sedrickkeh commited on
Commit
344d377
·
verified ·
1 Parent(s): 63592bb

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:f2323030a1456390635c8b4e5f449b682a619123f01cc8b50e2d920ea2ce38ba
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f7041fe1a61af2f4151fbad3c23e55dd351b2b893c075b684c37bdd30fd1cb
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b124836fe0c38fb22b359785b9088cd64d5baad3add9c2be98d92b57bd79306
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5913a2db96d863c43288ad691ac16f528bd0eda930047205b506da340dfcad
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a76e13dea231215a4b7eb125f62d8452e93cac61f5fb9911095c09b57d1fae6d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf29e6e7c4770f3bf525f57d546335021bb46c165b378fe2b33150570e118ed
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bcee2a295e28bf02818709eac3bf41464601066ce4d4194b0eba070beedee38
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a8d3c86162c20264ad284dd17dfa5859e9ec5ca4becf6a2da062cd16b1e1cc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -152,3 +152,64 @@
152
  {"current_steps": 152, "total_steps": 315, "loss": 0.1673, "lr": 5.706846570773677e-06, "epoch": 2.4126984126984126, "percentage": 48.25, "elapsed_time": "0:13:59", "remaining_time": "0:15:00"}
153
  {"current_steps": 153, "total_steps": 315, "loss": 0.1474, "lr": 5.654801129740863e-06, "epoch": 2.4285714285714284, "percentage": 48.57, "elapsed_time": "0:14:04", "remaining_time": "0:14:54"}
154
  {"current_steps": 154, "total_steps": 315, "loss": 0.2067, "lr": 5.6026834012766155e-06, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "0:14:08", "remaining_time": "0:14:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  {"current_steps": 152, "total_steps": 315, "loss": 0.1673, "lr": 5.706846570773677e-06, "epoch": 2.4126984126984126, "percentage": 48.25, "elapsed_time": "0:13:59", "remaining_time": "0:15:00"}
153
  {"current_steps": 153, "total_steps": 315, "loss": 0.1474, "lr": 5.654801129740863e-06, "epoch": 2.4285714285714284, "percentage": 48.57, "elapsed_time": "0:14:04", "remaining_time": "0:14:54"}
154
  {"current_steps": 154, "total_steps": 315, "loss": 0.2067, "lr": 5.6026834012766155e-06, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "0:14:08", "remaining_time": "0:14:47"}
155
+ {"current_steps": 155, "total_steps": 315, "loss": 0.1449, "lr": 5.550499138970158e-06, "epoch": 2.4603174603174605, "percentage": 49.21, "elapsed_time": "0:14:13", "remaining_time": "0:14:40"}
156
+ {"current_steps": 156, "total_steps": 315, "loss": 0.1716, "lr": 5.4982541037557825e-06, "epoch": 2.4761904761904763, "percentage": 49.52, "elapsed_time": "0:14:17", "remaining_time": "0:14:34"}
157
+ {"current_steps": 157, "total_steps": 315, "loss": 0.1932, "lr": 5.44595406327687e-06, "epoch": 2.492063492063492, "percentage": 49.84, "elapsed_time": "0:14:22", "remaining_time": "0:14:28"}
158
+ {"current_steps": 158, "total_steps": 315, "loss": 0.1787, "lr": 5.393604791249158e-06, "epoch": 2.507936507936508, "percentage": 50.16, "elapsed_time": "0:14:27", "remaining_time": "0:14:21"}
159
+ {"current_steps": 159, "total_steps": 315, "loss": 0.1448, "lr": 5.341212066823356e-06, "epoch": 2.5238095238095237, "percentage": 50.48, "elapsed_time": "0:14:32", "remaining_time": "0:14:16"}
160
+ {"current_steps": 160, "total_steps": 315, "loss": 0.1788, "lr": 5.288781673947143e-06, "epoch": 2.5396825396825395, "percentage": 50.79, "elapsed_time": "0:14:37", "remaining_time": "0:14:09"}
161
+ {"current_steps": 161, "total_steps": 315, "loss": 0.1582, "lr": 5.2363194007266435e-06, "epoch": 2.5555555555555554, "percentage": 51.11, "elapsed_time": "0:14:41", "remaining_time": "0:14:03"}
162
+ {"current_steps": 162, "total_steps": 315, "loss": 0.1242, "lr": 5.183831038787449e-06, "epoch": 2.571428571428571, "percentage": 51.43, "elapsed_time": "0:14:46", "remaining_time": "0:13:56"}
163
+ {"current_steps": 163, "total_steps": 315, "loss": 0.1534, "lr": 5.131322382635236e-06, "epoch": 2.5873015873015874, "percentage": 51.75, "elapsed_time": "0:14:51", "remaining_time": "0:13:50"}
164
+ {"current_steps": 164, "total_steps": 315, "loss": 0.1479, "lr": 5.078799229016083e-06, "epoch": 2.6031746031746033, "percentage": 52.06, "elapsed_time": "0:14:55", "remaining_time": "0:13:44"}
165
+ {"current_steps": 165, "total_steps": 315, "loss": 0.1646, "lr": 5.0262673762765316e-06, "epoch": 2.619047619047619, "percentage": 52.38, "elapsed_time": "0:14:59", "remaining_time": "0:13:38"}
166
+ {"current_steps": 166, "total_steps": 315, "loss": 0.1708, "lr": 4.973732623723471e-06, "epoch": 2.634920634920635, "percentage": 52.7, "elapsed_time": "0:15:04", "remaining_time": "0:13:31"}
167
+ {"current_steps": 167, "total_steps": 315, "loss": 0.1294, "lr": 4.921200770983919e-06, "epoch": 2.6507936507936507, "percentage": 53.02, "elapsed_time": "0:15:09", "remaining_time": "0:13:26"}
168
+ {"current_steps": 168, "total_steps": 315, "loss": 0.1558, "lr": 4.8686776173647655e-06, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:15:15", "remaining_time": "0:13:20"}
169
+ {"current_steps": 169, "total_steps": 315, "loss": 0.1592, "lr": 4.816168961212553e-06, "epoch": 2.682539682539683, "percentage": 53.65, "elapsed_time": "0:15:19", "remaining_time": "0:13:14"}
170
+ {"current_steps": 170, "total_steps": 315, "loss": 0.1494, "lr": 4.763680599273357e-06, "epoch": 2.6984126984126986, "percentage": 53.97, "elapsed_time": "0:15:24", "remaining_time": "0:13:08"}
171
+ {"current_steps": 171, "total_steps": 315, "loss": 0.189, "lr": 4.711218326052859e-06, "epoch": 2.7142857142857144, "percentage": 54.29, "elapsed_time": "0:15:29", "remaining_time": "0:13:02"}
172
+ {"current_steps": 172, "total_steps": 315, "loss": 0.1343, "lr": 4.6587879331766465e-06, "epoch": 2.7301587301587302, "percentage": 54.6, "elapsed_time": "0:15:34", "remaining_time": "0:12:56"}
173
+ {"current_steps": 173, "total_steps": 315, "loss": 0.1931, "lr": 4.606395208750844e-06, "epoch": 2.746031746031746, "percentage": 54.92, "elapsed_time": "0:15:39", "remaining_time": "0:12:50"}
174
+ {"current_steps": 174, "total_steps": 315, "loss": 0.1393, "lr": 4.554045936723132e-06, "epoch": 2.761904761904762, "percentage": 55.24, "elapsed_time": "0:15:43", "remaining_time": "0:12:44"}
175
+ {"current_steps": 175, "total_steps": 315, "loss": 0.1446, "lr": 4.501745896244219e-06, "epoch": 2.7777777777777777, "percentage": 55.56, "elapsed_time": "0:15:48", "remaining_time": "0:12:38"}
176
+ {"current_steps": 176, "total_steps": 315, "loss": 0.1862, "lr": 4.4495008610298435e-06, "epoch": 2.7936507936507935, "percentage": 55.87, "elapsed_time": "0:15:53", "remaining_time": "0:12:33"}
177
+ {"current_steps": 177, "total_steps": 315, "loss": 0.1534, "lr": 4.397316598723385e-06, "epoch": 2.8095238095238093, "percentage": 56.19, "elapsed_time": "0:15:58", "remaining_time": "0:12:27"}
178
+ {"current_steps": 178, "total_steps": 315, "loss": 0.1519, "lr": 4.345198870259139e-06, "epoch": 2.825396825396825, "percentage": 56.51, "elapsed_time": "0:16:03", "remaining_time": "0:12:21"}
179
+ {"current_steps": 179, "total_steps": 315, "loss": 0.1756, "lr": 4.2931534292263265e-06, "epoch": 2.8412698412698414, "percentage": 56.83, "elapsed_time": "0:16:09", "remaining_time": "0:12:16"}
180
+ {"current_steps": 180, "total_steps": 315, "loss": 0.1506, "lr": 4.241186021233925e-06, "epoch": 2.857142857142857, "percentage": 57.14, "elapsed_time": "0:16:13", "remaining_time": "0:12:10"}
181
+ {"current_steps": 181, "total_steps": 315, "loss": 0.1507, "lr": 4.189302383276378e-06, "epoch": 2.873015873015873, "percentage": 57.46, "elapsed_time": "0:16:18", "remaining_time": "0:12:04"}
182
+ {"current_steps": 182, "total_steps": 315, "loss": 0.1472, "lr": 4.137508243100249e-06, "epoch": 2.888888888888889, "percentage": 57.78, "elapsed_time": "0:16:22", "remaining_time": "0:11:58"}
183
+ {"current_steps": 183, "total_steps": 315, "loss": 0.1738, "lr": 4.085809318571905e-06, "epoch": 2.9047619047619047, "percentage": 58.1, "elapsed_time": "0:16:27", "remaining_time": "0:11:52"}
184
+ {"current_steps": 184, "total_steps": 315, "loss": 0.1747, "lr": 4.034211317046285e-06, "epoch": 2.9206349206349205, "percentage": 58.41, "elapsed_time": "0:16:32", "remaining_time": "0:11:46"}
185
+ {"current_steps": 185, "total_steps": 315, "loss": 0.1544, "lr": 3.982719934736832e-06, "epoch": 2.9365079365079367, "percentage": 58.73, "elapsed_time": "0:16:37", "remaining_time": "0:11:40"}
186
+ {"current_steps": 186, "total_steps": 315, "loss": 0.1247, "lr": 3.931340856086652e-06, "epoch": 2.9523809523809526, "percentage": 59.05, "elapsed_time": "0:16:42", "remaining_time": "0:11:35"}
187
+ {"current_steps": 187, "total_steps": 315, "loss": 0.1405, "lr": 3.880079753140978e-06, "epoch": 2.9682539682539684, "percentage": 59.37, "elapsed_time": "0:16:47", "remaining_time": "0:11:29"}
188
+ {"current_steps": 188, "total_steps": 315, "loss": 0.18, "lr": 3.82894228492099e-06, "epoch": 2.984126984126984, "percentage": 59.68, "elapsed_time": "0:16:51", "remaining_time": "0:11:23"}
189
+ {"current_steps": 189, "total_steps": 315, "loss": 0.133, "lr": 3.777934096799094e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:16:56", "remaining_time": "0:11:17"}
190
+ {"current_steps": 190, "total_steps": 315, "loss": 0.0625, "lr": 3.7270608198756852e-06, "epoch": 3.015873015873016, "percentage": 60.32, "elapsed_time": "0:18:02", "remaining_time": "0:11:52"}
191
+ {"current_steps": 191, "total_steps": 315, "loss": 0.124, "lr": 3.676328070357503e-06, "epoch": 3.0317460317460316, "percentage": 60.63, "elapsed_time": "0:18:07", "remaining_time": "0:11:46"}
192
+ {"current_steps": 192, "total_steps": 315, "loss": 0.0867, "lr": 3.6257414489376217e-06, "epoch": 3.0476190476190474, "percentage": 60.95, "elapsed_time": "0:18:12", "remaining_time": "0:11:39"}
193
+ {"current_steps": 193, "total_steps": 315, "loss": 0.079, "lr": 3.5753065401771577e-06, "epoch": 3.0634920634920633, "percentage": 61.27, "elapsed_time": "0:18:17", "remaining_time": "0:11:33"}
194
+ {"current_steps": 194, "total_steps": 315, "loss": 0.0736, "lr": 3.5250289118887515e-06, "epoch": 3.0793650793650795, "percentage": 61.59, "elapsed_time": "0:18:22", "remaining_time": "0:11:27"}
195
+ {"current_steps": 195, "total_steps": 315, "loss": 0.0768, "lr": 3.4749141145219118e-06, "epoch": 3.0952380952380953, "percentage": 61.9, "elapsed_time": "0:18:27", "remaining_time": "0:11:21"}
196
+ {"current_steps": 196, "total_steps": 315, "loss": 0.0748, "lr": 3.424967680550261e-06, "epoch": 3.111111111111111, "percentage": 62.22, "elapsed_time": "0:18:31", "remaining_time": "0:11:14"}
197
+ {"current_steps": 197, "total_steps": 315, "loss": 0.101, "lr": 3.3751951238607745e-06, "epoch": 3.126984126984127, "percentage": 62.54, "elapsed_time": "0:18:35", "remaining_time": "0:11:08"}
198
+ {"current_steps": 198, "total_steps": 315, "loss": 0.0662, "lr": 3.3256019391450696e-06, "epoch": 3.142857142857143, "percentage": 62.86, "elapsed_time": "0:18:40", "remaining_time": "0:11:02"}
199
+ {"current_steps": 199, "total_steps": 315, "loss": 0.0731, "lr": 3.2761936012928147e-06, "epoch": 3.1587301587301586, "percentage": 63.17, "elapsed_time": "0:18:45", "remaining_time": "0:10:55"}
200
+ {"current_steps": 200, "total_steps": 315, "loss": 0.0725, "lr": 3.226975564787322e-06, "epoch": 3.1746031746031744, "percentage": 63.49, "elapsed_time": "0:18:50", "remaining_time": "0:10:50"}
201
+ {"current_steps": 201, "total_steps": 315, "loss": 0.0957, "lr": 3.177953263103394e-06, "epoch": 3.1904761904761907, "percentage": 63.81, "elapsed_time": "0:18:55", "remaining_time": "0:10:44"}
202
+ {"current_steps": 202, "total_steps": 315, "loss": 0.1012, "lr": 3.1291321081074887e-06, "epoch": 3.2063492063492065, "percentage": 64.13, "elapsed_time": "0:19:01", "remaining_time": "0:10:38"}
203
+ {"current_steps": 203, "total_steps": 315, "loss": 0.0683, "lr": 3.0805174894602775e-06, "epoch": 3.2222222222222223, "percentage": 64.44, "elapsed_time": "0:19:06", "remaining_time": "0:10:32"}
204
+ {"current_steps": 204, "total_steps": 315, "loss": 0.0834, "lr": 3.032114774021636e-06, "epoch": 3.238095238095238, "percentage": 64.76, "elapsed_time": "0:19:12", "remaining_time": "0:10:27"}
205
+ {"current_steps": 205, "total_steps": 315, "loss": 0.081, "lr": 2.9839293052581767e-06, "epoch": 3.253968253968254, "percentage": 65.08, "elapsed_time": "0:19:17", "remaining_time": "0:10:21"}
206
+ {"current_steps": 206, "total_steps": 315, "loss": 0.0698, "lr": 2.9359664026533443e-06, "epoch": 3.2698412698412698, "percentage": 65.4, "elapsed_time": "0:19:22", "remaining_time": "0:10:15"}
207
+ {"current_steps": 207, "total_steps": 315, "loss": 0.0795, "lr": 2.8882313611201684e-06, "epoch": 3.2857142857142856, "percentage": 65.71, "elapsed_time": "0:19:27", "remaining_time": "0:10:09"}
208
+ {"current_steps": 208, "total_steps": 315, "loss": 0.0929, "lr": 2.8407294504167238e-06, "epoch": 3.3015873015873014, "percentage": 66.03, "elapsed_time": "0:19:32", "remaining_time": "0:10:03"}
209
+ {"current_steps": 209, "total_steps": 315, "loss": 0.0832, "lr": 2.793465914564375e-06, "epoch": 3.317460317460317, "percentage": 66.35, "elapsed_time": "0:19:37", "remaining_time": "0:09:57"}
210
+ {"current_steps": 210, "total_steps": 315, "loss": 0.0827, "lr": 2.7464459712688517e-06, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:19:43", "remaining_time": "0:09:51"}
211
+ {"current_steps": 211, "total_steps": 315, "loss": 0.0938, "lr": 2.6996748113442397e-06, "epoch": 3.3492063492063493, "percentage": 66.98, "elapsed_time": "0:19:48", "remaining_time": "0:09:45"}
212
+ {"current_steps": 212, "total_steps": 315, "loss": 0.0807, "lr": 2.653157598139932e-06, "epoch": 3.365079365079365, "percentage": 67.3, "elapsed_time": "0:19:52", "remaining_time": "0:09:39"}
213
+ {"current_steps": 213, "total_steps": 315, "loss": 0.0645, "lr": 2.6068994669706184e-06, "epoch": 3.380952380952381, "percentage": 67.62, "elapsed_time": "0:19:58", "remaining_time": "0:09:33"}
214
+ {"current_steps": 214, "total_steps": 315, "loss": 0.0976, "lr": 2.560905524549364e-06, "epoch": 3.3968253968253967, "percentage": 67.94, "elapsed_time": "0:20:03", "remaining_time": "0:09:27"}
215
+ {"current_steps": 215, "total_steps": 315, "loss": 0.0732, "lr": 2.515180848423853e-06, "epoch": 3.4126984126984126, "percentage": 68.25, "elapsed_time": "0:20:08", "remaining_time": "0:09:22"}