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:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d8aa58f9f5c469db326a8c23c75c43566099809ac74363f962a168769459a9a
|
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:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5feecaccb79460c86e1674dd0b93582b9e63d79eef484b470cb2f889fe267c0
|
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:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11eb0bec53bfe9a5bc692bfa554b75a63f2b496789320b2b5c45a97041746a5c
|
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:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0bfbd1ce62d7bf23eaee626db92851ab885f880cc0409c73ad1398df4db2311
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -166,3 +166,59 @@
|
|
166 |
{"current_steps": 1640, "total_steps": 4392, "loss": 0.6707, "lr": 5e-06, "epoch": 2.9858898497951754, "percentage": 37.34, "elapsed_time": "14:53:34", "remaining_time": "1 day, 0:59:27"}
|
167 |
{"current_steps": 1647, "total_steps": 4392, "eval_loss": 0.7486923933029175, "epoch": 2.9986345015930813, "percentage": 37.5, "elapsed_time": "15:03:50", "remaining_time": "1 day, 1:06:24"}
|
168 |
{"current_steps": 1650, "total_steps": 4392, "loss": 0.7123, "lr": 5e-06, "epoch": 3.0040964952207556, "percentage": 37.57, "elapsed_time": "15:06:24", "remaining_time": "1 day, 1:06:16"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
{"current_steps": 1640, "total_steps": 4392, "loss": 0.6707, "lr": 5e-06, "epoch": 2.9858898497951754, "percentage": 37.34, "elapsed_time": "14:53:34", "remaining_time": "1 day, 0:59:27"}
|
167 |
{"current_steps": 1647, "total_steps": 4392, "eval_loss": 0.7486923933029175, "epoch": 2.9986345015930813, "percentage": 37.5, "elapsed_time": "15:03:50", "remaining_time": "1 day, 1:06:24"}
|
168 |
{"current_steps": 1650, "total_steps": 4392, "loss": 0.7123, "lr": 5e-06, "epoch": 3.0040964952207556, "percentage": 37.57, "elapsed_time": "15:06:24", "remaining_time": "1 day, 1:06:16"}
|
169 |
+
{"current_steps": 1660, "total_steps": 4392, "loss": 0.6192, "lr": 5e-06, "epoch": 3.022303140646336, "percentage": 37.8, "elapsed_time": "15:11:43", "remaining_time": "1 day, 1:00:29"}
|
170 |
+
{"current_steps": 1670, "total_steps": 4392, "loss": 0.6192, "lr": 5e-06, "epoch": 3.040509786071916, "percentage": 38.02, "elapsed_time": "15:17:04", "remaining_time": "1 day, 0:54:46"}
|
171 |
+
{"current_steps": 1680, "total_steps": 4392, "loss": 0.6218, "lr": 5e-06, "epoch": 3.0587164314974964, "percentage": 38.25, "elapsed_time": "15:22:25", "remaining_time": "1 day, 0:49:03"}
|
172 |
+
{"current_steps": 1690, "total_steps": 4392, "loss": 0.6211, "lr": 5e-06, "epoch": 3.076923076923077, "percentage": 38.48, "elapsed_time": "15:27:48", "remaining_time": "1 day, 0:43:23"}
|
173 |
+
{"current_steps": 1700, "total_steps": 4392, "loss": 0.621, "lr": 5e-06, "epoch": 3.0951297223486574, "percentage": 38.71, "elapsed_time": "15:33:08", "remaining_time": "1 day, 0:37:39"}
|
174 |
+
{"current_steps": 1710, "total_steps": 4392, "loss": 0.6201, "lr": 5e-06, "epoch": 3.1133363677742376, "percentage": 38.93, "elapsed_time": "15:38:28", "remaining_time": "1 day, 0:31:55"}
|
175 |
+
{"current_steps": 1720, "total_steps": 4392, "loss": 0.6224, "lr": 5e-06, "epoch": 3.131543013199818, "percentage": 39.16, "elapsed_time": "15:43:49", "remaining_time": "1 day, 0:26:13"}
|
176 |
+
{"current_steps": 1730, "total_steps": 4392, "loss": 0.625, "lr": 5e-06, "epoch": 3.149749658625398, "percentage": 39.39, "elapsed_time": "15:49:11", "remaining_time": "1 day, 0:20:32"}
|
177 |
+
{"current_steps": 1740, "total_steps": 4392, "loss": 0.6204, "lr": 5e-06, "epoch": 3.1679563040509784, "percentage": 39.62, "elapsed_time": "15:54:33", "remaining_time": "1 day, 0:14:52"}
|
178 |
+
{"current_steps": 1750, "total_steps": 4392, "loss": 0.6163, "lr": 5e-06, "epoch": 3.186162949476559, "percentage": 39.85, "elapsed_time": "15:59:55", "remaining_time": "1 day, 0:09:12"}
|
179 |
+
{"current_steps": 1760, "total_steps": 4392, "loss": 0.6234, "lr": 5e-06, "epoch": 3.2043695949021394, "percentage": 40.07, "elapsed_time": "16:05:17", "remaining_time": "1 day, 0:03:32"}
|
180 |
+
{"current_steps": 1770, "total_steps": 4392, "loss": 0.6213, "lr": 5e-06, "epoch": 3.2225762403277196, "percentage": 40.3, "elapsed_time": "16:10:38", "remaining_time": "23:57:52"}
|
181 |
+
{"current_steps": 1780, "total_steps": 4392, "loss": 0.6229, "lr": 5e-06, "epoch": 3.2407828857533, "percentage": 40.53, "elapsed_time": "16:15:59", "remaining_time": "23:52:11"}
|
182 |
+
{"current_steps": 1790, "total_steps": 4392, "loss": 0.621, "lr": 5e-06, "epoch": 3.25898953117888, "percentage": 40.76, "elapsed_time": "16:21:20", "remaining_time": "23:46:30"}
|
183 |
+
{"current_steps": 1800, "total_steps": 4392, "loss": 0.6244, "lr": 5e-06, "epoch": 3.277196176604461, "percentage": 40.98, "elapsed_time": "16:26:42", "remaining_time": "23:40:51"}
|
184 |
+
{"current_steps": 1810, "total_steps": 4392, "loss": 0.6229, "lr": 5e-06, "epoch": 3.295402822030041, "percentage": 41.21, "elapsed_time": "16:32:01", "remaining_time": "23:35:09"}
|
185 |
+
{"current_steps": 1820, "total_steps": 4392, "loss": 0.6226, "lr": 5e-06, "epoch": 3.3136094674556213, "percentage": 41.44, "elapsed_time": "16:37:22", "remaining_time": "23:29:28"}
|
186 |
+
{"current_steps": 1830, "total_steps": 4392, "loss": 0.6241, "lr": 5e-06, "epoch": 3.3318161128812016, "percentage": 41.67, "elapsed_time": "16:42:44", "remaining_time": "23:23:50"}
|
187 |
+
{"current_steps": 1840, "total_steps": 4392, "loss": 0.6234, "lr": 5e-06, "epoch": 3.350022758306782, "percentage": 41.89, "elapsed_time": "16:48:06", "remaining_time": "23:18:12"}
|
188 |
+
{"current_steps": 1850, "total_steps": 4392, "loss": 0.6239, "lr": 5e-06, "epoch": 3.368229403732362, "percentage": 42.12, "elapsed_time": "16:53:28", "remaining_time": "23:12:34"}
|
189 |
+
{"current_steps": 1860, "total_steps": 4392, "loss": 0.6225, "lr": 5e-06, "epoch": 3.386436049157943, "percentage": 42.35, "elapsed_time": "16:58:48", "remaining_time": "23:06:53"}
|
190 |
+
{"current_steps": 1870, "total_steps": 4392, "loss": 0.6255, "lr": 5e-06, "epoch": 3.404642694583523, "percentage": 42.58, "elapsed_time": "17:04:09", "remaining_time": "23:01:14"}
|
191 |
+
{"current_steps": 1880, "total_steps": 4392, "loss": 0.6253, "lr": 5e-06, "epoch": 3.4228493400091033, "percentage": 42.81, "elapsed_time": "17:09:28", "remaining_time": "22:55:32"}
|
192 |
+
{"current_steps": 1890, "total_steps": 4392, "loss": 0.6313, "lr": 5e-06, "epoch": 3.4410559854346836, "percentage": 43.03, "elapsed_time": "17:14:48", "remaining_time": "22:49:52"}
|
193 |
+
{"current_steps": 1900, "total_steps": 4392, "loss": 0.6279, "lr": 5e-06, "epoch": 3.459262630860264, "percentage": 43.26, "elapsed_time": "17:20:07", "remaining_time": "22:44:12"}
|
194 |
+
{"current_steps": 1910, "total_steps": 4392, "loss": 0.6279, "lr": 5e-06, "epoch": 3.477469276285844, "percentage": 43.49, "elapsed_time": "17:25:28", "remaining_time": "22:38:33"}
|
195 |
+
{"current_steps": 1920, "total_steps": 4392, "loss": 0.6299, "lr": 5e-06, "epoch": 3.495675921711425, "percentage": 43.72, "elapsed_time": "17:30:50", "remaining_time": "22:32:57"}
|
196 |
+
{"current_steps": 1930, "total_steps": 4392, "loss": 0.6281, "lr": 5e-06, "epoch": 3.513882567137005, "percentage": 43.94, "elapsed_time": "17:36:11", "remaining_time": "22:27:19"}
|
197 |
+
{"current_steps": 1940, "total_steps": 4392, "loss": 0.6275, "lr": 5e-06, "epoch": 3.5320892125625853, "percentage": 44.17, "elapsed_time": "17:41:33", "remaining_time": "22:21:43"}
|
198 |
+
{"current_steps": 1950, "total_steps": 4392, "loss": 0.6299, "lr": 5e-06, "epoch": 3.5502958579881656, "percentage": 44.4, "elapsed_time": "17:46:56", "remaining_time": "22:16:08"}
|
199 |
+
{"current_steps": 1960, "total_steps": 4392, "loss": 0.6286, "lr": 5e-06, "epoch": 3.568502503413746, "percentage": 44.63, "elapsed_time": "17:52:19", "remaining_time": "22:10:33"}
|
200 |
+
{"current_steps": 1970, "total_steps": 4392, "loss": 0.6248, "lr": 5e-06, "epoch": 3.5867091488393266, "percentage": 44.85, "elapsed_time": "17:57:41", "remaining_time": "22:04:57"}
|
201 |
+
{"current_steps": 1980, "total_steps": 4392, "loss": 0.6281, "lr": 5e-06, "epoch": 3.604915794264907, "percentage": 45.08, "elapsed_time": "18:03:02", "remaining_time": "21:59:21"}
|
202 |
+
{"current_steps": 1990, "total_steps": 4392, "loss": 0.6278, "lr": 5e-06, "epoch": 3.623122439690487, "percentage": 45.31, "elapsed_time": "18:08:25", "remaining_time": "21:53:45"}
|
203 |
+
{"current_steps": 2000, "total_steps": 4392, "loss": 0.6296, "lr": 5e-06, "epoch": 3.6413290851160673, "percentage": 45.54, "elapsed_time": "18:13:48", "remaining_time": "21:48:11"}
|
204 |
+
{"current_steps": 2010, "total_steps": 4392, "loss": 0.6312, "lr": 5e-06, "epoch": 3.6595357305416476, "percentage": 45.77, "elapsed_time": "18:19:10", "remaining_time": "21:42:36"}
|
205 |
+
{"current_steps": 2020, "total_steps": 4392, "loss": 0.6282, "lr": 5e-06, "epoch": 3.6777423759672283, "percentage": 45.99, "elapsed_time": "18:24:33", "remaining_time": "21:37:02"}
|
206 |
+
{"current_steps": 2030, "total_steps": 4392, "loss": 0.6282, "lr": 5e-06, "epoch": 3.695949021392808, "percentage": 46.22, "elapsed_time": "18:29:54", "remaining_time": "21:31:25"}
|
207 |
+
{"current_steps": 2040, "total_steps": 4392, "loss": 0.633, "lr": 5e-06, "epoch": 3.714155666818389, "percentage": 46.45, "elapsed_time": "18:35:15", "remaining_time": "21:25:50"}
|
208 |
+
{"current_steps": 2050, "total_steps": 4392, "loss": 0.6299, "lr": 5e-06, "epoch": 3.732362312243969, "percentage": 46.68, "elapsed_time": "18:40:37", "remaining_time": "21:20:15"}
|
209 |
+
{"current_steps": 2060, "total_steps": 4392, "loss": 0.6307, "lr": 5e-06, "epoch": 3.7505689576695493, "percentage": 46.9, "elapsed_time": "18:46:00", "remaining_time": "21:14:41"}
|
210 |
+
{"current_steps": 2070, "total_steps": 4392, "loss": 0.6314, "lr": 5e-06, "epoch": 3.7687756030951296, "percentage": 47.13, "elapsed_time": "18:51:23", "remaining_time": "21:09:07"}
|
211 |
+
{"current_steps": 2080, "total_steps": 4392, "loss": 0.6292, "lr": 5e-06, "epoch": 3.78698224852071, "percentage": 47.36, "elapsed_time": "18:56:45", "remaining_time": "21:03:33"}
|
212 |
+
{"current_steps": 2090, "total_steps": 4392, "loss": 0.6302, "lr": 5e-06, "epoch": 3.8051888939462906, "percentage": 47.59, "elapsed_time": "19:02:08", "remaining_time": "20:57:59"}
|
213 |
+
{"current_steps": 2100, "total_steps": 4392, "loss": 0.6329, "lr": 5e-06, "epoch": 3.823395539371871, "percentage": 47.81, "elapsed_time": "19:07:30", "remaining_time": "20:52:25"}
|
214 |
+
{"current_steps": 2110, "total_steps": 4392, "loss": 0.6336, "lr": 5e-06, "epoch": 3.841602184797451, "percentage": 48.04, "elapsed_time": "19:12:51", "remaining_time": "20:46:49"}
|
215 |
+
{"current_steps": 2120, "total_steps": 4392, "loss": 0.6343, "lr": 5e-06, "epoch": 3.8598088302230313, "percentage": 48.27, "elapsed_time": "19:18:11", "remaining_time": "20:41:13"}
|
216 |
+
{"current_steps": 2130, "total_steps": 4392, "loss": 0.6323, "lr": 5e-06, "epoch": 3.8780154756486116, "percentage": 48.5, "elapsed_time": "19:23:33", "remaining_time": "20:35:39"}
|
217 |
+
{"current_steps": 2140, "total_steps": 4392, "loss": 0.6289, "lr": 5e-06, "epoch": 3.8962221210741923, "percentage": 48.72, "elapsed_time": "19:28:55", "remaining_time": "20:30:06"}
|
218 |
+
{"current_steps": 2150, "total_steps": 4392, "loss": 0.6319, "lr": 5e-06, "epoch": 3.9144287664997726, "percentage": 48.95, "elapsed_time": "19:34:17", "remaining_time": "20:24:32"}
|
219 |
+
{"current_steps": 2160, "total_steps": 4392, "loss": 0.6326, "lr": 5e-06, "epoch": 3.932635411925353, "percentage": 49.18, "elapsed_time": "19:39:39", "remaining_time": "20:18:58"}
|
220 |
+
{"current_steps": 2170, "total_steps": 4392, "loss": 0.6347, "lr": 5e-06, "epoch": 3.950842057350933, "percentage": 49.41, "elapsed_time": "19:44:59", "remaining_time": "20:13:23"}
|
221 |
+
{"current_steps": 2180, "total_steps": 4392, "loss": 0.6255, "lr": 5e-06, "epoch": 3.9690487027765133, "percentage": 49.64, "elapsed_time": "19:50:21", "remaining_time": "20:07:50"}
|
222 |
+
{"current_steps": 2190, "total_steps": 4392, "loss": 0.6324, "lr": 5e-06, "epoch": 3.987255348202094, "percentage": 49.86, "elapsed_time": "19:55:44", "remaining_time": "20:02:17"}
|
223 |
+
{"current_steps": 2197, "total_steps": 4392, "eval_loss": 0.7583181262016296, "epoch": 4.0, "percentage": 50.02, "elapsed_time": "20:05:43", "remaining_time": "20:04:37"}
|
224 |
+
{"current_steps": 2200, "total_steps": 4392, "loss": 0.6642, "lr": 5e-06, "epoch": 4.005461993627674, "percentage": 50.09, "elapsed_time": "20:08:36", "remaining_time": "20:04:12"}
|