ryanmarten commited on
Commit
f60c2c5
·
verified ·
1 Parent(s): f8824b4

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e452816ca12e79fe9d515667361b2ed8b7cc287562533670d90a46771982f51
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6bef6dde5f1e7c29b8f803ac0223e3296481cc038eae2801a54346be8cf6c27
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:bc4ac356d33d5b52ea74c7eca6c3b9b9aafc852dbe786858b54aadf84708d50b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd89205383a25e7ffca30a8bc6a6cf1182f5e414e36823bb464fdb1c75527b1
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01c63fb31a280850f37f6ad69eef147bb25546a569be8605a1d160e2a1208cca
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe0a8595dede6b8f9488203299b020b2260701609156d463fa26269205dd304
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad722f60c8fec2c544397a261581050bb0771c883e7b5d59b5cae36a92a6f64
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf1ee2ff5ec23c4ea416f0504264a386161376de02e902c0137b8150f29be58
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -157,3 +157,35 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
160
+ {"current_steps": 160, "total_steps": 190, "loss": 0.1187, "lr": 2.9616118232334613e-06, "epoch": 4.1688311688311686, "percentage": 84.21, "elapsed_time": "1:04:04", "remaining_time": "0:12:00"}
161
+ {"current_steps": 161, "total_steps": 190, "loss": 0.1143, "lr": 2.7720808273372823e-06, "epoch": 4.194805194805195, "percentage": 84.74, "elapsed_time": "1:04:25", "remaining_time": "0:11:36"}
162
+ {"current_steps": 162, "total_steps": 190, "loss": 0.1267, "lr": 2.588364542442754e-06, "epoch": 4.220779220779221, "percentage": 85.26, "elapsed_time": "1:04:48", "remaining_time": "0:11:12"}
163
+ {"current_steps": 163, "total_steps": 190, "loss": 0.127, "lr": 2.410524975870221e-06, "epoch": 4.246753246753247, "percentage": 85.79, "elapsed_time": "1:05:08", "remaining_time": "0:10:47"}
164
+ {"current_steps": 164, "total_steps": 190, "loss": 0.132, "lr": 2.2386221514492502e-06, "epoch": 4.2727272727272725, "percentage": 86.32, "elapsed_time": "1:05:36", "remaining_time": "0:10:24"}
165
+ {"current_steps": 165, "total_steps": 190, "loss": 0.1249, "lr": 2.0727140892595998e-06, "epoch": 4.298701298701299, "percentage": 86.84, "elapsed_time": "1:05:57", "remaining_time": "0:09:59"}
166
+ {"current_steps": 166, "total_steps": 190, "loss": 0.1297, "lr": 1.9128567860484516e-06, "epoch": 4.324675324675325, "percentage": 87.37, "elapsed_time": "1:06:20", "remaining_time": "0:09:35"}
167
+ {"current_steps": 167, "total_steps": 190, "loss": 0.1163, "lr": 1.759104196330592e-06, "epoch": 4.35064935064935, "percentage": 87.89, "elapsed_time": "1:06:40", "remaining_time": "0:09:10"}
168
+ {"current_steps": 168, "total_steps": 190, "loss": 0.1219, "lr": 1.6115082141778459e-06, "epoch": 4.376623376623376, "percentage": 88.42, "elapsed_time": "1:07:05", "remaining_time": "0:08:47"}
169
+ {"current_steps": 169, "total_steps": 190, "loss": 0.1096, "lr": 1.4701186557039648e-06, "epoch": 4.402597402597403, "percentage": 88.95, "elapsed_time": "1:07:28", "remaining_time": "0:08:23"}
170
+ {"current_steps": 170, "total_steps": 190, "loss": 0.1097, "lr": 1.334983242250858e-06, "epoch": 4.428571428571429, "percentage": 89.47, "elapsed_time": "1:07:55", "remaining_time": "0:07:59"}
171
+ {"current_steps": 171, "total_steps": 190, "loss": 0.1279, "lr": 1.2061475842818337e-06, "epoch": 4.454545454545454, "percentage": 90.0, "elapsed_time": "1:08:15", "remaining_time": "0:07:35"}
172
+ {"current_steps": 172, "total_steps": 190, "loss": 0.123, "lr": 1.0836551659873073e-06, "epoch": 4.48051948051948, "percentage": 90.53, "elapsed_time": "1:08:36", "remaining_time": "0:07:10"}
173
+ {"current_steps": 173, "total_steps": 190, "loss": 0.1189, "lr": 9.67547330608165e-07, "epoch": 4.5064935064935066, "percentage": 91.05, "elapsed_time": "1:09:01", "remaining_time": "0:06:46"}
174
+ {"current_steps": 174, "total_steps": 190, "loss": 0.1249, "lr": 8.578632664817177e-07, "epoch": 4.532467532467533, "percentage": 91.58, "elapsed_time": "1:09:26", "remaining_time": "0:06:23"}
175
+ {"current_steps": 175, "total_steps": 190, "loss": 0.1137, "lr": 7.546399938149918e-07, "epoch": 4.558441558441558, "percentage": 92.11, "elapsed_time": "1:09:44", "remaining_time": "0:05:58"}
176
+ {"current_steps": 176, "total_steps": 190, "loss": 0.1015, "lr": 6.579123521897867e-07, "epoch": 4.584415584415584, "percentage": 92.63, "elapsed_time": "1:10:06", "remaining_time": "0:05:34"}
177
+ {"current_steps": 177, "total_steps": 190, "loss": 0.1126, "lr": 5.677129888037236e-07, "epoch": 4.6103896103896105, "percentage": 93.16, "elapsed_time": "1:10:25", "remaining_time": "0:05:10"}
178
+ {"current_steps": 178, "total_steps": 190, "loss": 0.123, "lr": 4.840723474512876e-07, "epoch": 4.636363636363637, "percentage": 93.68, "elapsed_time": "1:10:50", "remaining_time": "0:04:46"}
179
+ {"current_steps": 179, "total_steps": 190, "loss": 0.1227, "lr": 4.070186582485214e-07, "epoch": 4.662337662337662, "percentage": 94.21, "elapsed_time": "1:11:13", "remaining_time": "0:04:22"}
180
+ {"current_steps": 180, "total_steps": 190, "loss": 0.1265, "lr": 3.3657792810489975e-07, "epoch": 4.688311688311688, "percentage": 94.74, "elapsed_time": "1:11:33", "remaining_time": "0:03:58"}
181
+ {"current_steps": 181, "total_steps": 190, "loss": 0.0993, "lr": 2.7277393194555357e-07, "epoch": 4.714285714285714, "percentage": 95.26, "elapsed_time": "1:11:51", "remaining_time": "0:03:34"}
182
+ {"current_steps": 182, "total_steps": 190, "loss": 0.1271, "lr": 2.1562820468684187e-07, "epoch": 4.740259740259741, "percentage": 95.79, "elapsed_time": "1:12:14", "remaining_time": "0:03:10"}
183
+ {"current_steps": 183, "total_steps": 190, "loss": 0.132, "lr": 1.6516003396795489e-07, "epoch": 4.766233766233766, "percentage": 96.32, "elapsed_time": "1:12:34", "remaining_time": "0:02:46"}
184
+ {"current_steps": 184, "total_steps": 190, "loss": 0.099, "lr": 1.2138645364101032e-07, "epoch": 4.792207792207792, "percentage": 96.84, "elapsed_time": "1:12:52", "remaining_time": "0:02:22"}
185
+ {"current_steps": 185, "total_steps": 190, "loss": 0.1111, "lr": 8.432223802185002e-08, "epoch": 4.818181818181818, "percentage": 97.37, "elapsed_time": "1:13:14", "remaining_time": "0:01:58"}
186
+ {"current_steps": 186, "total_steps": 190, "loss": 0.1229, "lr": 5.3979896903453287e-08, "epoch": 4.8441558441558445, "percentage": 97.89, "elapsed_time": "1:13:38", "remaining_time": "0:01:35"}
187
+ {"current_steps": 187, "total_steps": 190, "loss": 0.1303, "lr": 3.036967133367652e-08, "epoch": 4.87012987012987, "percentage": 98.42, "elapsed_time": "1:14:00", "remaining_time": "0:01:11"}
188
+ {"current_steps": 188, "total_steps": 190, "loss": 0.1212, "lr": 1.349953015872707e-08, "epoch": 4.896103896103896, "percentage": 98.95, "elapsed_time": "1:14:22", "remaining_time": "0:00:47"}
189
+ {"current_steps": 189, "total_steps": 190, "loss": 0.1268, "lr": 3.3751673335458147e-09, "epoch": 4.922077922077922, "percentage": 99.47, "elapsed_time": "1:14:44", "remaining_time": "0:00:23"}
190
+ {"current_steps": 190, "total_steps": 190, "loss": 0.1421, "lr": 0.0, "epoch": 4.948051948051948, "percentage": 100.0, "elapsed_time": "1:15:09", "remaining_time": "0:00:00"}
191
+ {"current_steps": 190, "total_steps": 190, "epoch": 4.948051948051948, "percentage": 100.0, "elapsed_time": "1:16:31", "remaining_time": "0:00:00"}