ryanmarten commited on
Commit
9d0293d
·
verified ·
1 Parent(s): d402b4f

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 sha256:0df531af4cd3051c754917ddc7ca0c1d8ea48c1c6154d0a48cca38393e27b5a8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a0db6ab8f4a8e50bfb6e7a1e0da87e301a2b5b7ab1d832f4b6c6174e91a94a
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:b755a2bdb536ba5725bd9ed9b6c781037cfaca312e1cfcadc4a09227df1e6896
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd92f06350732f763e0551c9211ad6e91a7e250816fc7b3c14d564a6cd432e36
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bcea63aabef35d3c5510caa1ceda65569665e979d30f9d8f8ec7fa5b4fb7f1d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ed159e5cd7abbb212cadc43cf4e77f7c31033983b02b8699e72fded3175e6b
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84fca1e6febc1df43548755614c45c7e1f1460c48959a9ae97abc8652a1216ee
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087647d189ab1ad58b5aed2962ba07c4a7223767f57e9ee8c6db28ccfb6f256e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -77,3 +77,81 @@
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6385, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:28:50", "remaining_time": "14:08:56"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6446, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:31:16", "remaining_time": "14:05:06"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.6037, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:34:49", "remaining_time": "14:05:42"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6385, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:28:50", "remaining_time": "14:08:56"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6446, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:31:16", "remaining_time": "14:05:06"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.6037, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:34:49", "remaining_time": "14:05:42"}
80
+ {"current_steps": 80, "total_steps": 390, "loss": 0.587, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:37:43", "remaining_time": "14:03:41"}
81
+ {"current_steps": 81, "total_steps": 390, "loss": 0.5928, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:40:33", "remaining_time": "14:01:22"}
82
+ {"current_steps": 82, "total_steps": 390, "loss": 0.5948, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:43:18", "remaining_time": "13:58:47"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.6015, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:46:04", "remaining_time": "13:56:11"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.5881, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:48:44", "remaining_time": "13:53:15"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.5908, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:51:29", "remaining_time": "13:50:38"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.5954, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:54:20", "remaining_time": "13:48:22"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5999, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:57:02", "remaining_time": "13:45:34"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.5967, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:59:39", "remaining_time": "13:42:27"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.6134, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "4:02:20", "remaining_time": "13:39:37"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.6097, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "4:05:06", "remaining_time": "13:37:03"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.5706, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "4:07:38", "remaining_time": "13:33:41"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.5831, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "4:10:10", "remaining_time": "13:30:20"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.582, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:12:56", "remaining_time": "13:27:46"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.5902, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:15:42", "remaining_time": "13:25:12"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.604, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:18:27", "remaining_time": "13:22:35"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.5949, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:21:01", "remaining_time": "13:19:23"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.5933, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:23:35", "remaining_time": "13:16:13"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.5898, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:26:19", "remaining_time": "13:13:31"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.5781, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:28:55", "remaining_time": "13:10:29"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.5956, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:31:31", "remaining_time": "13:07:25"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.5873, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:34:16", "remaining_time": "13:04:47"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.5888, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:37:01", "remaining_time": "13:02:12"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.5853, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:39:47", "remaining_time": "12:59:37"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.59, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:42:32", "remaining_time": "12:56:58"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.6016, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:45:20", "remaining_time": "12:54:29"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.5634, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:48:08", "remaining_time": "12:52:00"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.5662, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:50:53", "remaining_time": "12:49:22"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.5909, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:53:37", "remaining_time": "12:46:40"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.5737, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:56:24", "remaining_time": "12:44:07"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.5863, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:59:07", "remaining_time": "12:41:25"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.5741, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "5:02:04", "remaining_time": "12:39:15"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.6046, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "5:04:48", "remaining_time": "12:36:35"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.5681, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "5:07:31", "remaining_time": "12:33:50"}
114
+ {"current_steps": 114, "total_steps": 390, "loss": 0.5862, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "5:10:25", "remaining_time": "12:31:33"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.5817, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "5:12:56", "remaining_time": "12:28:19"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.5845, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "5:15:36", "remaining_time": "12:25:29"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.5822, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "5:18:08", "remaining_time": "12:22:20"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.5928, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:21:00", "remaining_time": "12:19:56"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.5728, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:23:35", "remaining_time": "12:16:55"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.5843, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:26:16", "remaining_time": "12:14:07"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.5734, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:29:15", "remaining_time": "12:11:59"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.59, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:32:01", "remaining_time": "12:09:21"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.5812, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:34:56", "remaining_time": "12:07:04"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.5884, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:37:27", "remaining_time": "12:03:54"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.5771, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:40:13", "remaining_time": "12:01:17"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.5776, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:42:56", "remaining_time": "11:58:31"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.5841, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:45:42", "remaining_time": "11:55:53"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.5871, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:48:20", "remaining_time": "11:53:01"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.5723, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:51:09", "remaining_time": "11:50:29"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.583, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:53:47", "remaining_time": "11:47:34"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.585, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:56:26", "remaining_time": "11:44:42"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.5816, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:59:09", "remaining_time": "11:41:59"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.5832, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "6:01:46", "remaining_time": "11:39:05"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.5716, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "6:04:33", "remaining_time": "11:36:29"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.5762, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "6:07:26", "remaining_time": "11:34:03"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.5799, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "6:10:15", "remaining_time": "11:31:30"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.575, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "6:13:00", "remaining_time": "11:28:49"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.583, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "6:15:47", "remaining_time": "11:26:12"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.5696, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "6:18:26", "remaining_time": "11:23:23"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.5772, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "6:21:12", "remaining_time": "11:20:43"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.5798, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "6:23:40", "remaining_time": "11:17:32"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.5821, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:26:27", "remaining_time": "11:14:56"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.5699, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:29:03", "remaining_time": "11:12:00"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.5632, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:31:38", "remaining_time": "11:09:03"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.5684, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:34:24", "remaining_time": "11:06:24"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.5769, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:37:20", "remaining_time": "11:04:03"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.5713, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:40:06", "remaining_time": "11:01:24"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.5811, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:42:43", "remaining_time": "10:58:31"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.5864, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:45:33", "remaining_time": "10:55:58"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.5721, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:48:15", "remaining_time": "10:53:12"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.5824, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:50:58", "remaining_time": "10:50:29"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.5724, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:53:32", "remaining_time": "10:47:30"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.5625, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:56:03", "remaining_time": "10:44:29"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.5689, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:58:47", "remaining_time": "10:41:47"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.5637, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:01:20", "remaining_time": "10:38:47"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.5754, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:03:57", "remaining_time": "10:35:56"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.5323, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:07:19", "remaining_time": "10:34:10"}