neginr commited on
Commit
e059d46
·
verified ·
1 Parent(s): bdddbb2

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5da0add5654ba525ae5294b05e230d5d0c904360efc6970f7a25e1d5adb14da
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583c02d70cfe2a97958027c94138b5e3c277d5538b60b62ee0e665c34c58cfef
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a022af7e212d49d864c15c468732f0c125eb98074e79aa65fd5bd24f3e37a3f8
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa59c8e28910353a9027b41657225abda9337062c47e0a8e95cf86e51ba1be76
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11bd8ec9bb0d5d1613ee9c4bec4c9e1452082cc4d49dcb517907fab1a18d8891
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3ebf88c615843d76dae09c1bb0a83cccb91c1851d37c78156d2fb39d9b5e85
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5506906b7bc7cf2c4b4247730ba885ceba4b5a0afa1c471f9b649b0c40b86cbd
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56380b670c3e823fbf3d092f4dac3d6d4f81c04b86700811399e4be4c023223
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -58,3 +58,62 @@
58
  {"current_steps": 58, "total_steps": 295, "loss": 0.6642, "lr": 7.781645249316853e-05, "epoch": 0.9809725158562368, "percentage": 19.66, "elapsed_time": "1:36:50", "remaining_time": "6:35:43"}
59
  {"current_steps": 59, "total_steps": 295, "loss": 0.6568, "lr": 7.765926580392275e-05, "epoch": 0.9978858350951374, "percentage": 20.0, "elapsed_time": "1:38:30", "remaining_time": "6:34:00"}
60
  {"current_steps": 60, "total_steps": 295, "loss": 0.6371, "lr": 7.749678644536485e-05, "epoch": 1.014799154334038, "percentage": 20.34, "elapsed_time": "1:41:58", "remaining_time": "6:39:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  {"current_steps": 58, "total_steps": 295, "loss": 0.6642, "lr": 7.781645249316853e-05, "epoch": 0.9809725158562368, "percentage": 19.66, "elapsed_time": "1:36:50", "remaining_time": "6:35:43"}
59
  {"current_steps": 59, "total_steps": 295, "loss": 0.6568, "lr": 7.765926580392275e-05, "epoch": 0.9978858350951374, "percentage": 20.0, "elapsed_time": "1:38:30", "remaining_time": "6:34:00"}
60
  {"current_steps": 60, "total_steps": 295, "loss": 0.6371, "lr": 7.749678644536485e-05, "epoch": 1.014799154334038, "percentage": 20.34, "elapsed_time": "1:41:58", "remaining_time": "6:39:25"}
61
+ {"current_steps": 61, "total_steps": 295, "loss": 0.6287, "lr": 7.73290372524996e-05, "epoch": 1.0317124735729386, "percentage": 20.68, "elapsed_time": "1:43:39", "remaining_time": "6:37:36"}
62
+ {"current_steps": 62, "total_steps": 295, "loss": 0.6311, "lr": 7.715604180095937e-05, "epoch": 1.0486257928118394, "percentage": 21.02, "elapsed_time": "1:45:18", "remaining_time": "6:35:46"}
63
+ {"current_steps": 63, "total_steps": 295, "loss": 0.6307, "lr": 7.697782440369076e-05, "epoch": 1.06553911205074, "percentage": 21.36, "elapsed_time": "1:46:58", "remaining_time": "6:33:54"}
64
+ {"current_steps": 64, "total_steps": 295, "loss": 0.6299, "lr": 7.679441010753755e-05, "epoch": 1.0824524312896406, "percentage": 21.69, "elapsed_time": "1:48:37", "remaining_time": "6:32:03"}
65
+ {"current_steps": 65, "total_steps": 295, "loss": 0.6192, "lr": 7.660582468972074e-05, "epoch": 1.0993657505285412, "percentage": 22.03, "elapsed_time": "1:50:16", "remaining_time": "6:30:12"}
66
+ {"current_steps": 66, "total_steps": 295, "loss": 0.6292, "lr": 7.641209465421573e-05, "epoch": 1.1162790697674418, "percentage": 22.37, "elapsed_time": "1:51:55", "remaining_time": "6:28:22"}
67
+ {"current_steps": 67, "total_steps": 295, "loss": 0.6316, "lr": 7.621324722802738e-05, "epoch": 1.1331923890063424, "percentage": 22.71, "elapsed_time": "1:53:35", "remaining_time": "6:26:31"}
68
+ {"current_steps": 68, "total_steps": 295, "loss": 0.6248, "lr": 7.600931035736356e-05, "epoch": 1.150105708245243, "percentage": 23.05, "elapsed_time": "1:55:14", "remaining_time": "6:24:41"}
69
+ {"current_steps": 69, "total_steps": 295, "loss": 0.6262, "lr": 7.580031270370755e-05, "epoch": 1.1670190274841437, "percentage": 23.39, "elapsed_time": "1:56:53", "remaining_time": "6:22:51"}
70
+ {"current_steps": 70, "total_steps": 295, "loss": 0.6263, "lr": 7.558628363978991e-05, "epoch": 1.1839323467230445, "percentage": 23.73, "elapsed_time": "1:58:32", "remaining_time": "6:21:02"}
71
+ {"current_steps": 71, "total_steps": 295, "loss": 0.627, "lr": 7.536725324546042e-05, "epoch": 1.200845665961945, "percentage": 24.07, "elapsed_time": "2:00:11", "remaining_time": "6:19:12"}
72
+ {"current_steps": 72, "total_steps": 295, "loss": 0.6235, "lr": 7.514325230346066e-05, "epoch": 1.2177589852008457, "percentage": 24.41, "elapsed_time": "2:01:51", "remaining_time": "6:17:24"}
73
+ {"current_steps": 73, "total_steps": 295, "loss": 0.6217, "lr": 7.491431229509771e-05, "epoch": 1.2346723044397463, "percentage": 24.75, "elapsed_time": "2:03:30", "remaining_time": "6:15:35"}
74
+ {"current_steps": 74, "total_steps": 295, "loss": 0.6223, "lr": 7.468046539581978e-05, "epoch": 1.251585623678647, "percentage": 25.08, "elapsed_time": "2:05:09", "remaining_time": "6:13:47"}
75
+ {"current_steps": 75, "total_steps": 295, "loss": 0.6222, "lr": 7.444174447069423e-05, "epoch": 1.2684989429175475, "percentage": 25.42, "elapsed_time": "2:06:48", "remaining_time": "6:11:59"}
76
+ {"current_steps": 76, "total_steps": 295, "loss": 0.6216, "lr": 7.41981830697887e-05, "epoch": 1.285412262156448, "percentage": 25.76, "elapsed_time": "2:08:28", "remaining_time": "6:10:11"}
77
+ {"current_steps": 77, "total_steps": 295, "loss": 0.6271, "lr": 7.394981542345592e-05, "epoch": 1.302325581395349, "percentage": 26.1, "elapsed_time": "2:10:07", "remaining_time": "6:08:23"}
78
+ {"current_steps": 78, "total_steps": 295, "loss": 0.6182, "lr": 7.369667643752296e-05, "epoch": 1.3192389006342495, "percentage": 26.44, "elapsed_time": "2:11:46", "remaining_time": "6:06:36"}
79
+ {"current_steps": 79, "total_steps": 295, "loss": 0.6224, "lr": 7.343880168838554e-05, "epoch": 1.3361522198731501, "percentage": 26.78, "elapsed_time": "2:13:25", "remaining_time": "6:04:49"}
80
+ {"current_steps": 80, "total_steps": 295, "loss": 0.623, "lr": 7.317622741800808e-05, "epoch": 1.3530655391120507, "percentage": 27.12, "elapsed_time": "2:15:05", "remaining_time": "6:03:02"}
81
+ {"current_steps": 81, "total_steps": 295, "loss": 0.6244, "lr": 7.29089905288302e-05, "epoch": 1.3699788583509513, "percentage": 27.46, "elapsed_time": "2:16:44", "remaining_time": "6:01:15"}
82
+ {"current_steps": 82, "total_steps": 295, "loss": 0.6166, "lr": 7.263712857858044e-05, "epoch": 1.386892177589852, "percentage": 27.8, "elapsed_time": "2:18:23", "remaining_time": "5:59:29"}
83
+ {"current_steps": 83, "total_steps": 295, "loss": 0.6132, "lr": 7.236067977499791e-05, "epoch": 1.4038054968287526, "percentage": 28.14, "elapsed_time": "2:20:03", "remaining_time": "5:57:43"}
84
+ {"current_steps": 84, "total_steps": 295, "loss": 0.6144, "lr": 7.207968297046238e-05, "epoch": 1.4207188160676534, "percentage": 28.47, "elapsed_time": "2:21:42", "remaining_time": "5:55:56"}
85
+ {"current_steps": 85, "total_steps": 295, "loss": 0.6069, "lr": 7.179417765653413e-05, "epoch": 1.437632135306554, "percentage": 28.81, "elapsed_time": "2:23:21", "remaining_time": "5:54:10"}
86
+ {"current_steps": 86, "total_steps": 295, "loss": 0.6118, "lr": 7.150420395840363e-05, "epoch": 1.4545454545454546, "percentage": 29.15, "elapsed_time": "2:25:01", "remaining_time": "5:52:25"}
87
+ {"current_steps": 87, "total_steps": 295, "loss": 0.6125, "lr": 7.120980262925234e-05, "epoch": 1.4714587737843552, "percentage": 29.49, "elapsed_time": "2:26:40", "remaining_time": "5:50:40"}
88
+ {"current_steps": 88, "total_steps": 295, "loss": 0.6092, "lr": 7.091101504452525e-05, "epoch": 1.4883720930232558, "percentage": 29.83, "elapsed_time": "2:28:19", "remaining_time": "5:48:55"}
89
+ {"current_steps": 89, "total_steps": 295, "loss": 0.6104, "lr": 7.06078831961159e-05, "epoch": 1.5052854122621564, "percentage": 30.17, "elapsed_time": "2:29:59", "remaining_time": "5:47:10"}
90
+ {"current_steps": 90, "total_steps": 295, "loss": 0.6031, "lr": 7.030044968646481e-05, "epoch": 1.522198731501057, "percentage": 30.51, "elapsed_time": "2:31:39", "remaining_time": "5:45:25"}
91
+ {"current_steps": 91, "total_steps": 295, "loss": 0.6142, "lr": 6.99887577225721e-05, "epoch": 1.5391120507399578, "percentage": 30.85, "elapsed_time": "2:33:18", "remaining_time": "5:43:41"}
92
+ {"current_steps": 92, "total_steps": 295, "loss": 0.606, "lr": 6.967285110992512e-05, "epoch": 1.5560253699788582, "percentage": 31.19, "elapsed_time": "2:34:58", "remaining_time": "5:41:56"}
93
+ {"current_steps": 93, "total_steps": 295, "loss": 0.608, "lr": 6.935277424634203e-05, "epoch": 1.572938689217759, "percentage": 31.53, "elapsed_time": "2:36:37", "remaining_time": "5:40:11"}
94
+ {"current_steps": 94, "total_steps": 295, "loss": 0.609, "lr": 6.902857211573202e-05, "epoch": 1.5898520084566596, "percentage": 31.86, "elapsed_time": "2:38:17", "remaining_time": "5:38:27"}
95
+ {"current_steps": 95, "total_steps": 295, "loss": 0.6072, "lr": 6.870029028177324e-05, "epoch": 1.6067653276955602, "percentage": 32.2, "elapsed_time": "2:39:56", "remaining_time": "5:36:42"}
96
+ {"current_steps": 96, "total_steps": 295, "loss": 0.6104, "lr": 6.836797488150935e-05, "epoch": 1.6236786469344608, "percentage": 32.54, "elapsed_time": "2:41:35", "remaining_time": "5:34:58"}
97
+ {"current_steps": 97, "total_steps": 295, "loss": 0.6047, "lr": 6.803167261886515e-05, "epoch": 1.6405919661733614, "percentage": 32.88, "elapsed_time": "2:43:15", "remaining_time": "5:33:14"}
98
+ {"current_steps": 98, "total_steps": 295, "loss": 0.6043, "lr": 6.769143075808304e-05, "epoch": 1.6575052854122623, "percentage": 33.22, "elapsed_time": "2:44:54", "remaining_time": "5:31:29"}
99
+ {"current_steps": 99, "total_steps": 295, "loss": 0.5988, "lr": 6.734729711708021e-05, "epoch": 1.6744186046511627, "percentage": 33.56, "elapsed_time": "2:46:33", "remaining_time": "5:29:45"}
100
+ {"current_steps": 100, "total_steps": 295, "loss": 0.6073, "lr": 6.699932006072842e-05, "epoch": 1.6913319238900635, "percentage": 33.9, "elapsed_time": "2:48:12", "remaining_time": "5:28:01"}
101
+ {"current_steps": 101, "total_steps": 295, "loss": 0.5998, "lr": 6.664754849405673e-05, "epoch": 1.708245243128964, "percentage": 34.24, "elapsed_time": "2:49:52", "remaining_time": "5:26:17"}
102
+ {"current_steps": 102, "total_steps": 295, "loss": 0.6021, "lr": 6.629203185537827e-05, "epoch": 1.7251585623678647, "percentage": 34.58, "elapsed_time": "2:51:31", "remaining_time": "5:24:33"}
103
+ {"current_steps": 103, "total_steps": 295, "loss": 0.6063, "lr": 6.59328201093422e-05, "epoch": 1.7420718816067653, "percentage": 34.92, "elapsed_time": "2:53:10", "remaining_time": "5:22:49"}
104
+ {"current_steps": 104, "total_steps": 295, "loss": 0.5995, "lr": 6.55699637399116e-05, "epoch": 1.758985200845666, "percentage": 35.25, "elapsed_time": "2:54:50", "remaining_time": "5:21:05"}
105
+ {"current_steps": 105, "total_steps": 295, "loss": 0.595, "lr": 6.520351374326846e-05, "epoch": 1.7758985200845667, "percentage": 35.59, "elapsed_time": "2:56:29", "remaining_time": "5:19:22"}
106
+ {"current_steps": 106, "total_steps": 295, "loss": 0.5937, "lr": 6.483352162064649e-05, "epoch": 1.792811839323467, "percentage": 35.93, "elapsed_time": "2:58:09", "remaining_time": "5:17:38"}
107
+ {"current_steps": 107, "total_steps": 295, "loss": 0.596, "lr": 6.446003937109329e-05, "epoch": 1.809725158562368, "percentage": 36.27, "elapsed_time": "2:59:48", "remaining_time": "5:15:54"}
108
+ {"current_steps": 108, "total_steps": 295, "loss": 0.6024, "lr": 6.408311948416215e-05, "epoch": 1.8266384778012685, "percentage": 36.61, "elapsed_time": "3:01:27", "remaining_time": "5:14:11"}
109
+ {"current_steps": 109, "total_steps": 295, "loss": 0.6001, "lr": 6.370281493253529e-05, "epoch": 1.8435517970401691, "percentage": 36.95, "elapsed_time": "3:03:06", "remaining_time": "5:12:28"}
110
+ {"current_steps": 110, "total_steps": 295, "loss": 0.6003, "lr": 6.331917916457889e-05, "epoch": 1.8604651162790697, "percentage": 37.29, "elapsed_time": "3:04:46", "remaining_time": "5:10:44"}
111
+ {"current_steps": 111, "total_steps": 295, "loss": 0.5952, "lr": 6.29322660968315e-05, "epoch": 1.8773784355179703, "percentage": 37.63, "elapsed_time": "3:06:25", "remaining_time": "5:09:01"}
112
+ {"current_steps": 112, "total_steps": 295, "loss": 0.5921, "lr": 6.25421301064265e-05, "epoch": 1.8942917547568712, "percentage": 37.97, "elapsed_time": "3:08:04", "remaining_time": "5:07:18"}
113
+ {"current_steps": 113, "total_steps": 295, "loss": 0.6011, "lr": 6.214882602344995e-05, "epoch": 1.9112050739957716, "percentage": 38.31, "elapsed_time": "3:09:43", "remaining_time": "5:05:34"}
114
+ {"current_steps": 114, "total_steps": 295, "loss": 0.5954, "lr": 6.175240912323461e-05, "epoch": 1.9281183932346724, "percentage": 38.64, "elapsed_time": "3:11:22", "remaining_time": "5:03:51"}
115
+ {"current_steps": 115, "total_steps": 295, "loss": 0.596, "lr": 6.135293511859164e-05, "epoch": 1.945031712473573, "percentage": 38.98, "elapsed_time": "3:13:02", "remaining_time": "5:02:08"}
116
+ {"current_steps": 116, "total_steps": 295, "loss": 0.5992, "lr": 6.0950460151980515e-05, "epoch": 1.9619450317124736, "percentage": 39.32, "elapsed_time": "3:14:41", "remaining_time": "5:00:25"}
117
+ {"current_steps": 117, "total_steps": 295, "loss": 0.5942, "lr": 6.054504078761882e-05, "epoch": 1.9788583509513742, "percentage": 39.66, "elapsed_time": "3:16:20", "remaining_time": "4:58:42"}
118
+ {"current_steps": 118, "total_steps": 295, "loss": 0.5989, "lr": 6.013673400353261e-05, "epoch": 1.9957716701902748, "percentage": 40.0, "elapsed_time": "3:17:59", "remaining_time": "4:56:59"}
119
+ {"current_steps": 119, "total_steps": 295, "loss": 0.5599, "lr": 5.972559718354869e-05, "epoch": 2.0126849894291756, "percentage": 40.34, "elapsed_time": "3:21:32", "remaining_time": "4:58:04"}