neginr commited on
Commit
7d895df
·
verified ·
1 Parent(s): fffe8ee

Training in progress, epoch 6

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:648a1707617f0d5d7802362e674a749d91009149c84c46b935d37cdfa66221f5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d120e057ceca23d213004b724fcbbe67a45af1f565dab7df6387712968d22d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17e77b2e3afe3483549354e3104d99b4793cb854b6e47d750cce5aa0a09f3787
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb923283f5efbd513fd617e7b1eca6b4aed2638c32dee564e3dee534130f5ac4
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58a873e60cb31b57982dc07b1f853dd3f5fa274f07d121918de07d60a97e36ee
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4652215f44c9d46f19fc1aeb787f8d85222c58d12d0711d331aee86c9458f95
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3747267143881247e904c85e241a85b381348fbf0f773eee248f5591eb40e20f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bdd420700ba49a6dc1b995d52679108a06ec22b912eea0126b4416b0661ec99
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -177,3 +177,36 @@
177
  {"current_steps": 177, "total_steps": 231, "loss": 0.1645, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "0:44:06", "remaining_time": "0:13:27"}
178
  {"current_steps": 178, "total_steps": 231, "loss": 0.1588, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "0:44:19", "remaining_time": "0:13:11"}
179
  {"current_steps": 179, "total_steps": 231, "loss": 0.1397, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "0:44:34", "remaining_time": "0:12:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  {"current_steps": 177, "total_steps": 231, "loss": 0.1645, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "0:44:06", "remaining_time": "0:13:27"}
178
  {"current_steps": 178, "total_steps": 231, "loss": 0.1588, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "0:44:19", "remaining_time": "0:13:11"}
179
  {"current_steps": 179, "total_steps": 231, "loss": 0.1397, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "0:44:34", "remaining_time": "0:12:56"}
180
+ {"current_steps": 180, "total_steps": 231, "loss": 0.1394, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "0:44:45", "remaining_time": "0:12:40"}
181
+ {"current_steps": 181, "total_steps": 231, "loss": 0.1592, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "0:45:01", "remaining_time": "0:12:26"}
182
+ {"current_steps": 182, "total_steps": 231, "loss": 0.1585, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "0:45:13", "remaining_time": "0:12:10"}
183
+ {"current_steps": 183, "total_steps": 231, "loss": 0.1705, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "0:45:26", "remaining_time": "0:11:55"}
184
+ {"current_steps": 184, "total_steps": 231, "loss": 0.156, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "0:45:37", "remaining_time": "0:11:39"}
185
+ {"current_steps": 185, "total_steps": 231, "loss": 0.1623, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "0:45:49", "remaining_time": "0:11:23"}
186
+ {"current_steps": 186, "total_steps": 231, "loss": 0.1323, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "0:45:59", "remaining_time": "0:11:07"}
187
+ {"current_steps": 187, "total_steps": 231, "loss": 0.1356, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "0:46:12", "remaining_time": "0:10:52"}
188
+ {"current_steps": 188, "total_steps": 231, "loss": 0.1368, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "0:46:23", "remaining_time": "0:10:36"}
189
+ {"current_steps": 189, "total_steps": 231, "loss": 0.1395, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "0:46:32", "remaining_time": "0:10:20"}
190
+ {"current_steps": 190, "total_steps": 231, "loss": 0.1739, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "0:46:45", "remaining_time": "0:10:05"}
191
+ {"current_steps": 191, "total_steps": 231, "loss": 0.124, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "0:46:59", "remaining_time": "0:09:50"}
192
+ {"current_steps": 192, "total_steps": 231, "loss": 0.1823, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "0:47:10", "remaining_time": "0:09:34"}
193
+ {"current_steps": 193, "total_steps": 231, "loss": 0.1589, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "0:47:20", "remaining_time": "0:09:19"}
194
+ {"current_steps": 194, "total_steps": 231, "loss": 0.1599, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "0:47:35", "remaining_time": "0:09:04"}
195
+ {"current_steps": 195, "total_steps": 231, "loss": 0.1342, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "0:47:48", "remaining_time": "0:08:49"}
196
+ {"current_steps": 196, "total_steps": 231, "loss": 0.1328, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "0:48:01", "remaining_time": "0:08:34"}
197
+ {"current_steps": 197, "total_steps": 231, "loss": 0.1656, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "0:48:14", "remaining_time": "0:08:19"}
198
+ {"current_steps": 198, "total_steps": 231, "loss": 0.1448, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "0:48:27", "remaining_time": "0:08:04"}
199
+ {"current_steps": 199, "total_steps": 231, "loss": 0.1431, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "0:50:22", "remaining_time": "0:08:05"}
200
+ {"current_steps": 200, "total_steps": 231, "loss": 0.1565, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "0:50:34", "remaining_time": "0:07:50"}
201
+ {"current_steps": 201, "total_steps": 231, "loss": 0.1085, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "0:50:43", "remaining_time": "0:07:34"}
202
+ {"current_steps": 202, "total_steps": 231, "loss": 0.1434, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "0:50:54", "remaining_time": "0:07:18"}
203
+ {"current_steps": 203, "total_steps": 231, "loss": 0.1399, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "0:51:05", "remaining_time": "0:07:02"}
204
+ {"current_steps": 204, "total_steps": 231, "loss": 0.1402, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "0:51:19", "remaining_time": "0:06:47"}
205
+ {"current_steps": 205, "total_steps": 231, "loss": 0.1518, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "0:51:34", "remaining_time": "0:06:32"}
206
+ {"current_steps": 206, "total_steps": 231, "loss": 0.13, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "0:51:46", "remaining_time": "0:06:16"}
207
+ {"current_steps": 207, "total_steps": 231, "loss": 0.1387, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "0:51:56", "remaining_time": "0:06:01"}
208
+ {"current_steps": 208, "total_steps": 231, "loss": 0.1549, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "0:52:08", "remaining_time": "0:05:45"}
209
+ {"current_steps": 209, "total_steps": 231, "loss": 0.1109, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "0:52:16", "remaining_time": "0:05:30"}
210
+ {"current_steps": 210, "total_steps": 231, "loss": 0.15, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "0:52:30", "remaining_time": "0:05:15"}
211
+ {"current_steps": 211, "total_steps": 231, "loss": 0.1368, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "0:52:42", "remaining_time": "0:04:59"}
212
+ {"current_steps": 212, "total_steps": 231, "loss": 0.1636, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "0:52:56", "remaining_time": "0:04:44"}