ryanmarten commited on
Commit
83d22d2
·
verified ·
1 Parent(s): 54ca379

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:dfabd3542eae5e54ea5b5e1cb6ddb140cd8c43b8489172f5f02dc27ad40c5136
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908431bb9b2c3b4ef113ea621b240141e8da643971c94ae298a821861d363d75
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:391074d28868d202eabce49b576b17b97f9ff324f1d0b738a7057d35f69766a9
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c928b96777e1dc485ccaa910c0f0263bc4eaa6b0fb05c13252be70b067bf67
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:f3b2b3d0059f17028a4c0f463240ddd91fff5c534ee2f3340a19635180554297
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df4589d6d77c6b2efc99a11699077ea62e755bfb8152407d11d173a2e82f1f6b
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:de10378be5e5cf91a91a46573e997b6e2c7878b3e726e34b18d6afcd0cc148a6
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bb02b2713f2daaa307a994a0958f1a87516fcaa4b1482e566c4529a907d3c5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -77,3 +77,81 @@
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6512, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:30:32", "remaining_time": "14:15:51"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.643, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:33:13", "remaining_time": "14:12:53"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.5974, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:36:44", "remaining_time": "14:13:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.6512, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:30:32", "remaining_time": "14:15:51"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.643, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:33:13", "remaining_time": "14:12:53"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.5974, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:36:44", "remaining_time": "14:13:13"}
80
+ {"current_steps": 80, "total_steps": 390, "loss": 0.6108, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:39:27", "remaining_time": "14:10:23"}
81
+ {"current_steps": 81, "total_steps": 390, "loss": 0.6066, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:42:11", "remaining_time": "14:07:38"}
82
+ {"current_steps": 82, "total_steps": 390, "loss": 0.5945, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:44:52", "remaining_time": "14:04:40"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.5886, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:47:28", "remaining_time": "14:01:21"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.6027, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:50:16", "remaining_time": "13:58:52"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.5882, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:52:55", "remaining_time": "13:55:47"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.5813, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:55:34", "remaining_time": "13:52:42"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5888, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:58:24", "remaining_time": "13:50:17"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.6061, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "4:01:13", "remaining_time": "13:47:50"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.5821, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "4:04:01", "remaining_time": "13:45:19"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.5841, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "4:06:48", "remaining_time": "13:42:42"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.5833, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "4:09:33", "remaining_time": "13:39:59"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.5918, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "4:12:11", "remaining_time": "13:36:54"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.6054, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:15:03", "remaining_time": "13:34:32"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.5849, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:17:43", "remaining_time": "13:31:34"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.5999, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:20:31", "remaining_time": "13:28:59"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.5858, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:23:22", "remaining_time": "13:26:35"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.5995, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:26:16", "remaining_time": "13:24:20"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.5985, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:28:58", "remaining_time": "13:21:26"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.5824, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:31:47", "remaining_time": "13:18:53"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.5766, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:34:26", "remaining_time": "13:15:52"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.5983, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:37:15", "remaining_time": "13:13:20"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.5717, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:39:52", "remaining_time": "13:10:14"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.5812, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:42:50", "remaining_time": "13:08:06"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.5872, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:45:34", "remaining_time": "13:05:18"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.5832, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:48:15", "remaining_time": "13:02:24"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.5742, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:51:01", "remaining_time": "12:59:42"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.577, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:53:37", "remaining_time": "12:56:35"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.593, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:56:12", "remaining_time": "12:53:25"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.5732, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:59:00", "remaining_time": "12:50:50"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.5852, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "5:01:44", "remaining_time": "12:48:03"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.6005, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "5:04:27", "remaining_time": "12:45:14"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.5897, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "5:07:27", "remaining_time": "12:43:09"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.5816, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "5:10:02", "remaining_time": "12:40:01"}
114
+ {"current_steps": 114, "total_steps": 390, "loss": 0.5877, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "5:12:41", "remaining_time": "12:37:03"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.5949, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "5:15:23", "remaining_time": "12:34:11"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.5925, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "5:17:59", "remaining_time": "12:31:06"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.5986, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "5:20:37", "remaining_time": "12:28:07"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.593, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:23:32", "remaining_time": "12:25:48"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.5794, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:26:16", "remaining_time": "12:23:02"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.5941, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:29:02", "remaining_time": "12:20:20"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.5946, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:31:38", "remaining_time": "12:17:16"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.5821, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:34:17", "remaining_time": "12:14:20"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.5899, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:36:56", "remaining_time": "12:11:25"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.5776, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:39:33", "remaining_time": "12:08:23"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.5805, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:42:10", "remaining_time": "12:05:23"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.5849, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:44:54", "remaining_time": "12:02:40"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.5782, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:47:42", "remaining_time": "12:00:03"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.5933, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:50:25", "remaining_time": "11:57:15"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.5801, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:53:08", "remaining_time": "11:54:29"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.6014, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:56:02", "remaining_time": "11:52:04"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.5842, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:58:42", "remaining_time": "11:49:11"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.5902, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "6:01:11", "remaining_time": "11:45:57"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.5854, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "6:03:59", "remaining_time": "11:43:21"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.5792, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "6:06:53", "remaining_time": "11:40:55"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.5888, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "6:09:34", "remaining_time": "11:38:05"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.5848, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "6:12:10", "remaining_time": "11:35:06"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.5827, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "6:14:59", "remaining_time": "11:32:30"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.5726, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "6:17:46", "remaining_time": "11:29:50"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.5905, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "6:20:34", "remaining_time": "11:27:12"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.5848, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "6:23:26", "remaining_time": "11:24:43"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.5751, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "6:26:03", "remaining_time": "11:21:46"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.5779, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:28:54", "remaining_time": "11:19:13"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.5678, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:31:37", "remaining_time": "11:16:26"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.5688, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:34:20", "remaining_time": "11:13:39"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.5743, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:36:59", "remaining_time": "11:10:46"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.5742, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:39:58", "remaining_time": "11:08:26"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.5693, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:42:35", "remaining_time": "11:05:30"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.5625, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:45:08", "remaining_time": "11:02:27"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.594, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:47:35", "remaining_time": "10:59:15"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.591, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:50:22", "remaining_time": "10:56:35"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.5747, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:53:01", "remaining_time": "10:53:43"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.5686, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:55:48", "remaining_time": "10:51:04"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.5837, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:58:32", "remaining_time": "10:48:19"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.5804, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "7:01:08", "remaining_time": "10:45:22"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.574, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:03:50", "remaining_time": "10:42:35"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.5767, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:06:29", "remaining_time": "10:39:44"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.5201, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:10:10", "remaining_time": "10:38:25"}