.0, "elapsed_time": "0:13:11", "remaining_time": "0:33:56"}
596
+ {"current_steps": 112, "total_steps": 400, "eval_loss": 0.7153984904289246, "epoch": 28.0, "percentage": 28.0, "elapsed_time": "0:13:12", "remaining_time": "0:33:57"}
597
+ {"current_steps": 113, "total_steps": 400, "loss": 0.7923, "lr": 9.140576474687262e-08, "epoch": 28.29090909090909, "percentage": 28.25, "elapsed_time": "0:13:41", "remaining_time": "0:34:47"}
598
+ {"current_steps": 114, "total_steps": 400, "loss": 0.6965, "lr": 9.117355872777476e-08, "epoch": 28.581818181818182, "percentage": 28.5, "elapsed_time": "0:13:48", "remaining_time": "0:34:39"}
599
+ {"current_steps": 115, "total_steps": 400, "loss": 0.7564, "lr": 9.093859795212817e-08, "epoch": 28.87272727272727, "percentage": 28.75, "elapsed_time": "0:13:55", "remaining_time": "0:34:30"}
600
+ {"current_steps": 116, "total_steps": 400, "loss": 0.7325, "lr": 9.070090031310558e-08, "epoch": 29.0, "percentage": 29.0, "elapsed_time": "0:13:58", "remaining_time": "0:34:13"}
601
+ {"current_steps": 117, "total_steps": 400, "loss": 0.6957, "lr": 9.046048391230248e-08, "epoch": 29.29090909090909, "percentage": 29.25, "elapsed_time": "0:14:05", "remaining_time": "0:34:06"}
602
+ {"current_steps": 118, "total_steps": 400, "loss": 0.8011, "lr": 9.021736705835861e-08, "epoch": 29.581818181818182, "percentage": 29.5, "elapsed_time": "0:14:13", "remaining_time": "0:33:59"}
603
+ {"current_steps": 119, "total_steps": 400, "loss": 0.7767, "lr": 8.997156826556369e-08, "epoch": 29.87272727272727, "percentage": 29.75, "elapsed_time": "0:14:19", "remaining_time": "0:33:50"}
604
+ {"current_steps": 120, "total_steps": 400, "loss": 0.6864, "lr": 8.97231062524474e-08, "epoch": 30.0, "percentage": 30.0, "elapsed_time": "0:14:23", "remaining_time": "0:33:33"}
605
+ {"current_steps": 121, "total_steps": 400, "loss": 0.757, "lr": 8.9471999940354e-08, "epoch": 30.29090909090909, "percentage": 30.25, "elapsed_time": "0:14:30", "remaining_time": "0:33:26"}
606
+ {"current_steps": 122, "total_steps": 400, "loss": 0.7184, "lr": 8.921826845200139e-08, "epoch": 30.581818181818182, "percentage": 30.5, "elapsed_time": "0:14:37", "remaining_time": "0:33:19"}
607
+ {"current_steps": 123, "total_steps": 400, "loss": 0.8074, "lr": 8.896193111002475e-08, "epoch": 30.87272727272727, "percentage": 30.75, "elapsed_time": "0:14:44", "remaining_time": "0:33:10"}
608
+ {"current_steps": 124, "total_steps": 400, "loss": 0.666, "lr": 8.87030074355051e-08, "epoch": 31.0, "percentage": 31.0, "elapsed_time": "0:14:47", "remaining_time": "0:32:54"}
609
+ {"current_steps": 125, "total_steps": 400, "loss": 0.7109, "lr": 8.844151714648274e-08, "epoch": 31.29090909090909, "percentage": 31.25, "elapsed_time": "0:14:54", "remaining_time": "0:32:47"}
610
+ {"current_steps": 126, "total_steps": 400, "loss": 0.7848, "lr": 8.817748015645558e-08, "epoch": 31.581818181818182, "percentage": 31.5, "elapsed_time": "0:15:00", "remaining_time": "0:32:39"}
611
+ {"current_steps": 127, "total_steps": 400, "loss": 0.7756, "lr": 8.791091657286267e-08, "epoch": 31.87272727272727, "percentage": 31.75, "elapsed_time": "0:15:08", "remaining_time": "0:32:31"}
612
+ {"current_steps": 128, "total_steps": 400, "loss": 0.6471, "lr": 8.764184669555293e-08, "epoch": 32.0, "percentage": 32.0, "elapsed_time": "0:15:10", "remaining_time": "0:32:15"}
613
+ {"current_steps": 128, "total_steps": 400, "eval_loss": 0.7097088694572449, "epoch": 32.0, "percentage": 32.0, "elapsed_time": "0:15:11", "remaining_time": "0:32:17"}