rbelanec commited on
Commit
db6c175
·
verified ·
1 Parent(s): 9f6fd3d

Training in progress, step 40000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +42 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1278f58df1c8c7dc346e8851235754e687f0d7d18223ab531d51452753856373
3
  size 18124968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8aee5cbf5c9a3750fee20e7c87849759b7b0712bda4ef0a3e21f7da1d6e71d
3
  size 18124968
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "9:38:11", "remaining_time": "0:02:58", "throughput": 1751.84, "total_tokens": 60774960}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "9:38:16", "remaining_time": "0:02:54", "throughput": 1751.87, "total_tokens": 60782960}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.3297935724258423, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "9:38:24", "remaining_time": "0:02:54", "throughput": 1751.46, "total_tokens": 60782960}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "9:38:11", "remaining_time": "0:02:58", "throughput": 1751.84, "total_tokens": 60774960}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "9:38:16", "remaining_time": "0:02:54", "throughput": 1751.87, "total_tokens": 60782960}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.3297935724258423, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "9:38:24", "remaining_time": "0:02:54", "throughput": 1751.46, "total_tokens": 60782960}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 122.85625965996908, "percentage": 99.51, "elapsed_time": "9:38:30", "remaining_time": "0:02:50", "throughput": 1751.36, "total_tokens": 60790352}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 122.87171561051005, "percentage": 99.52, "elapsed_time": "9:38:34", "remaining_time": "0:02:45", "throughput": 1751.37, "total_tokens": 60797808}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 122.887171561051, "percentage": 99.54, "elapsed_time": "9:38:38", "remaining_time": "0:02:41", "throughput": 1751.39, "total_tokens": 60805808}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 122.90262751159196, "percentage": 99.55, "elapsed_time": "9:38:42", "remaining_time": "0:02:36", "throughput": 1751.41, "total_tokens": 60813552}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 122.91808346213293, "percentage": 99.56, "elapsed_time": "9:38:46", "remaining_time": "0:02:32", "throughput": 1751.42, "total_tokens": 60821200}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 122.93353941267388, "percentage": 99.58, "elapsed_time": "9:38:50", "remaining_time": "0:02:28", "throughput": 1751.45, "total_tokens": 60829232}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0006, "lr": 2.1247106758215397e-09, "epoch": 122.94899536321483, "percentage": 99.59, "elapsed_time": "9:38:54", "remaining_time": "0:02:23", "throughput": 1751.46, "total_tokens": 60836720}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 122.9644513137558, "percentage": 99.6, "elapsed_time": "9:38:59", "remaining_time": "0:02:19", "throughput": 1751.48, "total_tokens": 60844656}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 122.97990726429676, "percentage": 99.61, "elapsed_time": "9:39:03", "remaining_time": "0:02:15", "throughput": 1751.49, "total_tokens": 60852336}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 122.99536321483771, "percentage": 99.62, "elapsed_time": "9:39:07", "remaining_time": "0:02:10", "throughput": 1751.54, "total_tokens": 60861072}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 123.00927357032458, "percentage": 99.64, "elapsed_time": "9:39:11", "remaining_time": "0:02:06", "throughput": 1751.52, "total_tokens": 60867632}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 123.02472952086553, "percentage": 99.65, "elapsed_time": "9:39:15", "remaining_time": "0:02:02", "throughput": 1751.52, "total_tokens": 60874832}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0007, "lr": 1.4261442765006739e-09, "epoch": 123.04018547140649, "percentage": 99.66, "elapsed_time": "9:39:19", "remaining_time": "0:01:57", "throughput": 1751.53, "total_tokens": 60882512}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 123.05564142194746, "percentage": 99.67, "elapsed_time": "9:39:23", "remaining_time": "0:01:53", "throughput": 1751.54, "total_tokens": 60890000}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 123.07109737248841, "percentage": 99.69, "elapsed_time": "9:39:27", "remaining_time": "0:01:48", "throughput": 1751.56, "total_tokens": 60897680}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 123.08655332302936, "percentage": 99.7, "elapsed_time": "9:39:31", "remaining_time": "0:01:44", "throughput": 1751.58, "total_tokens": 60905648}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 123.10200927357033, "percentage": 99.71, "elapsed_time": "9:39:35", "remaining_time": "0:01:40", "throughput": 1751.58, "total_tokens": 60913008}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 123.11746522411129, "percentage": 99.72, "elapsed_time": "9:39:40", "remaining_time": "0:01:35", "throughput": 1751.59, "total_tokens": 60920432}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 123.13292117465224, "percentage": 99.74, "elapsed_time": "9:39:44", "remaining_time": "0:01:31", "throughput": 1751.61, "total_tokens": 60928144}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 123.14837712519319, "percentage": 99.75, "elapsed_time": "9:39:48", "remaining_time": "0:01:27", "throughput": 1751.63, "total_tokens": 60936016}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 123.16383307573416, "percentage": 99.76, "elapsed_time": "9:39:52", "remaining_time": "0:01:22", "throughput": 1751.64, "total_tokens": 60943632}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 123.17928902627511, "percentage": 99.78, "elapsed_time": "9:39:56", "remaining_time": "0:01:18", "throughput": 1751.65, "total_tokens": 60951120}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 123.19474497681607, "percentage": 99.79, "elapsed_time": "9:40:00", "remaining_time": "0:01:14", "throughput": 1751.66, "total_tokens": 60958576}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 123.21020092735704, "percentage": 99.8, "elapsed_time": "9:40:04", "remaining_time": "0:01:09", "throughput": 1751.67, "total_tokens": 60966224}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 123.22565687789799, "percentage": 99.81, "elapsed_time": "9:40:08", "remaining_time": "0:01:05", "throughput": 1751.68, "total_tokens": 60973744}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 123.24111282843894, "percentage": 99.83, "elapsed_time": "9:40:12", "remaining_time": "0:01:01", "throughput": 1751.68, "total_tokens": 60980944}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 123.25656877897991, "percentage": 99.84, "elapsed_time": "9:40:16", "remaining_time": "0:00:56", "throughput": 1751.7, "total_tokens": 60988752}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 123.27202472952087, "percentage": 99.85, "elapsed_time": "9:40:21", "remaining_time": "0:00:52", "throughput": 1751.7, "total_tokens": 60996112}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 123.28748068006182, "percentage": 99.86, "elapsed_time": "9:40:25", "remaining_time": "0:00:47", "throughput": 1751.7, "total_tokens": 61003312}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 123.30293663060279, "percentage": 99.88, "elapsed_time": "9:40:29", "remaining_time": "0:00:43", "throughput": 1751.71, "total_tokens": 61010736}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 123.31839258114374, "percentage": 99.89, "elapsed_time": "9:40:33", "remaining_time": "0:00:39", "throughput": 1751.72, "total_tokens": 61018256}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0006, "lr": 1.2961555204693555e-10, "epoch": 123.3338485316847, "percentage": 99.9, "elapsed_time": "9:40:37", "remaining_time": "0:00:34", "throughput": 1751.73, "total_tokens": 61025648}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 123.34930448222566, "percentage": 99.91, "elapsed_time": "9:40:41", "remaining_time": "0:00:30", "throughput": 1751.73, "total_tokens": 61033136}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 123.36476043276662, "percentage": 99.92, "elapsed_time": "9:40:45", "remaining_time": "0:00:26", "throughput": 1751.76, "total_tokens": 61041168}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0004, "lr": 5.212383012986877e-11, "epoch": 123.38021638330757, "percentage": 99.94, "elapsed_time": "9:40:49", "remaining_time": "0:00:21", "throughput": 1751.79, "total_tokens": 61049584}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 123.39567233384854, "percentage": 99.95, "elapsed_time": "9:40:53", "remaining_time": "0:00:17", "throughput": 1751.82, "total_tokens": 61057584}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 123.41112828438949, "percentage": 99.96, "elapsed_time": "9:40:57", "remaining_time": "0:00:13", "throughput": 1751.86, "total_tokens": 61066064}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 123.42658423493044, "percentage": 99.98, "elapsed_time": "9:41:02", "remaining_time": "0:00:08", "throughput": 1751.87, "total_tokens": 61073936}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 123.44204018547141, "percentage": 99.99, "elapsed_time": "9:41:06", "remaining_time": "0:00:04", "throughput": 1751.9, "total_tokens": 61081840}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "9:41:10", "remaining_time": "0:00:00", "throughput": 1751.9, "total_tokens": 61089232}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.330073595046997, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "9:41:18", "remaining_time": "0:00:00", "throughput": 1751.49, "total_tokens": 61089232}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "9:41:20", "remaining_time": "0:00:00", "throughput": 1751.4, "total_tokens": 61089232}