gsmyrnis commited on
Commit
da18204
·
verified ·
1 Parent(s): ef0841b

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4234deb664e95835f1a4c3b496754b23cadb527b27be635c31c5d5eadecfe0b2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794934ab7c1df78bae95447b82a3ca6a285b83b13cf814946f127635b8142af1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:625ff49b3037e2326d1b25c56859ea003d9236f39bdf1ba1cb7e4bafdb066dec
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a116d61df965ddde4dbe0aba6fc31bcdbab5d7114fe0783e5bb49d3cd71d9704
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:e73f0f278884577757a918d715a8bc518902d4b7fceccd74e15533349255afa9
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d654906298bebb818f2735759ee6c59bba2ef6515b11f1894f3e8c57280be3
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f11a8d3ff8e5447e511a978519b8b0f9bce76bba932fe9b56c88483cc1a880
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b345b4b5bae15ddba03d401b335db4249f3d23ab33b13b67bc3db4c4ab1a9cc5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -165,3 +165,71 @@
165
  {"current_steps": 165, "total_steps": 234, "loss": 0.6573, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:42:59", "remaining_time": "0:17:58"}
166
  {"current_steps": 166, "total_steps": 234, "loss": 0.6132, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:43:13", "remaining_time": "0:17:42"}
167
  {"current_steps": 167, "total_steps": 234, "loss": 0.6436, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:43:25", "remaining_time": "0:17:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165
  {"current_steps": 165, "total_steps": 234, "loss": 0.6573, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:42:59", "remaining_time": "0:17:58"}
166
  {"current_steps": 166, "total_steps": 234, "loss": 0.6132, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:43:13", "remaining_time": "0:17:42"}
167
  {"current_steps": 167, "total_steps": 234, "loss": 0.6436, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:43:25", "remaining_time": "0:17:25"}
168
+ {"current_steps": 168, "total_steps": 234, "loss": 0.7057, "lr": 2.245515092739488e-06, "epoch": 2.1446808510638298, "percentage": 71.79, "elapsed_time": "0:43:40", "remaining_time": "0:17:09"}
169
+ {"current_steps": 169, "total_steps": 234, "loss": 0.6898, "lr": 2.1833997096818897e-06, "epoch": 2.157446808510638, "percentage": 72.22, "elapsed_time": "0:43:58", "remaining_time": "0:16:54"}
170
+ {"current_steps": 170, "total_steps": 234, "loss": 0.6066, "lr": 2.1219146715716332e-06, "epoch": 2.1702127659574466, "percentage": 72.65, "elapsed_time": "0:44:15", "remaining_time": "0:16:39"}
171
+ {"current_steps": 171, "total_steps": 234, "loss": 0.7451, "lr": 2.061073738537635e-06, "epoch": 2.1829787234042555, "percentage": 73.08, "elapsed_time": "0:44:31", "remaining_time": "0:16:24"}
172
+ {"current_steps": 172, "total_steps": 234, "loss": 0.6688, "lr": 2.0008905265604316e-06, "epoch": 2.195744680851064, "percentage": 73.5, "elapsed_time": "0:44:47", "remaining_time": "0:16:08"}
173
+ {"current_steps": 173, "total_steps": 234, "loss": 0.7059, "lr": 1.941378504424968e-06, "epoch": 2.2085106382978723, "percentage": 73.93, "elapsed_time": "0:45:02", "remaining_time": "0:15:53"}
174
+ {"current_steps": 174, "total_steps": 234, "loss": 0.6934, "lr": 1.8825509907063328e-06, "epoch": 2.2212765957446807, "percentage": 74.36, "elapsed_time": "0:45:20", "remaining_time": "0:15:38"}
175
+ {"current_steps": 175, "total_steps": 234, "loss": 0.6081, "lr": 1.8244211507891064e-06, "epoch": 2.2340425531914896, "percentage": 74.79, "elapsed_time": "0:45:32", "remaining_time": "0:15:21"}
176
+ {"current_steps": 176, "total_steps": 234, "loss": 0.7652, "lr": 1.7670019939210025e-06, "epoch": 2.246808510638298, "percentage": 75.21, "elapsed_time": "0:45:46", "remaining_time": "0:15:05"}
177
+ {"current_steps": 177, "total_steps": 234, "loss": 0.7186, "lr": 1.7103063703014372e-06, "epoch": 2.2595744680851064, "percentage": 75.64, "elapsed_time": "0:46:00", "remaining_time": "0:14:48"}
178
+ {"current_steps": 178, "total_steps": 234, "loss": 0.6669, "lr": 1.6543469682057105e-06, "epoch": 2.272340425531915, "percentage": 76.07, "elapsed_time": "0:46:15", "remaining_time": "0:14:33"}
179
+ {"current_steps": 179, "total_steps": 234, "loss": 0.6817, "lr": 1.5991363111454023e-06, "epoch": 2.2851063829787233, "percentage": 76.5, "elapsed_time": "0:46:31", "remaining_time": "0:14:17"}
180
+ {"current_steps": 180, "total_steps": 234, "loss": 0.6174, "lr": 1.544686755065677e-06, "epoch": 2.297872340425532, "percentage": 76.92, "elapsed_time": "0:46:46", "remaining_time": "0:14:01"}
181
+ {"current_steps": 181, "total_steps": 234, "loss": 0.6884, "lr": 1.4910104855800429e-06, "epoch": 2.3106382978723405, "percentage": 77.35, "elapsed_time": "0:46:56", "remaining_time": "0:13:44"}
182
+ {"current_steps": 182, "total_steps": 234, "loss": 0.6935, "lr": 1.438119515243277e-06, "epoch": 2.323404255319149, "percentage": 77.78, "elapsed_time": "0:47:10", "remaining_time": "0:13:28"}
183
+ {"current_steps": 183, "total_steps": 234, "loss": 0.6116, "lr": 1.3860256808630429e-06, "epoch": 2.3361702127659574, "percentage": 78.21, "elapsed_time": "0:47:26", "remaining_time": "0:13:13"}
184
+ {"current_steps": 184, "total_steps": 234, "loss": 0.6779, "lr": 1.3347406408508695e-06, "epoch": 2.348936170212766, "percentage": 78.63, "elapsed_time": "0:47:39", "remaining_time": "0:12:57"}
185
+ {"current_steps": 185, "total_steps": 234, "loss": 0.733, "lr": 1.2842758726130283e-06, "epoch": 2.3617021276595747, "percentage": 79.06, "elapsed_time": "0:47:54", "remaining_time": "0:12:41"}
186
+ {"current_steps": 186, "total_steps": 234, "loss": 0.6138, "lr": 1.234642669981946e-06, "epoch": 2.374468085106383, "percentage": 79.49, "elapsed_time": "0:48:06", "remaining_time": "0:12:24"}
187
+ {"current_steps": 187, "total_steps": 234, "loss": 0.7082, "lr": 1.1858521406886674e-06, "epoch": 2.3872340425531915, "percentage": 79.91, "elapsed_time": "0:48:23", "remaining_time": "0:12:09"}
188
+ {"current_steps": 188, "total_steps": 234, "loss": 0.7132, "lr": 1.137915203877003e-06, "epoch": 2.4, "percentage": 80.34, "elapsed_time": "0:48:37", "remaining_time": "0:11:53"}
189
+ {"current_steps": 189, "total_steps": 234, "loss": 0.595, "lr": 1.0908425876598512e-06, "epoch": 2.4127659574468083, "percentage": 80.77, "elapsed_time": "0:48:53", "remaining_time": "0:11:38"}
190
+ {"current_steps": 190, "total_steps": 234, "loss": 0.5945, "lr": 1.044644826718295e-06, "epoch": 2.425531914893617, "percentage": 81.2, "elapsed_time": "0:49:08", "remaining_time": "0:11:22"}
191
+ {"current_steps": 191, "total_steps": 234, "loss": 0.7383, "lr": 9.993322599439692e-07, "epoch": 2.4382978723404256, "percentage": 81.62, "elapsed_time": "0:49:24", "remaining_time": "0:11:07"}
192
+ {"current_steps": 192, "total_steps": 234, "loss": 0.6384, "lr": 9.549150281252633e-07, "epoch": 2.451063829787234, "percentage": 82.05, "elapsed_time": "0:49:39", "remaining_time": "0:10:51"}
193
+ {"current_steps": 193, "total_steps": 234, "loss": 0.7709, "lr": 9.114030716778433e-07, "epoch": 2.4638297872340424, "percentage": 82.48, "elapsed_time": "0:49:51", "remaining_time": "0:10:35"}
194
+ {"current_steps": 194, "total_steps": 234, "loss": 0.67, "lr": 8.688061284200266e-07, "epoch": 2.476595744680851, "percentage": 82.91, "elapsed_time": "0:50:07", "remaining_time": "0:10:20"}
195
+ {"current_steps": 195, "total_steps": 234, "loss": 0.8132, "lr": 8.271337313934869e-07, "epoch": 2.4893617021276597, "percentage": 83.33, "elapsed_time": "0:50:21", "remaining_time": "0:10:04"}
196
+ {"current_steps": 196, "total_steps": 234, "loss": 0.609, "lr": 7.863952067298042e-07, "epoch": 2.502127659574468, "percentage": 83.76, "elapsed_time": "0:50:35", "remaining_time": "0:09:48"}
197
+ {"current_steps": 197, "total_steps": 234, "loss": 0.846, "lr": 7.465996715633028e-07, "epoch": 2.5148936170212766, "percentage": 84.19, "elapsed_time": "0:50:53", "remaining_time": "0:09:33"}
198
+ {"current_steps": 198, "total_steps": 234, "loss": 0.7215, "lr": 7.077560319906696e-07, "epoch": 2.527659574468085, "percentage": 84.62, "elapsed_time": "0:51:09", "remaining_time": "0:09:18"}
199
+ {"current_steps": 199, "total_steps": 234, "loss": 0.5401, "lr": 6.698729810778065e-07, "epoch": 2.5404255319148934, "percentage": 85.04, "elapsed_time": "0:51:20", "remaining_time": "0:09:01"}
200
+ {"current_steps": 200, "total_steps": 234, "loss": 0.7005, "lr": 6.329589969143518e-07, "epoch": 2.5531914893617023, "percentage": 85.47, "elapsed_time": "0:51:32", "remaining_time": "0:08:45"}
201
+ {"current_steps": 201, "total_steps": 234, "loss": 0.6182, "lr": 5.9702234071631e-07, "epoch": 2.5659574468085107, "percentage": 85.9, "elapsed_time": "0:51:46", "remaining_time": "0:08:29"}
202
+ {"current_steps": 202, "total_steps": 234, "loss": 0.7059, "lr": 5.620710549772295e-07, "epoch": 2.578723404255319, "percentage": 86.32, "elapsed_time": "0:52:01", "remaining_time": "0:08:14"}
203
+ {"current_steps": 203, "total_steps": 234, "loss": 0.625, "lr": 5.281129616683167e-07, "epoch": 2.5914893617021275, "percentage": 86.75, "elapsed_time": "0:52:15", "remaining_time": "0:07:58"}
204
+ {"current_steps": 204, "total_steps": 234, "loss": 0.7309, "lr": 4.951556604879049e-07, "epoch": 2.604255319148936, "percentage": 87.18, "elapsed_time": "0:52:30", "remaining_time": "0:07:43"}
205
+ {"current_steps": 205, "total_steps": 234, "loss": 0.6416, "lr": 4.632065271606756e-07, "epoch": 2.617021276595745, "percentage": 87.61, "elapsed_time": "0:52:43", "remaining_time": "0:07:27"}
206
+ {"current_steps": 206, "total_steps": 234, "loss": 0.6622, "lr": 4.322727117869951e-07, "epoch": 2.629787234042553, "percentage": 88.03, "elapsed_time": "0:52:57", "remaining_time": "0:07:11"}
207
+ {"current_steps": 207, "total_steps": 234, "loss": 0.6591, "lr": 4.0236113724274716e-07, "epoch": 2.6425531914893616, "percentage": 88.46, "elapsed_time": "0:53:12", "remaining_time": "0:06:56"}
208
+ {"current_steps": 208, "total_steps": 234, "loss": 0.6527, "lr": 3.734784976300165e-07, "epoch": 2.65531914893617, "percentage": 88.89, "elapsed_time": "0:53:25", "remaining_time": "0:06:40"}
209
+ {"current_steps": 209, "total_steps": 234, "loss": 0.6087, "lr": 3.4563125677897936e-07, "epoch": 2.6680851063829785, "percentage": 89.32, "elapsed_time": "0:53:37", "remaining_time": "0:06:24"}
210
+ {"current_steps": 210, "total_steps": 234, "loss": 0.7705, "lr": 3.18825646801314e-07, "epoch": 2.6808510638297873, "percentage": 89.74, "elapsed_time": "0:53:53", "remaining_time": "0:06:09"}
211
+ {"current_steps": 211, "total_steps": 234, "loss": 0.6485, "lr": 2.930676666954846e-07, "epoch": 2.6936170212765957, "percentage": 90.17, "elapsed_time": "0:54:09", "remaining_time": "0:05:54"}
212
+ {"current_steps": 212, "total_steps": 234, "loss": 0.5956, "lr": 2.6836308100417874e-07, "epoch": 2.706382978723404, "percentage": 90.6, "elapsed_time": "0:54:23", "remaining_time": "0:05:38"}
213
+ {"current_steps": 213, "total_steps": 234, "loss": 0.6515, "lr": 2.447174185242324e-07, "epoch": 2.719148936170213, "percentage": 91.03, "elapsed_time": "0:54:36", "remaining_time": "0:05:23"}
214
+ {"current_steps": 214, "total_steps": 234, "loss": 0.7521, "lr": 2.2213597106929608e-07, "epoch": 2.731914893617021, "percentage": 91.45, "elapsed_time": "0:54:51", "remaining_time": "0:05:07"}
215
+ {"current_steps": 215, "total_steps": 234, "loss": 0.6371, "lr": 2.006237922855553e-07, "epoch": 2.74468085106383, "percentage": 91.88, "elapsed_time": "0:55:06", "remaining_time": "0:04:52"}
216
+ {"current_steps": 216, "total_steps": 234, "loss": 0.7641, "lr": 1.801856965207338e-07, "epoch": 2.7574468085106383, "percentage": 92.31, "elapsed_time": "0:55:21", "remaining_time": "0:04:36"}
217
+ {"current_steps": 217, "total_steps": 234, "loss": 0.6856, "lr": 1.6082625774666793e-07, "epoch": 2.7702127659574467, "percentage": 92.74, "elapsed_time": "0:55:36", "remaining_time": "0:04:21"}
218
+ {"current_steps": 218, "total_steps": 234, "loss": 0.661, "lr": 1.4254980853566248e-07, "epoch": 2.7829787234042556, "percentage": 93.16, "elapsed_time": "0:55:50", "remaining_time": "0:04:05"}
219
+ {"current_steps": 219, "total_steps": 234, "loss": 0.7534, "lr": 1.253604390908819e-07, "epoch": 2.795744680851064, "percentage": 93.59, "elapsed_time": "0:56:04", "remaining_time": "0:03:50"}
220
+ {"current_steps": 220, "total_steps": 234, "loss": 0.678, "lr": 1.0926199633097156e-07, "epoch": 2.8085106382978724, "percentage": 94.02, "elapsed_time": "0:56:16", "remaining_time": "0:03:34"}
221
+ {"current_steps": 221, "total_steps": 234, "loss": 0.7268, "lr": 9.42580830291373e-08, "epoch": 2.821276595744681, "percentage": 94.44, "elapsed_time": "0:56:33", "remaining_time": "0:03:19"}
222
+ {"current_steps": 222, "total_steps": 234, "loss": 0.6707, "lr": 8.035205700685167e-08, "epoch": 2.8340425531914892, "percentage": 94.87, "elapsed_time": "0:56:49", "remaining_time": "0:03:04"}
223
+ {"current_steps": 223, "total_steps": 234, "loss": 0.7161, "lr": 6.75470303823933e-08, "epoch": 2.846808510638298, "percentage": 95.3, "elapsed_time": "0:57:02", "remaining_time": "0:02:48"}
224
+ {"current_steps": 224, "total_steps": 234, "loss": 0.6633, "lr": 5.584586887435739e-08, "epoch": 2.8595744680851065, "percentage": 95.73, "elapsed_time": "0:57:20", "remaining_time": "0:02:33"}
225
+ {"current_steps": 225, "total_steps": 234, "loss": 0.6042, "lr": 4.52511911603265e-08, "epoch": 2.872340425531915, "percentage": 96.15, "elapsed_time": "0:57:30", "remaining_time": "0:02:18"}
226
+ {"current_steps": 226, "total_steps": 234, "loss": 0.7831, "lr": 3.576536829081323e-08, "epoch": 2.8851063829787233, "percentage": 96.58, "elapsed_time": "0:57:43", "remaining_time": "0:02:02"}
227
+ {"current_steps": 227, "total_steps": 234, "loss": 0.6996, "lr": 2.7390523158633552e-08, "epoch": 2.8978723404255318, "percentage": 97.01, "elapsed_time": "0:57:56", "remaining_time": "0:01:47"}
228
+ {"current_steps": 228, "total_steps": 234, "loss": 0.6679, "lr": 2.012853002380466e-08, "epoch": 2.9106382978723406, "percentage": 97.44, "elapsed_time": "0:58:12", "remaining_time": "0:01:31"}
229
+ {"current_steps": 229, "total_steps": 234, "loss": 0.6368, "lr": 1.3981014094099354e-08, "epoch": 2.923404255319149, "percentage": 97.86, "elapsed_time": "0:58:28", "remaining_time": "0:01:16"}
230
+ {"current_steps": 230, "total_steps": 234, "loss": 0.7147, "lr": 8.949351161324227e-09, "epoch": 2.9361702127659575, "percentage": 98.29, "elapsed_time": "0:58:44", "remaining_time": "0:01:01"}
231
+ {"current_steps": 231, "total_steps": 234, "loss": 0.6326, "lr": 5.034667293427053e-09, "epoch": 2.948936170212766, "percentage": 98.72, "elapsed_time": "0:58:56", "remaining_time": "0:00:45"}
232
+ {"current_steps": 232, "total_steps": 234, "loss": 0.6752, "lr": 2.237838582483387e-09, "epoch": 2.9617021276595743, "percentage": 99.15, "elapsed_time": "0:59:12", "remaining_time": "0:00:30"}
233
+ {"current_steps": 233, "total_steps": 234, "loss": 0.6547, "lr": 5.594909486328348e-10, "epoch": 2.974468085106383, "percentage": 99.57, "elapsed_time": "0:59:25", "remaining_time": "0:00:15"}
234
+ {"current_steps": 234, "total_steps": 234, "loss": 0.6771, "lr": 0.0, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "0:59:41", "remaining_time": "0:00:00"}
235
+ {"current_steps": 234, "total_steps": 234, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "1:01:44", "remaining_time": "0:00:00"}