ryanmarten commited on
Commit
55dc97c
·
verified ·
1 Parent(s): b58162c

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:dc0c71b1574f1df724de77bfed2a2bc6d972d6ae4524609ba2d75c152deb8e93
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa44b2f9f7fb00ad4c40e379eb6a5ee6d1b7a73ff245566cddf93f33d5a41558
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:b739970010ec3ead1f00534e3baf3082882ceb2f71b618da8cf004dc7733cebb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f20bf3dc2100d64074f7eb122b242ea0646cea7d9d223605a2636caa6d5a5d7
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:fb492ca9c6e3e3e10b4aaae9e8964cc83553205c1bdcf906ed3a5e8d0cd836d5
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35dc6f58b630e1092e2a5eb673c0024befd1ac427ccaed5d3b20f20e7dfc26bc
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a9bc4ee390b75b4d9066390b8334ffa46cbd856cbe5aef00548557a8fd6a30
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617b8e258eb8c32290b5c7b106c5e3bfd2a08d11edf3d055285b8ee0903872a7
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -80,3 +80,78 @@
80
  {"current_steps": 80, "total_steps": 390, "loss": 0.5657, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:29:20", "remaining_time": "13:31:12"}
81
  {"current_steps": 81, "total_steps": 390, "loss": 0.5762, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:31:52", "remaining_time": "13:28:16"}
82
  {"current_steps": 82, "total_steps": 390, "loss": 0.5495, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:34:07", "remaining_time": "13:24:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {"current_steps": 80, "total_steps": 390, "loss": 0.5657, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:29:20", "remaining_time": "13:31:12"}
81
  {"current_steps": 81, "total_steps": 390, "loss": 0.5762, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:31:52", "remaining_time": "13:28:16"}
82
  {"current_steps": 82, "total_steps": 390, "loss": 0.5495, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:34:07", "remaining_time": "13:24:17"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.5622, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:36:29", "remaining_time": "13:20:43"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.5651, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:39:05", "remaining_time": "13:18:05"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.5595, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:41:33", "remaining_time": "13:14:59"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.5453, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:44:05", "remaining_time": "13:12:07"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5507, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:46:28", "remaining_time": "13:08:45"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.5676, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:48:49", "remaining_time": "13:05:17"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.5577, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:51:13", "remaining_time": "13:01:59"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.5523, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:53:22", "remaining_time": "12:57:55"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.5529, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:55:55", "remaining_time": "12:55:10"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.5513, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "3:58:12", "remaining_time": "12:51:36"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.5612, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:00:50", "remaining_time": "12:49:09"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.5603, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:03:16", "remaining_time": "12:46:03"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.5619, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:05:45", "remaining_time": "12:43:09"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.5532, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:08:01", "remaining_time": "12:39:36"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.5351, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:10:16", "remaining_time": "12:35:58"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.5636, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:12:53", "remaining_time": "12:33:30"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.5589, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:15:36", "remaining_time": "12:31:19"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.5562, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:17:55", "remaining_time": "12:27:58"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.5604, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:20:32", "remaining_time": "12:25:29"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.5444, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:23:00", "remaining_time": "12:22:35"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.5646, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:25:32", "remaining_time": "12:19:54"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.5445, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:27:45", "remaining_time": "12:16:20"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.5598, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:30:03", "remaining_time": "12:13:01"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.5642, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:32:31", "remaining_time": "12:10:08"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.5584, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:34:56", "remaining_time": "12:07:10"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.5523, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:37:14", "remaining_time": "12:03:53"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.5391, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:39:26", "remaining_time": "12:00:24"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.5479, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:41:53", "remaining_time": "11:57:32"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.5527, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "4:44:16", "remaining_time": "11:54:31"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.5403, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "4:46:34", "remaining_time": "11:51:20"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.5444, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "4:48:52", "remaining_time": "11:48:06"}
114
+ {"current_steps": 114, "total_steps": 390, "loss": 0.5443, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "4:51:12", "remaining_time": "11:45:01"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.5556, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "4:53:45", "remaining_time": "11:42:27"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.5471, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "4:56:22", "remaining_time": "11:40:04"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.5558, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "4:58:50", "remaining_time": "11:37:17"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.5421, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:01:14", "remaining_time": "11:34:23"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.5448, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:03:48", "remaining_time": "11:31:52"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.5602, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:06:15", "remaining_time": "11:29:05"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.5527, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:08:44", "remaining_time": "11:26:22"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.5683, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:11:15", "remaining_time": "11:23:44"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.5488, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:13:39", "remaining_time": "11:20:51"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.5494, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:15:57", "remaining_time": "11:17:47"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.5372, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:18:22", "remaining_time": "11:14:57"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.5488, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:20:31", "remaining_time": "11:11:34"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.5444, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:22:50", "remaining_time": "11:08:34"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.5668, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:25:13", "remaining_time": "11:05:41"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.559, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:27:44", "remaining_time": "11:03:07"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.5304, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:29:59", "remaining_time": "10:59:58"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.5468, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:32:04", "remaining_time": "10:56:33"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.5459, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:34:24", "remaining_time": "10:53:37"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.5553, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "5:36:56", "remaining_time": "10:51:05"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.5405, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "5:39:18", "remaining_time": "10:48:14"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.5464, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "5:41:41", "remaining_time": "10:45:24"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.5404, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "5:43:58", "remaining_time": "10:42:25"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.5535, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "5:46:36", "remaining_time": "10:40:05"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.5495, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "5:48:53", "remaining_time": "10:37:05"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.5467, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "5:51:11", "remaining_time": "10:34:09"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.5553, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "5:53:37", "remaining_time": "10:31:28"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.5539, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "5:55:57", "remaining_time": "10:28:36"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.5469, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "5:58:21", "remaining_time": "10:25:52"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.5452, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:00:47", "remaining_time": "10:23:11"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.5491, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:03:33", "remaining_time": "10:21:05"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.549, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:06:08", "remaining_time": "10:18:39"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.5347, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:08:24", "remaining_time": "10:15:41"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.5462, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:11:04", "remaining_time": "10:13:24"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.5547, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:13:32", "remaining_time": "10:10:46"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.5621, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:16:04", "remaining_time": "10:08:17"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.5461, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:18:09", "remaining_time": "10:05:03"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.5545, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:20:40", "remaining_time": "10:02:31"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.5473, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:23:01", "remaining_time": "9:59:44"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.5582, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:25:26", "remaining_time": "9:57:02"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.5674, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:27:54", "remaining_time": "9:54:27"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.5556, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:30:17", "remaining_time": "9:51:44"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.5375, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:32:37", "remaining_time": "9:48:56"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.4848, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:35:48", "remaining_time": "9:47:25"}