ryanmarten commited on
Commit
8f039af
·
verified ·
1 Parent(s): b5e6c7e

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 sha256:21ae7f1f61f83ec52bc00f023f56182b6ff5b464c538c7e68182c4d77f0fe7df
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea969e55c03bea986a7468057cc83c38962f89fc9068512c5add08264bc63c94
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a3e32242ec9caaf50c91b3e0c3ffcc51cdd5caeb60298efa9618f5e94ca04eb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a5c96cb4bdc6a8be52ec31555db151c12b4fdc06bc49ec0a688aefa14f6a99
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:f561ef864b711deea579aab76baf0bb7f7f6ea98deb24a75b7e954f58deb4397
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d219b0825f3440118f3029e5b221fb8d72bb21f6353eed46d402f2f235106158
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61b2bb2f5f2a6e64fff0a20ba99cdad47305cb6b2ab23ed14a0d010666b6563b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e38406bc074a23e418d98f769b0584c17a6ff49845d341d73d4d9f84239370
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -77,3 +77,81 @@
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.4365, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:19:07", "remaining_time": "13:29:25"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.4499, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:21:37", "remaining_time": "13:26:31"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.4107, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:24:44", "remaining_time": "13:25:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  {"current_steps": 77, "total_steps": 390, "loss": 0.4365, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:19:07", "remaining_time": "13:29:25"}
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.4499, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:21:37", "remaining_time": "13:26:31"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.4107, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:24:44", "remaining_time": "13:25:58"}
80
+ {"current_steps": 80, "total_steps": 390, "loss": 0.4064, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:27:04", "remaining_time": "13:22:23"}
81
+ {"current_steps": 81, "total_steps": 390, "loss": 0.4268, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:29:27", "remaining_time": "13:19:02"}
82
+ {"current_steps": 82, "total_steps": 390, "loss": 0.3935, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:31:58", "remaining_time": "13:16:10"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.3981, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:34:27", "remaining_time": "13:13:14"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.4091, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:36:53", "remaining_time": "13:10:08"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.3992, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:39:24", "remaining_time": "13:07:16"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.416, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:41:40", "remaining_time": "13:03:34"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5898, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:44:09", "remaining_time": "13:00:41"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.4137, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:46:42", "remaining_time": "12:57:59"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.4128, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:49:20", "remaining_time": "12:55:39"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.4019, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:52:07", "remaining_time": "12:53:44"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.4186, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:54:34", "remaining_time": "12:50:44"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.4036, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "3:57:01", "remaining_time": "12:47:45"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.4035, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "3:59:23", "remaining_time": "12:44:30"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.408, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:01:41", "remaining_time": "12:41:03"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.4113, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:04:13", "remaining_time": "12:38:22"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.4125, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:06:55", "remaining_time": "12:36:13"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.4205, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:09:17", "remaining_time": "12:33:01"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.406, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:11:48", "remaining_time": "12:30:15"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.408, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:14:16", "remaining_time": "12:27:23"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.4067, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:16:48", "remaining_time": "12:24:45"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.4021, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:19:20", "remaining_time": "12:22:04"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.4015, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:21:47", "remaining_time": "12:19:10"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.3968, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:24:08", "remaining_time": "12:15:59"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.4136, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:26:34", "remaining_time": "12:13:04"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.3976, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:29:16", "remaining_time": "12:10:54"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.4055, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:31:42", "remaining_time": "12:07:59"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.4079, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:34:11", "remaining_time": "12:05:11"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.4185, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:36:40", "remaining_time": "12:02:24"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.418, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:39:11", "remaining_time": "11:59:44"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.3923, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:41:34", "remaining_time": "11:56:43"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.3997, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "4:44:03", "remaining_time": "11:53:58"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.4063, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "4:46:24", "remaining_time": "11:50:53"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.3892, "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": 0.402, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "4:51:15", "remaining_time": "11:45:09"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.3919, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "4:53:35", "remaining_time": "11:42:05"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.3994, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "4:56:04", "remaining_time": "11:39:21"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.3924, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "4:58:29", "remaining_time": "11:36:28"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.407, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:00:50", "remaining_time": "11:33:26"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.413, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:03:28", "remaining_time": "11:31:06"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.3932, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:05:58", "remaining_time": "11:28:27"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.3928, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:08:19", "remaining_time": "11:25:27"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.3852, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:11:05", "remaining_time": "11:23:22"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.4079, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:13:41", "remaining_time": "11:20:55"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.3923, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:16:19", "remaining_time": "11:18:34"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.4013, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:18:50", "remaining_time": "11:15:57"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.4043, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:21:15", "remaining_time": "11:13:07"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.3956, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:23:56", "remaining_time": "11:10:50"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.3874, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:26:15", "remaining_time": "11:07:49"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.3998, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:28:42", "remaining_time": "11:05:03"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.4, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:31:08", "remaining_time": "11:02:16"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.3943, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:33:33", "remaining_time": "10:59:28"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.3948, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:36:11", "remaining_time": "10:57:06"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.3955, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "5:38:34", "remaining_time": "10:54:13"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.3931, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "5:41:01", "remaining_time": "10:51:31"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.4045, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "5:43:33", "remaining_time": "10:48:57"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.3918, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "5:45:59", "remaining_time": "10:46:11"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.3843, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "5:48:32", "remaining_time": "10:43:39"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.3861, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "5:50:58", "remaining_time": "10:40:54"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.3919, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "5:53:34", "remaining_time": "10:38:27"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.3825, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "5:55:57", "remaining_time": "10:35:38"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.3944, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "5:58:32", "remaining_time": "10:33:10"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.4046, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:00:57", "remaining_time": "10:30:24"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.3953, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:03:27", "remaining_time": "10:27:46"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.3839, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:05:52", "remaining_time": "10:25:01"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.3957, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:08:35", "remaining_time": "10:22:46"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.3887, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:10:56", "remaining_time": "10:19:55"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.399, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:13:30", "remaining_time": "10:17:26"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.3899, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:15:54", "remaining_time": "10:14:39"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.3947, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:18:03", "remaining_time": "10:11:29"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.3783, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:20:30", "remaining_time": "10:08:48"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.3926, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:23:04", "remaining_time": "10:06:20"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.3789, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:25:21", "remaining_time": "10:03:23"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.3878, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:27:58", "remaining_time": "10:00:58"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.3852, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:30:30", "remaining_time": "9:58:27"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.3934, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:33:09", "remaining_time": "9:56:05"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.3809, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:35:37", "remaining_time": "9:53:26"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.3455, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:38:55", "remaining_time": "9:52:02"}