penfever commited on
Commit
74929a9
·
verified ·
1 Parent(s): fe1bfe4

Training in progress, step 2600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9f6976626ee793388b3c152c52a7f85152c9b758be988ace11b51341b12740
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed736d6f7c92193fa39105250ee8628785bbfa9fd8a82000f32ef4b4a2c8fa57
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba91d5c2836f44d84c61c34be3bfe7a1738d833f6e5b60da4c9ed0b8afcd1e04
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee4905203c42052bb46534282464873266a6bb7f2fc7b489f148233f0399430
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c93c68bc389a6a48442592e60e4dbeceea73ff32fb976591cbc1c94e02655672
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ade83710eaf6411840e40f7b437f965db33c59317c59ba5b55397aa58e6b6c5
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8173e150f6a9f91c231ba85abc04eedc0e4b84b0eb31430974c8034e15430d9
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06548d1dbed959b57a2ac7c173fa275ed9a5f8247ffec1ba599344b63db3a668
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -478,3 +478,46 @@
478
  {"current_steps": 2390, "total_steps": 3850, "loss": 0.2029, "lr": 1.5126380752688934e-05, "epoch": 4.345768880800728, "percentage": 62.08, "elapsed_time": "15:59:07", "remaining_time": "9:45:54"}
479
  {"current_steps": 2395, "total_steps": 3850, "loss": 0.2009, "lr": 1.503849777777543e-05, "epoch": 4.3548680618744315, "percentage": 62.21, "elapsed_time": "16:01:10", "remaining_time": "9:43:55"}
480
  {"current_steps": 2400, "total_steps": 3850, "loss": 0.2047, "lr": 1.4950716766593872e-05, "epoch": 4.363967242948135, "percentage": 62.34, "elapsed_time": "16:03:11", "remaining_time": "9:41:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
478
  {"current_steps": 2390, "total_steps": 3850, "loss": 0.2029, "lr": 1.5126380752688934e-05, "epoch": 4.345768880800728, "percentage": 62.08, "elapsed_time": "15:59:07", "remaining_time": "9:45:54"}
479
  {"current_steps": 2395, "total_steps": 3850, "loss": 0.2009, "lr": 1.503849777777543e-05, "epoch": 4.3548680618744315, "percentage": 62.21, "elapsed_time": "16:01:10", "remaining_time": "9:43:55"}
480
  {"current_steps": 2400, "total_steps": 3850, "loss": 0.2047, "lr": 1.4950716766593872e-05, "epoch": 4.363967242948135, "percentage": 62.34, "elapsed_time": "16:03:11", "remaining_time": "9:41:55"}
481
+ {"current_steps": 2405, "total_steps": 3850, "loss": 0.2024, "lr": 1.4863039523130054e-05, "epoch": 4.373066424021838, "percentage": 62.47, "elapsed_time": "16:06:42", "remaining_time": "9:40:49"}
482
+ {"current_steps": 2410, "total_steps": 3850, "loss": 0.2137, "lr": 1.4775467849237234e-05, "epoch": 4.382165605095541, "percentage": 62.6, "elapsed_time": "16:08:26", "remaining_time": "9:38:39"}
483
+ {"current_steps": 2415, "total_steps": 3850, "loss": 0.2165, "lr": 1.468800354459912e-05, "epoch": 4.391264786169245, "percentage": 62.73, "elapsed_time": "16:10:29", "remaining_time": "9:36:40"}
484
+ {"current_steps": 2420, "total_steps": 3850, "loss": 0.2123, "lr": 1.4600648406692863e-05, "epoch": 4.400363967242948, "percentage": 62.86, "elapsed_time": "16:12:21", "remaining_time": "9:34:34"}
485
+ {"current_steps": 2425, "total_steps": 3850, "loss": 0.2079, "lr": 1.451340423075214e-05, "epoch": 4.409463148316651, "percentage": 62.99, "elapsed_time": "16:14:16", "remaining_time": "9:32:30"}
486
+ {"current_steps": 2430, "total_steps": 3850, "loss": 0.2163, "lr": 1.4426272809730248e-05, "epoch": 4.418562329390355, "percentage": 63.12, "elapsed_time": "16:16:01", "remaining_time": "9:30:21"}
487
+ {"current_steps": 2435, "total_steps": 3850, "loss": 0.2152, "lr": 1.433925593426326e-05, "epoch": 4.427661510464058, "percentage": 63.25, "elapsed_time": "16:17:56", "remaining_time": "9:28:17"}
488
+ {"current_steps": 2440, "total_steps": 3850, "loss": 0.2129, "lr": 1.4252355392633237e-05, "epoch": 4.436760691537762, "percentage": 63.38, "elapsed_time": "16:19:52", "remaining_time": "9:26:14"}
489
+ {"current_steps": 2445, "total_steps": 3850, "loss": 0.208, "lr": 1.4165572970731435e-05, "epoch": 4.445859872611465, "percentage": 63.51, "elapsed_time": "16:21:59", "remaining_time": "9:24:17"}
490
+ {"current_steps": 2450, "total_steps": 3850, "loss": 0.2145, "lr": 1.4078910452021664e-05, "epoch": 4.454959053685168, "percentage": 63.64, "elapsed_time": "16:23:50", "remaining_time": "9:22:11"}
491
+ {"current_steps": 2455, "total_steps": 3850, "loss": 0.2071, "lr": 1.3992369617503594e-05, "epoch": 4.4640582347588715, "percentage": 63.77, "elapsed_time": "16:25:48", "remaining_time": "9:20:09"}
492
+ {"current_steps": 2460, "total_steps": 3850, "loss": 0.2026, "lr": 1.3905952245676173e-05, "epoch": 4.473157415832575, "percentage": 63.9, "elapsed_time": "16:27:48", "remaining_time": "9:18:09"}
493
+ {"current_steps": 2465, "total_steps": 3850, "loss": 0.1955, "lr": 1.3819660112501054e-05, "epoch": 4.482256596906279, "percentage": 64.03, "elapsed_time": "16:29:47", "remaining_time": "9:16:07"}
494
+ {"current_steps": 2470, "total_steps": 3850, "loss": 0.2162, "lr": 1.3733494991366128e-05, "epoch": 4.491355777979982, "percentage": 64.16, "elapsed_time": "16:31:40", "remaining_time": "9:14:03"}
495
+ {"current_steps": 2475, "total_steps": 3850, "loss": 0.2122, "lr": 1.364745865304906e-05, "epoch": 4.500454959053685, "percentage": 64.29, "elapsed_time": "16:33:37", "remaining_time": "9:12:01"}
496
+ {"current_steps": 2480, "total_steps": 3850, "loss": 0.2011, "lr": 1.3561552865680899e-05, "epoch": 4.509554140127388, "percentage": 64.42, "elapsed_time": "16:35:39", "remaining_time": "9:10:01"}
497
+ {"current_steps": 2485, "total_steps": 3850, "loss": 0.2134, "lr": 1.3475779394709754e-05, "epoch": 4.518653321201092, "percentage": 64.55, "elapsed_time": "16:37:32", "remaining_time": "9:07:56"}
498
+ {"current_steps": 2490, "total_steps": 3850, "loss": 0.1926, "lr": 1.3390140002864481e-05, "epoch": 4.5277525022747955, "percentage": 64.68, "elapsed_time": "16:39:51", "remaining_time": "9:06:06"}
499
+ {"current_steps": 2495, "total_steps": 3850, "loss": 0.2065, "lr": 1.3304636450118495e-05, "epoch": 4.536851683348498, "percentage": 64.81, "elapsed_time": "16:41:47", "remaining_time": "9:04:03"}
500
+ {"current_steps": 2500, "total_steps": 3850, "loss": 0.2016, "lr": 1.3219270493653587e-05, "epoch": 4.545950864422202, "percentage": 64.94, "elapsed_time": "16:43:59", "remaining_time": "9:02:09"}
501
+ {"current_steps": 2505, "total_steps": 3850, "loss": 0.207, "lr": 1.3134043887823807e-05, "epoch": 4.555050045495905, "percentage": 65.06, "elapsed_time": "16:45:58", "remaining_time": "9:00:08"}
502
+ {"current_steps": 2510, "total_steps": 3850, "loss": 0.2255, "lr": 1.3048958384119397e-05, "epoch": 4.564149226569609, "percentage": 65.19, "elapsed_time": "16:47:43", "remaining_time": "8:57:59"}
503
+ {"current_steps": 2515, "total_steps": 3850, "loss": 0.2081, "lr": 1.2964015731130836e-05, "epoch": 4.573248407643312, "percentage": 65.32, "elapsed_time": "16:49:48", "remaining_time": "8:56:01"}
504
+ {"current_steps": 2520, "total_steps": 3850, "loss": 0.2151, "lr": 1.2879217674512865e-05, "epoch": 4.582347588717015, "percentage": 65.45, "elapsed_time": "16:51:40", "remaining_time": "8:53:56"}
505
+ {"current_steps": 2525, "total_steps": 3850, "loss": 0.2064, "lr": 1.279456595694864e-05, "epoch": 4.591446769790719, "percentage": 65.58, "elapsed_time": "16:53:50", "remaining_time": "8:52:01"}
506
+ {"current_steps": 2530, "total_steps": 3850, "loss": 0.2154, "lr": 1.2710062318113887e-05, "epoch": 4.600545950864422, "percentage": 65.71, "elapsed_time": "16:55:39", "remaining_time": "8:49:54"}
507
+ {"current_steps": 2535, "total_steps": 3850, "loss": 0.2144, "lr": 1.2625708494641188e-05, "epoch": 4.609645131938126, "percentage": 65.84, "elapsed_time": "16:57:33", "remaining_time": "8:47:50"}
508
+ {"current_steps": 2540, "total_steps": 3850, "loss": 0.2042, "lr": 1.2541506220084262e-05, "epoch": 4.618744313011829, "percentage": 65.97, "elapsed_time": "16:59:24", "remaining_time": "8:45:45"}
509
+ {"current_steps": 2545, "total_steps": 3850, "loss": 0.2156, "lr": 1.2457457224882356e-05, "epoch": 4.627843494085532, "percentage": 66.1, "elapsed_time": "17:01:28", "remaining_time": "8:43:46"}
510
+ {"current_steps": 2550, "total_steps": 3850, "loss": 0.2194, "lr": 1.237356323632468e-05, "epoch": 4.6369426751592355, "percentage": 66.23, "elapsed_time": "17:03:25", "remaining_time": "8:41:44"}
511
+ {"current_steps": 2555, "total_steps": 3850, "loss": 0.1953, "lr": 1.2289825978514882e-05, "epoch": 4.646041856232939, "percentage": 66.36, "elapsed_time": "17:05:35", "remaining_time": "8:39:49"}
512
+ {"current_steps": 2560, "total_steps": 3850, "loss": 0.2027, "lr": 1.2206247172335662e-05, "epoch": 4.655141037306643, "percentage": 66.49, "elapsed_time": "17:07:36", "remaining_time": "8:37:49"}
513
+ {"current_steps": 2565, "total_steps": 3850, "loss": 0.2196, "lr": 1.2122828535413378e-05, "epoch": 4.664240218380346, "percentage": 66.62, "elapsed_time": "17:09:24", "remaining_time": "8:35:42"}
514
+ {"current_steps": 2570, "total_steps": 3850, "loss": 0.1972, "lr": 1.2039571782082762e-05, "epoch": 4.673339399454049, "percentage": 66.75, "elapsed_time": "17:11:29", "remaining_time": "8:33:44"}
515
+ {"current_steps": 2575, "total_steps": 3850, "loss": 0.2062, "lr": 1.1956478623351652e-05, "epoch": 4.682438580527752, "percentage": 66.88, "elapsed_time": "17:13:27", "remaining_time": "8:31:42"}
516
+ {"current_steps": 2580, "total_steps": 3850, "loss": 0.2192, "lr": 1.187355076686589e-05, "epoch": 4.691537761601456, "percentage": 67.01, "elapsed_time": "17:15:23", "remaining_time": "8:29:40"}
517
+ {"current_steps": 2585, "total_steps": 3850, "loss": 0.2052, "lr": 1.1790789916874172e-05, "epoch": 4.7006369426751595, "percentage": 67.14, "elapsed_time": "17:17:20", "remaining_time": "8:27:37"}
518
+ {"current_steps": 2590, "total_steps": 3850, "loss": 0.2034, "lr": 1.1708197774193055e-05, "epoch": 4.709736123748863, "percentage": 67.27, "elapsed_time": "17:19:35", "remaining_time": "8:25:44"}
519
+ {"current_steps": 2595, "total_steps": 3850, "loss": 0.2166, "lr": 1.1625776036172006e-05, "epoch": 4.718835304822566, "percentage": 67.4, "elapsed_time": "17:21:31", "remaining_time": "8:23:42"}
520
+ {"current_steps": 2600, "total_steps": 3850, "loss": 0.2217, "lr": 1.1543526396658475e-05, "epoch": 4.727934485896269, "percentage": 67.53, "elapsed_time": "17:23:21", "remaining_time": "8:21:37"}
521
+ {"current_steps": 2605, "total_steps": 3850, "loss": 0.2136, "lr": 1.1461450545963167e-05, "epoch": 4.737033666969973, "percentage": 67.66, "elapsed_time": "17:26:28", "remaining_time": "8:20:08"}
522
+ {"current_steps": 2610, "total_steps": 3850, "loss": 0.2093, "lr": 1.137955017082521e-05, "epoch": 4.746132848043676, "percentage": 67.79, "elapsed_time": "17:28:10", "remaining_time": "8:17:59"}
523
+ {"current_steps": 2615, "total_steps": 3850, "loss": 0.2091, "lr": 1.1297826954377587e-05, "epoch": 4.755232029117379, "percentage": 67.92, "elapsed_time": "17:30:09", "remaining_time": "8:15:57"}