ryanmarten commited on
Commit
1b36133
·
verified ·
1 Parent(s): 0dc1048

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 sha256:8441d828c672794e3ed4f7ccf0d27399dde0efe24b390ce96c925859b46c237b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cd82d0683fa136c5aba880b795923df28288864df46db9d4f38c9671cfc250
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:564fa1d7c681d7c3a821125d370bc68884a5497bbd255545ef78a8238a1bbf77
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f804b3710bea9a8b22195387ea0704fd1e425533dfc4483d3fcd6ddd2f7d1b
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:a893af71364d861e206d016e9e59a9c1efadca58df5aecb1bd4aecd6044f01c2
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15968a46339cb9f0e508a6380125b5b18967eb3bcb8a30403300630a74f110e0
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:c6ede24ddef086face46a260efeb377ca681b087906a31c52e721658ee7270bc
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3a8f832413efd83f1729907f208b64d6603b7afe1146fcec3ae4d1c3551c10
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -77,3 +77,81 @@
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6432, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:27:48", "remaining_time": "14:04:43"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6306, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:30:36", "remaining_time": "14:02:27"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.5884, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:33:57", "remaining_time": "14:02:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6432, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:27:48", "remaining_time": "14:04:43"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6306, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:30:36", "remaining_time": "14:02:27"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.5884, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:33:57", "remaining_time": "14:02:17"}
80
+ {"current_steps": 80, "total_steps": 390, "loss": 0.5942, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:36:39", "remaining_time": "13:59:31"}
81
+ {"current_steps": 81, "total_steps": 390, "loss": 0.5925, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:39:18", "remaining_time": "13:56:35"}
82
+ {"current_steps": 82, "total_steps": 390, "loss": 0.5844, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:42:06", "remaining_time": "13:54:16"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.6025, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:44:49", "remaining_time": "13:51:33"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.5934, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:47:27", "remaining_time": "13:48:35"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.5838, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:49:59", "remaining_time": "13:45:14"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.5901, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:52:39", "remaining_time": "13:42:26"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5894, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:55:28", "remaining_time": "13:40:06"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.5808, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:57:55", "remaining_time": "13:36:31"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.5775, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "4:00:41", "remaining_time": "13:34:03"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.5834, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "4:03:22", "remaining_time": "13:31:16"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.5827, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "4:06:04", "remaining_time": "13:28:32"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.5791, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "4:08:43", "remaining_time": "13:25:37"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.5943, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:11:29", "remaining_time": "13:23:08"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.5885, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:14:07", "remaining_time": "13:20:13"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.5955, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:16:51", "remaining_time": "13:17:36"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.5842, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:19:33", "remaining_time": "13:14:53"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.5771, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:22:16", "remaining_time": "13:12:14"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.5747, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:25:04", "remaining_time": "13:09:50"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.5766, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:27:41", "remaining_time": "13:06:51"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.5837, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:30:29", "remaining_time": "13:04:24"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.5723, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:33:04", "remaining_time": "13:01:22"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.5751, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:35:39", "remaining_time": "12:58:19"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.5876, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:38:28", "remaining_time": "12:55:57"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.595, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:41:22", "remaining_time": "12:53:46"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.6005, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:44:11", "remaining_time": "12:51:22"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.5804, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:46:53", "remaining_time": "12:48:39"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.5769, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:49:54", "remaining_time": "12:46:45"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.588, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:52:17", "remaining_time": "12:43:11"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.57, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:55:01", "remaining_time": "12:40:34"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.5729, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:57:40", "remaining_time": "12:37:42"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.5793, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "5:00:33", "remaining_time": "12:35:28"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.5841, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "5:03:14", "remaining_time": "12:32:42"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.5861, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "5:05:55", "remaining_time": "12:29:55"}
114
+ {"current_steps": 114, "total_steps": 390, "loss": 0.5834, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "5:08:45", "remaining_time": "12:27:30"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.582, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "5:11:30", "remaining_time": "12:24:54"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.572, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "5:14:06", "remaining_time": "12:21:55"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.5783, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "5:16:31", "remaining_time": "12:18:34"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.5642, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:19:13", "remaining_time": "12:15:49"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.5859, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:21:54", "remaining_time": "12:13:05"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.5711, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:24:48", "remaining_time": "12:10:48"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.5841, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:27:39", "remaining_time": "12:08:26"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.584, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:30:33", "remaining_time": "12:06:07"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.5868, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:33:04", "remaining_time": "12:03:01"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.5764, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:35:52", "remaining_time": "12:00:29"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.5794, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:38:36", "remaining_time": "11:57:51"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.5887, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:41:24", "remaining_time": "11:55:19"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.5708, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:43:59", "remaining_time": "11:52:21"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.5764, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:46:29", "remaining_time": "11:49:14"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.5872, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:49:06", "remaining_time": "11:46:19"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.574, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:51:44", "remaining_time": "11:43:29"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.5654, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:54:20", "remaining_time": "11:40:34"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.5671, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:56:54", "remaining_time": "11:37:36"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.5808, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "5:59:32", "remaining_time": "11:34:45"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.5736, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "6:02:12", "remaining_time": "11:31:59"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.5737, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "6:05:07", "remaining_time": "11:29:39"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.5778, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "6:07:52", "remaining_time": "11:27:04"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.5686, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "6:10:47", "remaining_time": "11:24:45"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.5716, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "6:13:29", "remaining_time": "11:22:02"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.5786, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "6:16:14", "remaining_time": "11:19:23"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.5663, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "6:18:59", "remaining_time": "11:16:45"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.5657, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "6:21:35", "remaining_time": "11:13:51"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.5747, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:24:17", "remaining_time": "11:11:09"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.5703, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:27:05", "remaining_time": "11:08:36"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.5702, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:29:50", "remaining_time": "11:05:59"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.5701, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:32:25", "remaining_time": "11:03:03"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.5687, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:35:14", "remaining_time": "11:00:32"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.5709, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:37:40", "remaining_time": "10:57:23"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.5677, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:40:29", "remaining_time": "10:54:50"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.5757, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:43:12", "remaining_time": "10:52:10"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.5675, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:45:52", "remaining_time": "10:49:24"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.5687, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:48:36", "remaining_time": "10:46:43"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.571, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:51:10", "remaining_time": "10:43:49"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.5691, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:53:42", "remaining_time": "10:40:51"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.5581, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:56:25", "remaining_time": "10:38:08"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.5789, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:59:00", "remaining_time": "10:35:16"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.5741, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:01:46", "remaining_time": "10:32:39"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.5143, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:05:15", "remaining_time": "10:31:06"}