ryanmarten commited on
Commit
b125795
·
verified ·
1 Parent(s): cac3678

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 sha256:68b48aae77830400830eaa273fceb1557a16edd9fcba98d9aad55276f655d18b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650ee312858b20963aec8648167203d5eeb5df9bc52c62cc56ea392139dbf749
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fcc82742f590919954c23c2bde2941f1105f1200a649e38e71e786f4a078329
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82f1cdb9869f2b39960edda84554f5116653c3e8f071d71f7a2c9c19aca8ff8
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:b0b4e4db712dd6720cccfa854b4371c55582cd5851856b1c11c83885f04a6e2b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f0ab9f38d08f14cefe2dca783ce121e145ab0bdd16b49fff9c466dba35b9b3
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89e9a1b41c39d99b9b6ec42c0c0d1a95b61564ea6760c1d2ae8abc553726defd
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1828c1df9bb799afd4cab534f46b38ba2ca42c40e9a7729a8c48459eaaa74e96
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -78,3 +78,80 @@
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6518, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:49:07", "remaining_time": "11:16:30"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.6111, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:51:57", "remaining_time": "11:16:58"}
80
  {"current_steps": 80, "total_steps": 390, "loss": 0.6014, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:54:16", "remaining_time": "11:15:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  {"current_steps": 78, "total_steps": 390, "loss": 0.6518, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:49:07", "remaining_time": "11:16:30"}
79
  {"current_steps": 79, "total_steps": 390, "loss": 0.6111, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:51:57", "remaining_time": "11:16:58"}
80
  {"current_steps": 80, "total_steps": 390, "loss": 0.6014, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:54:16", "remaining_time": "11:15:18"}
81
+ {"current_steps": 81, "total_steps": 390, "loss": 0.5856, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "2:56:19", "remaining_time": "11:12:37"}
82
+ {"current_steps": 82, "total_steps": 390, "loss": 0.5839, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "2:58:35", "remaining_time": "11:10:47"}
83
+ {"current_steps": 83, "total_steps": 390, "loss": 0.5966, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:00:46", "remaining_time": "11:08:40"}
84
+ {"current_steps": 84, "total_steps": 390, "loss": 0.5888, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:03:05", "remaining_time": "11:06:58"}
85
+ {"current_steps": 85, "total_steps": 390, "loss": 0.5873, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:05:13", "remaining_time": "11:04:36"}
86
+ {"current_steps": 86, "total_steps": 390, "loss": 0.5822, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:07:45", "remaining_time": "11:03:43"}
87
+ {"current_steps": 87, "total_steps": 390, "loss": 0.5931, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:10:10", "remaining_time": "11:02:18"}
88
+ {"current_steps": 88, "total_steps": 390, "loss": 0.5972, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:12:31", "remaining_time": "11:00:41"}
89
+ {"current_steps": 89, "total_steps": 390, "loss": 0.6046, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:14:24", "remaining_time": "10:57:30"}
90
+ {"current_steps": 90, "total_steps": 390, "loss": 0.5937, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:16:32", "remaining_time": "10:55:07"}
91
+ {"current_steps": 91, "total_steps": 390, "loss": 0.5886, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:18:33", "remaining_time": "10:52:24"}
92
+ {"current_steps": 92, "total_steps": 390, "loss": 0.6014, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "3:20:42", "remaining_time": "10:50:05"}
93
+ {"current_steps": 93, "total_steps": 390, "loss": 0.5903, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "3:22:56", "remaining_time": "10:48:05"}
94
+ {"current_steps": 94, "total_steps": 390, "loss": 0.6031, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "3:25:05", "remaining_time": "10:45:50"}
95
+ {"current_steps": 95, "total_steps": 390, "loss": 0.5871, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "3:27:05", "remaining_time": "10:43:03"}
96
+ {"current_steps": 96, "total_steps": 390, "loss": 0.5853, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "3:29:06", "remaining_time": "10:40:22"}
97
+ {"current_steps": 97, "total_steps": 390, "loss": 0.6017, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "3:31:22", "remaining_time": "10:38:28"}
98
+ {"current_steps": 98, "total_steps": 390, "loss": 0.5825, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "3:33:36", "remaining_time": "10:36:28"}
99
+ {"current_steps": 99, "total_steps": 390, "loss": 0.5899, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "3:35:48", "remaining_time": "10:34:19"}
100
+ {"current_steps": 100, "total_steps": 390, "loss": 0.5963, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "3:37:56", "remaining_time": "10:32:00"}
101
+ {"current_steps": 101, "total_steps": 390, "loss": 0.6026, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "3:40:04", "remaining_time": "10:29:43"}
102
+ {"current_steps": 102, "total_steps": 390, "loss": 0.598, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "3:42:25", "remaining_time": "10:28:00"}
103
+ {"current_steps": 103, "total_steps": 390, "loss": 0.591, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "3:44:42", "remaining_time": "10:26:09"}
104
+ {"current_steps": 104, "total_steps": 390, "loss": 0.5796, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "3:46:57", "remaining_time": "10:24:07"}
105
+ {"current_steps": 105, "total_steps": 390, "loss": 0.5882, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "3:49:03", "remaining_time": "10:21:45"}
106
+ {"current_steps": 106, "total_steps": 390, "loss": 0.5818, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "3:51:12", "remaining_time": "10:19:27"}
107
+ {"current_steps": 107, "total_steps": 390, "loss": 0.591, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "3:53:25", "remaining_time": "10:17:23"}
108
+ {"current_steps": 108, "total_steps": 390, "loss": 0.5791, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "3:55:33", "remaining_time": "10:15:05"}
109
+ {"current_steps": 109, "total_steps": 390, "loss": 0.5953, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "3:57:30", "remaining_time": "10:12:16"}
110
+ {"current_steps": 110, "total_steps": 390, "loss": 0.5774, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "3:59:53", "remaining_time": "10:10:37"}
111
+ {"current_steps": 111, "total_steps": 390, "loss": 0.588, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "4:02:11", "remaining_time": "10:08:44"}
112
+ {"current_steps": 112, "total_steps": 390, "loss": 0.5876, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "4:04:19", "remaining_time": "10:06:25"}
113
+ {"current_steps": 113, "total_steps": 390, "loss": 0.5855, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "4:06:32", "remaining_time": "10:04:21"}
114
+ {"current_steps": 114, "total_steps": 390, "loss": 0.5801, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "4:08:39", "remaining_time": "10:02:00"}
115
+ {"current_steps": 115, "total_steps": 390, "loss": 0.5816, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "4:10:30", "remaining_time": "9:59:01"}
116
+ {"current_steps": 116, "total_steps": 390, "loss": 0.5857, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "4:12:53", "remaining_time": "9:57:21"}
117
+ {"current_steps": 117, "total_steps": 390, "loss": 0.5855, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "4:14:56", "remaining_time": "9:54:50"}
118
+ {"current_steps": 118, "total_steps": 390, "loss": 0.5803, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "4:16:58", "remaining_time": "9:52:21"}
119
+ {"current_steps": 119, "total_steps": 390, "loss": 0.5739, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "4:19:03", "remaining_time": "9:49:56"}
120
+ {"current_steps": 120, "total_steps": 390, "loss": 0.5808, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "4:21:03", "remaining_time": "9:47:22"}
121
+ {"current_steps": 121, "total_steps": 390, "loss": 0.5811, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "4:23:03", "remaining_time": "9:44:48"}
122
+ {"current_steps": 122, "total_steps": 390, "loss": 0.5697, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "4:25:21", "remaining_time": "9:42:54"}
123
+ {"current_steps": 123, "total_steps": 390, "loss": 0.6, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "4:27:26", "remaining_time": "9:40:32"}
124
+ {"current_steps": 124, "total_steps": 390, "loss": 0.5785, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "4:29:39", "remaining_time": "9:38:27"}
125
+ {"current_steps": 125, "total_steps": 390, "loss": 0.5793, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "4:31:49", "remaining_time": "9:36:15"}
126
+ {"current_steps": 126, "total_steps": 390, "loss": 0.5829, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "4:34:08", "remaining_time": "9:34:23"}
127
+ {"current_steps": 127, "total_steps": 390, "loss": 0.5691, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "4:36:23", "remaining_time": "9:32:22"}
128
+ {"current_steps": 128, "total_steps": 390, "loss": 0.5977, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "4:38:33", "remaining_time": "9:30:10"}
129
+ {"current_steps": 129, "total_steps": 390, "loss": 0.5688, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "4:40:54", "remaining_time": "9:28:21"}
130
+ {"current_steps": 130, "total_steps": 390, "loss": 0.5692, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "4:43:04", "remaining_time": "9:26:08"}
131
+ {"current_steps": 131, "total_steps": 390, "loss": 0.5772, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "4:44:59", "remaining_time": "9:23:27"}
132
+ {"current_steps": 132, "total_steps": 390, "loss": 0.5774, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "4:47:08", "remaining_time": "9:21:13"}
133
+ {"current_steps": 133, "total_steps": 390, "loss": 0.5728, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "4:49:09", "remaining_time": "9:18:44"}
134
+ {"current_steps": 134, "total_steps": 390, "loss": 0.5641, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "4:51:27", "remaining_time": "9:16:48"}
135
+ {"current_steps": 135, "total_steps": 390, "loss": 0.5787, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "4:53:56", "remaining_time": "9:15:12"}
136
+ {"current_steps": 136, "total_steps": 390, "loss": 0.5899, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "4:55:58", "remaining_time": "9:12:47"}
137
+ {"current_steps": 137, "total_steps": 390, "loss": 0.5699, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "4:57:55", "remaining_time": "9:10:10"}
138
+ {"current_steps": 138, "total_steps": 390, "loss": 0.5846, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "5:00:15", "remaining_time": "9:08:16"}
139
+ {"current_steps": 139, "total_steps": 390, "loss": 0.5762, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "5:02:23", "remaining_time": "9:06:02"}
140
+ {"current_steps": 140, "total_steps": 390, "loss": 0.5751, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "5:04:26", "remaining_time": "9:03:39"}
141
+ {"current_steps": 141, "total_steps": 390, "loss": 0.5823, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "5:06:32", "remaining_time": "9:01:20"}
142
+ {"current_steps": 142, "total_steps": 390, "loss": 0.587, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "5:08:45", "remaining_time": "8:59:13"}
143
+ {"current_steps": 143, "total_steps": 390, "loss": 0.5836, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "5:10:49", "remaining_time": "8:56:52"}
144
+ {"current_steps": 144, "total_steps": 390, "loss": 0.5882, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "5:12:43", "remaining_time": "8:54:13"}
145
+ {"current_steps": 145, "total_steps": 390, "loss": 0.5717, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "5:14:44", "remaining_time": "8:51:47"}
146
+ {"current_steps": 146, "total_steps": 390, "loss": 0.5847, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "5:17:00", "remaining_time": "8:49:47"}
147
+ {"current_steps": 147, "total_steps": 390, "loss": 0.5897, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "5:19:20", "remaining_time": "8:47:53"}
148
+ {"current_steps": 148, "total_steps": 390, "loss": 0.5888, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "5:21:15", "remaining_time": "8:45:17"}
149
+ {"current_steps": 149, "total_steps": 390, "loss": 0.5492, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "5:23:07", "remaining_time": "8:42:38"}
150
+ {"current_steps": 150, "total_steps": 390, "loss": 0.5915, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "5:25:31", "remaining_time": "8:40:50"}
151
+ {"current_steps": 151, "total_steps": 390, "loss": 0.5934, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "5:27:51", "remaining_time": "8:38:55"}
152
+ {"current_steps": 152, "total_steps": 390, "loss": 0.5844, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "5:30:09", "remaining_time": "8:36:57"}
153
+ {"current_steps": 153, "total_steps": 390, "loss": 0.5934, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "5:32:10", "remaining_time": "8:34:32"}
154
+ {"current_steps": 154, "total_steps": 390, "loss": 0.6015, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "5:34:19", "remaining_time": "8:32:20"}
155
+ {"current_steps": 155, "total_steps": 390, "loss": 0.5831, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "5:36:30", "remaining_time": "8:30:10"}
156
+ {"current_steps": 156, "total_steps": 390, "loss": 0.5608, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "5:38:34", "remaining_time": "8:27:51"}
157
+ {"current_steps": 157, "total_steps": 390, "loss": 0.5186, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "5:41:37", "remaining_time": "8:26:59"}