penfever commited on
Commit
41b942c
·
verified ·
1 Parent(s): a162569

Training in progress, step 5400

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fdb661d7c97130ca54b094ac9e0264b98a8d5c24cd8339cdce4acbbe35b83fe
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4456e11fcc706ec81bfc8cf24ba6f64dded03acbcdf6899b876fda22e58124
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a07983c1ba93262b5c47c929f5508f3911d95f29c4bde5176cd2a275143b8c2
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5e3daf70cd7de21626b61176ba617857dd46e949c2b70cd2a24c1028fd437c
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e45f998edb788bf318c024fda4fbd550243466ad7d81a5935fb058a2a3233f1
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6356773d041df7279fd08e4e5dad9a1d6526a692ecdf0362494f91c5b64137f1
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:bdf6262e8baa25c4f1ac9031c32e32b3efb427e627bfb87a904399f453a4a565
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108ef8664b7eba91c6314ff4ca674d95dbe15902b943a3d71dfe68d1129c032e
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1061,3 +1061,43 @@
1061
  {"current_steps": 5190, "total_steps": 6713, "loss": 0.2135, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "17:09:27", "remaining_time": "5:02:05"}
1062
  {"current_steps": 5195, "total_steps": 6713, "loss": 0.2188, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "17:11:48", "remaining_time": "5:01:29"}
1063
  {"current_steps": 5200, "total_steps": 6713, "loss": 0.2103, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "17:14:11", "remaining_time": "5:00:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1061
  {"current_steps": 5190, "total_steps": 6713, "loss": 0.2135, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "17:09:27", "remaining_time": "5:02:05"}
1062
  {"current_steps": 5195, "total_steps": 6713, "loss": 0.2188, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "17:11:48", "remaining_time": "5:01:29"}
1063
  {"current_steps": 5200, "total_steps": 6713, "loss": 0.2103, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "17:14:11", "remaining_time": "5:00:54"}
1064
+ {"current_steps": 5205, "total_steps": 6713, "loss": 0.2053, "lr": 5.8486741789444804e-06, "epoch": 5.428794992175274, "percentage": 77.54, "elapsed_time": "17:17:51", "remaining_time": "5:00:41"}
1065
+ {"current_steps": 5210, "total_steps": 6713, "loss": 0.2134, "lr": 5.8119732281724715e-06, "epoch": 5.434011476264997, "percentage": 77.61, "elapsed_time": "17:20:14", "remaining_time": "5:00:05"}
1066
+ {"current_steps": 5215, "total_steps": 6713, "loss": 0.2127, "lr": 5.775368205057488e-06, "epoch": 5.439227960354721, "percentage": 77.69, "elapsed_time": "17:22:23", "remaining_time": "4:59:25"}
1067
+ {"current_steps": 5220, "total_steps": 6713, "loss": 0.2072, "lr": 5.738859357092297e-06, "epoch": 5.444444444444445, "percentage": 77.76, "elapsed_time": "17:24:36", "remaining_time": "4:58:46"}
1068
+ {"current_steps": 5225, "total_steps": 6713, "loss": 0.2104, "lr": 5.7024469311194095e-06, "epoch": 5.449660928534168, "percentage": 77.83, "elapsed_time": "17:27:11", "remaining_time": "4:58:13"}
1069
+ {"current_steps": 5230, "total_steps": 6713, "loss": 0.2095, "lr": 5.66613117332943e-06, "epoch": 5.454877412623891, "percentage": 77.91, "elapsed_time": "17:29:18", "remaining_time": "4:57:32"}
1070
+ {"current_steps": 5235, "total_steps": 6713, "loss": 0.2073, "lr": 5.629912329259355e-06, "epoch": 5.460093896713615, "percentage": 77.98, "elapsed_time": "17:31:24", "remaining_time": "4:56:50"}
1071
+ {"current_steps": 5240, "total_steps": 6713, "loss": 0.2048, "lr": 5.593790643790935e-06, "epoch": 5.465310380803339, "percentage": 78.06, "elapsed_time": "17:33:07", "remaining_time": "4:56:02"}
1072
+ {"current_steps": 5245, "total_steps": 6713, "loss": 0.203, "lr": 5.557766361149013e-06, "epoch": 5.470526864893062, "percentage": 78.13, "elapsed_time": "17:34:46", "remaining_time": "4:55:13"}
1073
+ {"current_steps": 5250, "total_steps": 6713, "loss": 0.2024, "lr": 5.521839724899887e-06, "epoch": 5.475743348982785, "percentage": 78.21, "elapsed_time": "17:36:30", "remaining_time": "4:54:24"}
1074
+ {"current_steps": 5255, "total_steps": 6713, "loss": 0.2123, "lr": 5.48601097794963e-06, "epoch": 5.480959833072509, "percentage": 78.28, "elapsed_time": "17:38:09", "remaining_time": "4:53:35"}
1075
+ {"current_steps": 5260, "total_steps": 6713, "loss": 0.2053, "lr": 5.450280362542495e-06, "epoch": 5.486176317162233, "percentage": 78.36, "elapsed_time": "17:39:45", "remaining_time": "4:52:44"}
1076
+ {"current_steps": 5265, "total_steps": 6713, "loss": 0.2057, "lr": 5.414648120259225e-06, "epoch": 5.491392801251957, "percentage": 78.43, "elapsed_time": "17:41:29", "remaining_time": "4:51:56"}
1077
+ {"current_steps": 5270, "total_steps": 6713, "loss": 0.2018, "lr": 5.379114492015467e-06, "epoch": 5.4966092853416795, "percentage": 78.5, "elapsed_time": "17:43:09", "remaining_time": "4:51:06"}
1078
+ {"current_steps": 5275, "total_steps": 6713, "loss": 0.1967, "lr": 5.343679718060104e-06, "epoch": 5.501825769431403, "percentage": 78.58, "elapsed_time": "17:44:52", "remaining_time": "4:50:17"}
1079
+ {"current_steps": 5280, "total_steps": 6713, "loss": 0.1856, "lr": 5.308344037973672e-06, "epoch": 5.507042253521127, "percentage": 78.65, "elapsed_time": "17:46:34", "remaining_time": "4:49:28"}
1080
+ {"current_steps": 5285, "total_steps": 6713, "loss": 0.1978, "lr": 5.2731076906666786e-06, "epoch": 5.51225873761085, "percentage": 78.73, "elapsed_time": "17:48:10", "remaining_time": "4:48:37"}
1081
+ {"current_steps": 5290, "total_steps": 6713, "loss": 0.2026, "lr": 5.237970914378068e-06, "epoch": 5.517475221700574, "percentage": 78.8, "elapsed_time": "17:49:49", "remaining_time": "4:47:46"}
1082
+ {"current_steps": 5295, "total_steps": 6713, "loss": 0.2083, "lr": 5.202933946673532e-06, "epoch": 5.522691705790297, "percentage": 78.88, "elapsed_time": "17:51:28", "remaining_time": "4:46:56"}
1083
+ {"current_steps": 5300, "total_steps": 6713, "loss": 0.1908, "lr": 5.1679970244439695e-06, "epoch": 5.527908189880021, "percentage": 78.95, "elapsed_time": "17:53:08", "remaining_time": "4:46:06"}
1084
+ {"current_steps": 5305, "total_steps": 6713, "loss": 0.194, "lr": 5.13316038390383e-06, "epoch": 5.533124673969745, "percentage": 79.03, "elapsed_time": "17:54:47", "remaining_time": "4:45:15"}
1085
+ {"current_steps": 5310, "total_steps": 6713, "loss": 0.1996, "lr": 5.098424260589565e-06, "epoch": 5.538341158059468, "percentage": 79.1, "elapsed_time": "17:56:26", "remaining_time": "4:44:24"}
1086
+ {"current_steps": 5315, "total_steps": 6713, "loss": 0.1941, "lr": 5.063788889357995e-06, "epoch": 5.5435576421491914, "percentage": 79.17, "elapsed_time": "17:58:08", "remaining_time": "4:43:34"}
1087
+ {"current_steps": 5320, "total_steps": 6713, "loss": 0.186, "lr": 5.029254504384733e-06, "epoch": 5.548774126238915, "percentage": 79.25, "elapsed_time": "17:59:45", "remaining_time": "4:42:43"}
1088
+ {"current_steps": 5325, "total_steps": 6713, "loss": 0.1999, "lr": 4.9948213391626325e-06, "epoch": 5.553990610328638, "percentage": 79.32, "elapsed_time": "18:01:26", "remaining_time": "4:41:53"}
1089
+ {"current_steps": 5330, "total_steps": 6713, "loss": 0.1979, "lr": 4.960489626500153e-06, "epoch": 5.559207094418362, "percentage": 79.4, "elapsed_time": "18:03:06", "remaining_time": "4:41:02"}
1090
+ {"current_steps": 5335, "total_steps": 6713, "loss": 0.1909, "lr": 4.926259598519851e-06, "epoch": 5.5644235785080856, "percentage": 79.47, "elapsed_time": "18:04:47", "remaining_time": "4:40:11"}
1091
+ {"current_steps": 5340, "total_steps": 6713, "loss": 0.1984, "lr": 4.892131486656733e-06, "epoch": 5.569640062597809, "percentage": 79.55, "elapsed_time": "18:06:21", "remaining_time": "4:39:19"}
1092
+ {"current_steps": 5345, "total_steps": 6713, "loss": 0.1974, "lr": 4.858105521656768e-06, "epoch": 5.574856546687533, "percentage": 79.62, "elapsed_time": "18:07:57", "remaining_time": "4:38:27"}
1093
+ {"current_steps": 5350, "total_steps": 6713, "loss": 0.1987, "lr": 4.824181933575272e-06, "epoch": 5.580073030777256, "percentage": 79.7, "elapsed_time": "18:09:41", "remaining_time": "4:37:36"}
1094
+ {"current_steps": 5355, "total_steps": 6713, "loss": 0.1912, "lr": 4.790360951775392e-06, "epoch": 5.58528951486698, "percentage": 79.77, "elapsed_time": "18:11:21", "remaining_time": "4:36:45"}
1095
+ {"current_steps": 5360, "total_steps": 6713, "loss": 0.2048, "lr": 4.756642804926517e-06, "epoch": 5.590505998956703, "percentage": 79.85, "elapsed_time": "18:13:01", "remaining_time": "4:35:54"}
1096
+ {"current_steps": 5365, "total_steps": 6713, "loss": 0.2038, "lr": 4.7230277210027685e-06, "epoch": 5.595722483046426, "percentage": 79.92, "elapsed_time": "18:14:49", "remaining_time": "4:35:05"}
1097
+ {"current_steps": 5370, "total_steps": 6713, "loss": 0.1876, "lr": 4.689515927281427e-06, "epoch": 5.60093896713615, "percentage": 79.99, "elapsed_time": "18:16:25", "remaining_time": "4:34:12"}
1098
+ {"current_steps": 5375, "total_steps": 6713, "loss": 0.2003, "lr": 4.6561076503414235e-06, "epoch": 5.606155451225874, "percentage": 80.07, "elapsed_time": "18:18:04", "remaining_time": "4:33:20"}
1099
+ {"current_steps": 5380, "total_steps": 6713, "loss": 0.1996, "lr": 4.622803116061789e-06, "epoch": 5.6113719353155975, "percentage": 80.14, "elapsed_time": "18:19:49", "remaining_time": "4:32:30"}
1100
+ {"current_steps": 5385, "total_steps": 6713, "loss": 0.1944, "lr": 4.589602549620127e-06, "epoch": 5.616588419405321, "percentage": 80.22, "elapsed_time": "18:21:34", "remaining_time": "4:31:39"}
1101
+ {"current_steps": 5390, "total_steps": 6713, "loss": 0.1872, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "18:23:13", "remaining_time": "4:30:47"}
1102
+ {"current_steps": 5395, "total_steps": 6713, "loss": 0.2032, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "18:24:52", "remaining_time": "4:29:55"}
1103
+ {"current_steps": 5400, "total_steps": 6713, "loss": 0.1975, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "18:26:36", "remaining_time": "4:29:04"}