ryanmarten commited on
Commit
f8824b4
·
verified ·
1 Parent(s): 0d15886

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:051d5668a04cc82311647f0e61fd60cf01d4d5e94004f6397c71d3a8a3da76c4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e452816ca12e79fe9d515667361b2ed8b7cc287562533670d90a46771982f51
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35ba29e4dfcdb83ec3838a8933550af71351c21be97e2dc957f374195a53b449
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4ac356d33d5b52ea74c7eca6c3b9b9aafc852dbe786858b54aadf84708d50b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79d8bef13c386a820ecc00732522b5e4e85e8e93cfba5a986264652edd9bb573
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c63fb31a280850f37f6ad69eef147bb25546a569be8605a1d160e2a1208cca
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:d538d8fa19241687206f65046e9ce847e7cd3028840eba86b1001974f2040ba1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad722f60c8fec2c544397a261581050bb0771c883e7b5d59b5cae36a92a6f64
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -119,3 +119,41 @@
119
  {"current_steps": 119, "total_steps": 190, "loss": 0.2093, "lr": 1.4734944608708022e-05, "epoch": 3.1006493506493507, "percentage": 62.63, "elapsed_time": "0:47:12", "remaining_time": "0:28:10"}
120
  {"current_steps": 120, "total_steps": 190, "loss": 0.2057, "lr": 1.4381376004528616e-05, "epoch": 3.1266233766233764, "percentage": 63.16, "elapsed_time": "0:47:36", "remaining_time": "0:27:46"}
121
  {"current_steps": 121, "total_steps": 190, "loss": 0.1884, "lr": 1.4029703779966116e-05, "epoch": 3.1525974025974026, "percentage": 63.68, "elapsed_time": "0:47:53", "remaining_time": "0:27:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  {"current_steps": 119, "total_steps": 190, "loss": 0.2093, "lr": 1.4734944608708022e-05, "epoch": 3.1006493506493507, "percentage": 62.63, "elapsed_time": "0:47:12", "remaining_time": "0:28:10"}
120
  {"current_steps": 120, "total_steps": 190, "loss": 0.2057, "lr": 1.4381376004528616e-05, "epoch": 3.1266233766233764, "percentage": 63.16, "elapsed_time": "0:47:36", "remaining_time": "0:27:46"}
121
  {"current_steps": 121, "total_steps": 190, "loss": 0.1884, "lr": 1.4029703779966116e-05, "epoch": 3.1525974025974026, "percentage": 63.68, "elapsed_time": "0:47:53", "remaining_time": "0:27:18"}
122
+ {"current_steps": 122, "total_steps": 190, "loss": 0.1977, "lr": 1.3680046630280952e-05, "epoch": 3.1785714285714284, "percentage": 64.21, "elapsed_time": "0:48:18", "remaining_time": "0:26:55"}
123
+ {"current_steps": 123, "total_steps": 190, "loss": 0.1891, "lr": 1.3332522570612097e-05, "epoch": 3.2045454545454546, "percentage": 64.74, "elapsed_time": "0:48:36", "remaining_time": "0:26:28"}
124
+ {"current_steps": 124, "total_steps": 190, "loss": 0.1912, "lr": 1.2987248896144915e-05, "epoch": 3.2305194805194803, "percentage": 65.26, "elapsed_time": "0:48:57", "remaining_time": "0:26:03"}
125
+ {"current_steps": 125, "total_steps": 190, "loss": 0.1982, "lr": 1.2644342142522142e-05, "epoch": 3.2564935064935066, "percentage": 65.79, "elapsed_time": "0:49:22", "remaining_time": "0:25:40"}
126
+ {"current_steps": 126, "total_steps": 190, "loss": 0.1825, "lr": 1.230391804651109e-05, "epoch": 3.2824675324675323, "percentage": 66.32, "elapsed_time": "0:49:40", "remaining_time": "0:25:13"}
127
+ {"current_steps": 127, "total_steps": 190, "loss": 0.1963, "lr": 1.1966091506940616e-05, "epoch": 3.3084415584415585, "percentage": 66.84, "elapsed_time": "0:50:02", "remaining_time": "0:24:49"}
128
+ {"current_steps": 128, "total_steps": 190, "loss": 0.1706, "lr": 1.1630976545920777e-05, "epoch": 3.3344155844155843, "percentage": 67.37, "elapsed_time": "0:50:26", "remaining_time": "0:24:25"}
129
+ {"current_steps": 129, "total_steps": 190, "loss": 0.1913, "lr": 1.1298686270358542e-05, "epoch": 3.3603896103896105, "percentage": 67.89, "elapsed_time": "0:50:49", "remaining_time": "0:24:01"}
130
+ {"current_steps": 130, "total_steps": 190, "loss": 0.1671, "lr": 1.0969332833782217e-05, "epoch": 3.3863636363636362, "percentage": 68.42, "elapsed_time": "0:51:07", "remaining_time": "0:23:35"}
131
+ {"current_steps": 131, "total_steps": 190, "loss": 0.1854, "lr": 1.0643027398487848e-05, "epoch": 3.4123376623376624, "percentage": 68.95, "elapsed_time": "0:51:29", "remaining_time": "0:23:11"}
132
+ {"current_steps": 132, "total_steps": 190, "loss": 0.1709, "lr": 1.031988009802003e-05, "epoch": 3.438311688311688, "percentage": 69.47, "elapsed_time": "0:51:51", "remaining_time": "0:22:47"}
133
+ {"current_steps": 133, "total_steps": 190, "loss": 0.1975, "lr": 1.0000000000000006e-05, "epoch": 3.4642857142857144, "percentage": 70.0, "elapsed_time": "0:52:19", "remaining_time": "0:22:25"}
134
+ {"current_steps": 134, "total_steps": 190, "loss": 0.1787, "lr": 9.683495069313527e-06, "epoch": 3.49025974025974, "percentage": 70.53, "elapsed_time": "0:52:40", "remaining_time": "0:22:00"}
135
+ {"current_steps": 135, "total_steps": 190, "loss": 0.1979, "lr": 9.370472131670887e-06, "epoch": 3.5162337662337664, "percentage": 71.05, "elapsed_time": "0:53:02", "remaining_time": "0:21:36"}
136
+ {"current_steps": 136, "total_steps": 190, "loss": 0.1672, "lr": 9.061036837551467e-06, "epoch": 3.542207792207792, "percentage": 71.58, "elapsed_time": "0:53:24", "remaining_time": "0:21:12"}
137
+ {"current_steps": 137, "total_steps": 190, "loss": 0.1578, "lr": 8.755293626544921e-06, "epoch": 3.5681818181818183, "percentage": 72.11, "elapsed_time": "0:53:44", "remaining_time": "0:20:47"}
138
+ {"current_steps": 138, "total_steps": 190, "loss": 0.1732, "lr": 8.453345692101076e-06, "epoch": 3.594155844155844, "percentage": 72.63, "elapsed_time": "0:54:05", "remaining_time": "0:20:22"}
139
+ {"current_steps": 139, "total_steps": 190, "loss": 0.1868, "lr": 8.155294946700402e-06, "epoch": 3.62012987012987, "percentage": 73.16, "elapsed_time": "0:54:28", "remaining_time": "0:19:59"}
140
+ {"current_steps": 140, "total_steps": 190, "loss": 0.1921, "lr": 7.861241987456869e-06, "epoch": 3.646103896103896, "percentage": 73.68, "elapsed_time": "0:54:54", "remaining_time": "0:19:36"}
141
+ {"current_steps": 141, "total_steps": 190, "loss": 0.1902, "lr": 7.571286062164709e-06, "epoch": 3.6720779220779223, "percentage": 74.21, "elapsed_time": "0:55:24", "remaining_time": "0:19:15"}
142
+ {"current_steps": 142, "total_steps": 190, "loss": 0.1885, "lr": 7.285525035800645e-06, "epoch": 3.698051948051948, "percentage": 74.74, "elapsed_time": "0:55:47", "remaining_time": "0:18:51"}
143
+ {"current_steps": 143, "total_steps": 190, "loss": 0.1646, "lr": 7.0040553574928115e-06, "epoch": 3.724025974025974, "percentage": 75.26, "elapsed_time": "0:56:08", "remaining_time": "0:18:27"}
144
+ {"current_steps": 144, "total_steps": 190, "loss": 0.1769, "lr": 6.7269720279675755e-06, "epoch": 3.75, "percentage": 75.79, "elapsed_time": "0:56:31", "remaining_time": "0:18:03"}
145
+ {"current_steps": 145, "total_steps": 190, "loss": 0.1927, "lr": 6.4543685674851834e-06, "epoch": 3.775974025974026, "percentage": 76.32, "elapsed_time": "0:56:53", "remaining_time": "0:17:39"}
146
+ {"current_steps": 146, "total_steps": 190, "loss": 0.1835, "lr": 6.1863369842751145e-06, "epoch": 3.801948051948052, "percentage": 76.84, "elapsed_time": "0:57:19", "remaining_time": "0:17:16"}
147
+ {"current_steps": 147, "total_steps": 190, "loss": 0.1912, "lr": 5.922967743481773e-06, "epoch": 3.8279220779220777, "percentage": 77.37, "elapsed_time": "0:57:44", "remaining_time": "0:16:53"}
148
+ {"current_steps": 148, "total_steps": 190, "loss": 0.1688, "lr": 5.664349736630979e-06, "epoch": 3.853896103896104, "percentage": 77.89, "elapsed_time": "0:58:12", "remaining_time": "0:16:31"}
149
+ {"current_steps": 149, "total_steps": 190, "loss": 0.202, "lr": 5.410570251627587e-06, "epoch": 3.87987012987013, "percentage": 78.42, "elapsed_time": "0:58:35", "remaining_time": "0:16:07"}
150
+ {"current_steps": 150, "total_steps": 190, "loss": 0.1841, "lr": 5.161714943294372e-06, "epoch": 3.905844155844156, "percentage": 78.95, "elapsed_time": "0:58:55", "remaining_time": "0:15:42"}
151
+ {"current_steps": 151, "total_steps": 190, "loss": 0.1819, "lr": 4.917867804462077e-06, "epoch": 3.9318181818181817, "percentage": 79.47, "elapsed_time": "0:59:17", "remaining_time": "0:15:18"}
152
+ {"current_steps": 152, "total_steps": 190, "loss": 0.187, "lr": 4.679111137620442e-06, "epoch": 3.957792207792208, "percentage": 80.0, "elapsed_time": "0:59:43", "remaining_time": "0:14:55"}
153
+ {"current_steps": 153, "total_steps": 190, "loss": 0.187, "lr": 4.445525527139725e-06, "epoch": 3.9837662337662336, "percentage": 80.53, "elapsed_time": "1:00:12", "remaining_time": "0:14:33"}
154
+ {"current_steps": 154, "total_steps": 190, "loss": 0.1686, "lr": 4.217189812072131e-06, "epoch": 4.012987012987013, "percentage": 81.05, "elapsed_time": "1:01:42", "remaining_time": "0:14:25"}
155
+ {"current_steps": 155, "total_steps": 190, "loss": 0.1176, "lr": 3.994181059542321e-06, "epoch": 4.038961038961039, "percentage": 81.58, "elapsed_time": "1:02:02", "remaining_time": "0:14:00"}
156
+ {"current_steps": 156, "total_steps": 190, "loss": 0.1154, "lr": 3.7765745387359574e-06, "epoch": 4.064935064935065, "percentage": 82.11, "elapsed_time": "1:02:32", "remaining_time": "0:13:37"}
157
+ {"current_steps": 157, "total_steps": 190, "loss": 0.1369, "lr": 3.564443695495099e-06, "epoch": 4.090909090909091, "percentage": 82.63, "elapsed_time": "1:03:00", "remaining_time": "0:13:14"}
158
+ {"current_steps": 158, "total_steps": 190, "loss": 0.1167, "lr": 3.357860127529e-06, "epoch": 4.116883116883117, "percentage": 83.16, "elapsed_time": "1:03:19", "remaining_time": "0:12:49"}
159
+ {"current_steps": 159, "total_steps": 190, "loss": 0.1242, "lr": 3.156893560248688e-06, "epoch": 4.142857142857143, "percentage": 83.68, "elapsed_time": "1:03:42", "remaining_time": "0:12:25"}