sumuks commited on
Commit
652770b
·
verified ·
1 Parent(s): 3d08179

Training in progress, step 2000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +51 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321755b19ccccc82f2199431da16e1458df733c7525b9527d1219ff07b607267
3
  size 645976488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543c520542a943774206477e40e5b855dec5eddf08a4786441bc3db1a89f74be
3
  size 645976488
trainer_log.jsonl CHANGED
@@ -150,3 +150,54 @@
150
  {"current_steps": 1480, "total_steps": 3573, "loss": 1.2633, "lr": 3.642044645802638e-05, "epoch": 1.2426532325776658, "percentage": 41.42, "elapsed_time": "0:32:26", "remaining_time": "0:45:53"}
151
  {"current_steps": 1490, "total_steps": 3573, "loss": 1.2631, "lr": 3.620259239393549e-05, "epoch": 1.2510495382031905, "percentage": 41.7, "elapsed_time": "0:32:39", "remaining_time": "0:45:38"}
152
  {"current_steps": 1500, "total_steps": 3573, "loss": 1.2323, "lr": 3.5983668652322914e-05, "epoch": 1.2594458438287153, "percentage": 41.98, "elapsed_time": "0:32:51", "remaining_time": "0:45:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  {"current_steps": 1480, "total_steps": 3573, "loss": 1.2633, "lr": 3.642044645802638e-05, "epoch": 1.2426532325776658, "percentage": 41.42, "elapsed_time": "0:32:26", "remaining_time": "0:45:53"}
151
  {"current_steps": 1490, "total_steps": 3573, "loss": 1.2631, "lr": 3.620259239393549e-05, "epoch": 1.2510495382031905, "percentage": 41.7, "elapsed_time": "0:32:39", "remaining_time": "0:45:38"}
152
  {"current_steps": 1500, "total_steps": 3573, "loss": 1.2323, "lr": 3.5983668652322914e-05, "epoch": 1.2594458438287153, "percentage": 41.98, "elapsed_time": "0:32:51", "remaining_time": "0:45:24"}
153
+ {"current_steps": 1510, "total_steps": 3573, "loss": 1.2499, "lr": 3.576369613708278e-05, "epoch": 1.26784214945424, "percentage": 42.26, "elapsed_time": "0:33:25", "remaining_time": "0:45:40"}
154
+ {"current_steps": 1520, "total_steps": 3573, "loss": 1.2623, "lr": 3.554269585225117e-05, "epoch": 1.276238455079765, "percentage": 42.54, "elapsed_time": "0:33:37", "remaining_time": "0:45:25"}
155
+ {"current_steps": 1530, "total_steps": 3573, "loss": 1.25, "lr": 3.532068890000059e-05, "epoch": 1.2846347607052897, "percentage": 42.82, "elapsed_time": "0:33:49", "remaining_time": "0:45:10"}
156
+ {"current_steps": 1540, "total_steps": 3573, "loss": 1.2615, "lr": 3.5097696478624956e-05, "epoch": 1.2930310663308144, "percentage": 43.1, "elapsed_time": "0:34:02", "remaining_time": "0:44:55"}
157
+ {"current_steps": 1550, "total_steps": 3573, "loss": 1.2577, "lr": 3.487373988051556e-05, "epoch": 1.3014273719563392, "percentage": 43.38, "elapsed_time": "0:34:14", "remaining_time": "0:44:41"}
158
+ {"current_steps": 1560, "total_steps": 3573, "loss": 1.2252, "lr": 3.464884049012794e-05, "epoch": 1.309823677581864, "percentage": 43.66, "elapsed_time": "0:34:26", "remaining_time": "0:44:26"}
159
+ {"current_steps": 1570, "total_steps": 3573, "loss": 1.2333, "lr": 3.442301978193996e-05, "epoch": 1.3182199832073889, "percentage": 43.94, "elapsed_time": "0:34:38", "remaining_time": "0:44:12"}
160
+ {"current_steps": 1580, "total_steps": 3573, "loss": 1.2309, "lr": 3.419629931840137e-05, "epoch": 1.3266162888329136, "percentage": 44.22, "elapsed_time": "0:34:50", "remaining_time": "0:43:57"}
161
+ {"current_steps": 1590, "total_steps": 3573, "loss": 1.2347, "lr": 3.396870074787489e-05, "epoch": 1.3350125944584383, "percentage": 44.5, "elapsed_time": "0:35:03", "remaining_time": "0:43:42"}
162
+ {"current_steps": 1600, "total_steps": 3573, "loss": 1.2278, "lr": 3.374024580256913e-05, "epoch": 1.343408900083963, "percentage": 44.78, "elapsed_time": "0:35:15", "remaining_time": "0:43:28"}
163
+ {"current_steps": 1610, "total_steps": 3573, "loss": 1.2459, "lr": 3.351095629646348e-05, "epoch": 1.3518052057094878, "percentage": 45.06, "elapsed_time": "0:35:27", "remaining_time": "0:43:13"}
164
+ {"current_steps": 1620, "total_steps": 3573, "loss": 1.2567, "lr": 3.3280854123225245e-05, "epoch": 1.3602015113350125, "percentage": 45.34, "elapsed_time": "0:35:39", "remaining_time": "0:42:59"}
165
+ {"current_steps": 1630, "total_steps": 3573, "loss": 1.2427, "lr": 3.3049961254119077e-05, "epoch": 1.3685978169605373, "percentage": 45.62, "elapsed_time": "0:35:51", "remaining_time": "0:42:44"}
166
+ {"current_steps": 1640, "total_steps": 3573, "loss": 1.2292, "lr": 3.281829973590909e-05, "epoch": 1.376994122586062, "percentage": 45.9, "elapsed_time": "0:36:03", "remaining_time": "0:42:30"}
167
+ {"current_steps": 1650, "total_steps": 3573, "loss": 1.2231, "lr": 3.258589168875373e-05, "epoch": 1.385390428211587, "percentage": 46.18, "elapsed_time": "0:36:16", "remaining_time": "0:42:16"}
168
+ {"current_steps": 1660, "total_steps": 3573, "loss": 1.2399, "lr": 3.2352759304093624e-05, "epoch": 1.3937867338371117, "percentage": 46.46, "elapsed_time": "0:36:28", "remaining_time": "0:42:01"}
169
+ {"current_steps": 1670, "total_steps": 3573, "loss": 1.2786, "lr": 3.211892484253261e-05, "epoch": 1.4021830394626364, "percentage": 46.74, "elapsed_time": "0:36:40", "remaining_time": "0:41:47"}
170
+ {"current_steps": 1680, "total_steps": 3573, "loss": 1.2423, "lr": 3.1884410631712235e-05, "epoch": 1.4105793450881612, "percentage": 47.02, "elapsed_time": "0:36:52", "remaining_time": "0:41:32"}
171
+ {"current_steps": 1690, "total_steps": 3573, "loss": 1.2399, "lr": 3.164923906417979e-05, "epoch": 1.418975650713686, "percentage": 47.3, "elapsed_time": "0:37:04", "remaining_time": "0:41:18"}
172
+ {"current_steps": 1700, "total_steps": 3573, "loss": 1.2575, "lr": 3.1413432595250134e-05, "epoch": 1.4273719563392109, "percentage": 47.58, "elapsed_time": "0:37:16", "remaining_time": "0:41:04"}
173
+ {"current_steps": 1710, "total_steps": 3573, "loss": 1.2155, "lr": 3.117701374086158e-05, "epoch": 1.4357682619647356, "percentage": 47.86, "elapsed_time": "0:37:28", "remaining_time": "0:40:50"}
174
+ {"current_steps": 1720, "total_steps": 3573, "loss": 1.2561, "lr": 3.094000507542595e-05, "epoch": 1.4441645675902604, "percentage": 48.14, "elapsed_time": "0:37:40", "remaining_time": "0:40:35"}
175
+ {"current_steps": 1730, "total_steps": 3573, "loss": 1.2389, "lr": 3.07024292296731e-05, "epoch": 1.452560873215785, "percentage": 48.42, "elapsed_time": "0:37:53", "remaining_time": "0:40:21"}
176
+ {"current_steps": 1740, "total_steps": 3573, "loss": 1.2323, "lr": 3.0464308888489936e-05, "epoch": 1.4609571788413098, "percentage": 48.7, "elapsed_time": "0:38:05", "remaining_time": "0:40:07"}
177
+ {"current_steps": 1750, "total_steps": 3573, "loss": 1.228, "lr": 3.022566678875446e-05, "epoch": 1.4693534844668346, "percentage": 48.98, "elapsed_time": "0:38:17", "remaining_time": "0:39:53"}
178
+ {"current_steps": 1760, "total_steps": 3573, "loss": 1.2025, "lr": 2.9986525717164694e-05, "epoch": 1.4777497900923593, "percentage": 49.26, "elapsed_time": "0:38:29", "remaining_time": "0:39:39"}
179
+ {"current_steps": 1770, "total_steps": 3573, "loss": 1.2585, "lr": 2.974690850806287e-05, "epoch": 1.486146095717884, "percentage": 49.54, "elapsed_time": "0:38:41", "remaining_time": "0:39:25"}
180
+ {"current_steps": 1780, "total_steps": 3573, "loss": 1.2438, "lr": 2.9506838041255147e-05, "epoch": 1.4945424013434088, "percentage": 49.82, "elapsed_time": "0:38:54", "remaining_time": "0:39:11"}
181
+ {"current_steps": 1790, "total_steps": 3573, "loss": 1.23, "lr": 2.926633723982692e-05, "epoch": 1.5029387069689337, "percentage": 50.1, "elapsed_time": "0:39:06", "remaining_time": "0:38:57"}
182
+ {"current_steps": 1800, "total_steps": 3573, "loss": 1.2089, "lr": 2.9025429067953975e-05, "epoch": 1.5113350125944585, "percentage": 50.38, "elapsed_time": "0:39:18", "remaining_time": "0:38:43"}
183
+ {"current_steps": 1800, "total_steps": 3573, "eval_loss": 1.3161499500274658, "epoch": 1.5113350125944585, "percentage": 50.38, "elapsed_time": "0:39:55", "remaining_time": "0:39:20"}
184
+ {"current_steps": 1810, "total_steps": 3573, "loss": 1.2452, "lr": 2.878413652870983e-05, "epoch": 1.5197313182199832, "percentage": 50.66, "elapsed_time": "0:40:08", "remaining_time": "0:39:05"}
185
+ {"current_steps": 1820, "total_steps": 3573, "loss": 1.2335, "lr": 2.8542482661869228e-05, "epoch": 1.528127623845508, "percentage": 50.94, "elapsed_time": "0:40:20", "remaining_time": "0:38:51"}
186
+ {"current_steps": 1830, "total_steps": 3573, "loss": 1.2107, "lr": 2.8300490541708226e-05, "epoch": 1.536523929471033, "percentage": 51.22, "elapsed_time": "0:40:32", "remaining_time": "0:38:36"}
187
+ {"current_steps": 1840, "total_steps": 3573, "loss": 1.2323, "lr": 2.8058183274800933e-05, "epoch": 1.5449202350965576, "percentage": 51.5, "elapsed_time": "0:40:44", "remaining_time": "0:38:22"}
188
+ {"current_steps": 1850, "total_steps": 3573, "loss": 1.2208, "lr": 2.7815583997813176e-05, "epoch": 1.5533165407220824, "percentage": 51.78, "elapsed_time": "0:40:56", "remaining_time": "0:38:08"}
189
+ {"current_steps": 1860, "total_steps": 3573, "loss": 1.2519, "lr": 2.7572715875293336e-05, "epoch": 1.561712846347607, "percentage": 52.06, "elapsed_time": "0:41:09", "remaining_time": "0:37:53"}
190
+ {"current_steps": 1870, "total_steps": 3573, "loss": 1.2072, "lr": 2.7329602097460453e-05, "epoch": 1.5701091519731318, "percentage": 52.34, "elapsed_time": "0:41:21", "remaining_time": "0:37:39"}
191
+ {"current_steps": 1880, "total_steps": 3573, "loss": 1.2171, "lr": 2.7086265877989907e-05, "epoch": 1.5785054575986566, "percentage": 52.62, "elapsed_time": "0:41:33", "remaining_time": "0:37:25"}
192
+ {"current_steps": 1890, "total_steps": 3573, "loss": 1.2032, "lr": 2.68427304517969e-05, "epoch": 1.5869017632241813, "percentage": 52.9, "elapsed_time": "0:41:45", "remaining_time": "0:37:11"}
193
+ {"current_steps": 1900, "total_steps": 3573, "loss": 1.2233, "lr": 2.6599019072817823e-05, "epoch": 1.595298068849706, "percentage": 53.18, "elapsed_time": "0:41:58", "remaining_time": "0:36:57"}
194
+ {"current_steps": 1910, "total_steps": 3573, "loss": 1.2302, "lr": 2.6355155011789918e-05, "epoch": 1.6036943744752308, "percentage": 53.46, "elapsed_time": "0:42:10", "remaining_time": "0:36:43"}
195
+ {"current_steps": 1920, "total_steps": 3573, "loss": 1.2237, "lr": 2.6111161554029216e-05, "epoch": 1.6120906801007555, "percentage": 53.74, "elapsed_time": "0:42:22", "remaining_time": "0:36:28"}
196
+ {"current_steps": 1930, "total_steps": 3573, "loss": 1.2373, "lr": 2.5867061997207208e-05, "epoch": 1.6204869857262805, "percentage": 54.02, "elapsed_time": "0:42:34", "remaining_time": "0:36:14"}
197
+ {"current_steps": 1940, "total_steps": 3573, "loss": 1.2366, "lr": 2.5622879649126204e-05, "epoch": 1.6288832913518052, "percentage": 54.3, "elapsed_time": "0:42:46", "remaining_time": "0:36:00"}
198
+ {"current_steps": 1950, "total_steps": 3573, "loss": 1.2175, "lr": 2.5378637825493827e-05, "epoch": 1.63727959697733, "percentage": 54.58, "elapsed_time": "0:42:58", "remaining_time": "0:35:46"}
199
+ {"current_steps": 1960, "total_steps": 3573, "loss": 1.2226, "lr": 2.5134359847696725e-05, "epoch": 1.645675902602855, "percentage": 54.86, "elapsed_time": "0:43:11", "remaining_time": "0:35:32"}
200
+ {"current_steps": 1970, "total_steps": 3573, "loss": 1.2354, "lr": 2.48900690405737e-05, "epoch": 1.6540722082283796, "percentage": 55.14, "elapsed_time": "0:43:23", "remaining_time": "0:35:18"}
201
+ {"current_steps": 1980, "total_steps": 3573, "loss": 1.2346, "lr": 2.4645788730188595e-05, "epoch": 1.6624685138539044, "percentage": 55.42, "elapsed_time": "0:43:35", "remaining_time": "0:35:04"}
202
+ {"current_steps": 1990, "total_steps": 3573, "loss": 1.2266, "lr": 2.4401542241602936e-05, "epoch": 1.670864819479429, "percentage": 55.7, "elapsed_time": "0:43:47", "remaining_time": "0:34:50"}
203
+ {"current_steps": 2000, "total_steps": 3573, "loss": 1.2489, "lr": 2.4157352896648785e-05, "epoch": 1.6792611251049538, "percentage": 55.98, "elapsed_time": "0:43:59", "remaining_time": "0:34:36"}