rbelanec commited on
Commit
e548416
·
verified ·
1 Parent(s): c4167d8

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 sha256:8482072b24e18771f0c7be9a742d1c6fd44726d1a55e448e6009a1d2a537103c
3
  size 498936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ae710fbc02df4fd6f32c7bc4421b07b54ff629920751c706939bb80ef7750e
3
  size 498936
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.2329, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "7:23:20", "remaining_time": "0:02:17", "throughput": 2284.73, "total_tokens": 60774960}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.2313, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:23:23", "remaining_time": "0:02:13", "throughput": 2284.76, "total_tokens": 60782960}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3018482029438019, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:23:29", "remaining_time": "0:02:13", "throughput": 2284.22, "total_tokens": 60782960}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.2329, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "7:23:20", "remaining_time": "0:02:17", "throughput": 2284.73, "total_tokens": 60774960}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.2313, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:23:23", "remaining_time": "0:02:13", "throughput": 2284.76, "total_tokens": 60782960}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3018482029438019, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:23:29", "remaining_time": "0:02:13", "throughput": 2284.22, "total_tokens": 60782960}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.2007, "lr": 2.962056527169854e-09, "epoch": 122.85625965996908, "percentage": 99.51, "elapsed_time": "7:23:34", "remaining_time": "0:02:10", "throughput": 2284.09, "total_tokens": 60790352}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.2722, "lr": 2.8128616110761898e-09, "epoch": 122.87171561051005, "percentage": 99.52, "elapsed_time": "7:23:37", "remaining_time": "0:02:07", "throughput": 2284.11, "total_tokens": 60797808}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.2925, "lr": 2.6675215753724223e-09, "epoch": 122.887171561051, "percentage": 99.54, "elapsed_time": "7:23:40", "remaining_time": "0:02:03", "throughput": 2284.14, "total_tokens": 60805808}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.1946, "lr": 2.5260364424739557e-09, "epoch": 122.90262751159196, "percentage": 99.55, "elapsed_time": "7:23:44", "remaining_time": "0:02:00", "throughput": 2284.16, "total_tokens": 60813552}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.2406, "lr": 2.3884062341994475e-09, "epoch": 122.91808346213293, "percentage": 99.56, "elapsed_time": "7:23:47", "remaining_time": "0:01:57", "throughput": 2284.18, "total_tokens": 60821200}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.2495, "lr": 2.25463097177081e-09, "epoch": 122.93353941267388, "percentage": 99.58, "elapsed_time": "7:23:50", "remaining_time": "0:01:53", "throughput": 2284.21, "total_tokens": 60829232}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.2772, "lr": 2.1247106758215397e-09, "epoch": 122.94899536321483, "percentage": 99.59, "elapsed_time": "7:23:53", "remaining_time": "0:01:50", "throughput": 2284.22, "total_tokens": 60836720}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.3358, "lr": 1.998645366382834e-09, "epoch": 122.9644513137558, "percentage": 99.6, "elapsed_time": "7:23:56", "remaining_time": "0:01:46", "throughput": 2284.25, "total_tokens": 60844656}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.1866, "lr": 1.876435062897475e-09, "epoch": 122.97990726429676, "percentage": 99.61, "elapsed_time": "7:23:59", "remaining_time": "0:01:43", "throughput": 2284.27, "total_tokens": 60852336}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.2243, "lr": 1.758079784211497e-09, "epoch": 122.99536321483771, "percentage": 99.62, "elapsed_time": "7:24:02", "remaining_time": "0:01:40", "throughput": 2284.33, "total_tokens": 60861072}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.229, "lr": 1.6435795485797434e-09, "epoch": 123.00927357032458, "percentage": 99.64, "elapsed_time": "7:24:06", "remaining_time": "0:01:36", "throughput": 2284.3, "total_tokens": 60867632}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.2225, "lr": 1.5329343736547596e-09, "epoch": 123.02472952086553, "percentage": 99.65, "elapsed_time": "7:24:09", "remaining_time": "0:01:33", "throughput": 2284.3, "total_tokens": 60874832}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.2594, "lr": 1.4261442765006739e-09, "epoch": 123.04018547140649, "percentage": 99.66, "elapsed_time": "7:24:12", "remaining_time": "0:01:30", "throughput": 2284.32, "total_tokens": 60882512}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.2863, "lr": 1.3232092735876445e-09, "epoch": 123.05564142194746, "percentage": 99.67, "elapsed_time": "7:24:15", "remaining_time": "0:01:26", "throughput": 2284.33, "total_tokens": 60890000}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.2733, "lr": 1.2241293807918607e-09, "epoch": 123.07109737248841, "percentage": 99.69, "elapsed_time": "7:24:18", "remaining_time": "0:01:23", "throughput": 2284.35, "total_tokens": 60897680}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.2334, "lr": 1.128904613387216e-09, "epoch": 123.08655332302936, "percentage": 99.7, "elapsed_time": "7:24:21", "remaining_time": "0:01:20", "throughput": 2284.38, "total_tokens": 60905648}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.2416, "lr": 1.0375349860591853e-09, "epoch": 123.10200927357033, "percentage": 99.71, "elapsed_time": "7:24:24", "remaining_time": "0:01:16", "throughput": 2284.39, "total_tokens": 60913008}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.2936, "lr": 9.5002051290205e-10, "epoch": 123.11746522411129, "percentage": 99.72, "elapsed_time": "7:24:28", "remaining_time": "0:01:13", "throughput": 2284.4, "total_tokens": 60920432}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.2006, "lr": 8.663612074077954e-10, "epoch": 123.13292117465224, "percentage": 99.74, "elapsed_time": "7:24:31", "remaining_time": "0:01:10", "throughput": 2284.42, "total_tokens": 60928144}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.252, "lr": 7.865570824799884e-10, "epoch": 123.14837712519319, "percentage": 99.75, "elapsed_time": "7:24:34", "remaining_time": "0:01:06", "throughput": 2284.45, "total_tokens": 60936016}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.3027, "lr": 7.106081504254514e-10, "epoch": 123.16383307573416, "percentage": 99.76, "elapsed_time": "7:24:37", "remaining_time": "0:01:03", "throughput": 2284.46, "total_tokens": 60943632}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.2114, "lr": 6.385144229570372e-10, "epoch": 123.17928902627511, "percentage": 99.78, "elapsed_time": "7:24:40", "remaining_time": "0:01:00", "throughput": 2284.47, "total_tokens": 60951120}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.2343, "lr": 5.70275911190854e-10, "epoch": 123.19474497681607, "percentage": 99.79, "elapsed_time": "7:24:43", "remaining_time": "0:00:56", "throughput": 2284.49, "total_tokens": 60958576}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.212, "lr": 5.058926256490403e-10, "epoch": 123.21020092735704, "percentage": 99.8, "elapsed_time": "7:24:46", "remaining_time": "0:00:53", "throughput": 2284.5, "total_tokens": 60966224}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.2991, "lr": 4.4536457626254134e-10, "epoch": 123.22565687789799, "percentage": 99.81, "elapsed_time": "7:24:49", "remaining_time": "0:00:50", "throughput": 2284.52, "total_tokens": 60973744}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.2839, "lr": 3.88691772365557e-10, "epoch": 123.24111282843894, "percentage": 99.83, "elapsed_time": "7:24:53", "remaining_time": "0:00:46", "throughput": 2284.52, "total_tokens": 60980944}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.2191, "lr": 3.358742226955425e-10, "epoch": 123.25656877897991, "percentage": 99.84, "elapsed_time": "7:24:56", "remaining_time": "0:00:43", "throughput": 2284.54, "total_tokens": 60988752}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.2159, "lr": 2.8691193539875925e-10, "epoch": 123.27202472952087, "percentage": 99.85, "elapsed_time": "7:24:59", "remaining_time": "0:00:40", "throughput": 2284.55, "total_tokens": 60996112}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.2474, "lr": 2.418049180274995e-10, "epoch": 123.28748068006182, "percentage": 99.86, "elapsed_time": "7:25:02", "remaining_time": "0:00:36", "throughput": 2284.55, "total_tokens": 61003312}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.2608, "lr": 2.005531775373104e-10, "epoch": 123.30293663060279, "percentage": 99.88, "elapsed_time": "7:25:05", "remaining_time": "0:00:33", "throughput": 2284.56, "total_tokens": 61010736}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.2687, "lr": 1.6315672028699435e-10, "epoch": 123.31839258114374, "percentage": 99.89, "elapsed_time": "7:25:08", "remaining_time": "0:00:30", "throughput": 2284.57, "total_tokens": 61018256}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.2167, "lr": 1.2961555204693555e-10, "epoch": 123.3338485316847, "percentage": 99.9, "elapsed_time": "7:25:11", "remaining_time": "0:00:26", "throughput": 2284.58, "total_tokens": 61025648}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.2394, "lr": 9.992967798799768e-11, "epoch": 123.34930448222566, "percentage": 99.91, "elapsed_time": "7:25:15", "remaining_time": "0:00:23", "throughput": 2284.59, "total_tokens": 61033136}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.2314, "lr": 7.409910268707521e-11, "epoch": 123.36476043276662, "percentage": 99.92, "elapsed_time": "7:25:18", "remaining_time": "0:00:20", "throughput": 2284.63, "total_tokens": 61041168}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.2089, "lr": 5.212383012986877e-11, "epoch": 123.38021638330757, "percentage": 99.94, "elapsed_time": "7:25:21", "remaining_time": "0:00:16", "throughput": 2284.67, "total_tokens": 61049584}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.3791, "lr": 3.400386370533415e-11, "epoch": 123.39567233384854, "percentage": 99.95, "elapsed_time": "7:25:24", "remaining_time": "0:00:13", "throughput": 2284.7, "total_tokens": 61057584}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.2373, "lr": 1.9739206205682258e-11, "epoch": 123.41112828438949, "percentage": 99.96, "elapsed_time": "7:25:27", "remaining_time": "0:00:10", "throughput": 2284.75, "total_tokens": 61066064}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.1968, "lr": 9.329859829154685e-12, "epoch": 123.42658423493044, "percentage": 99.98, "elapsed_time": "7:25:30", "remaining_time": "0:00:06", "throughput": 2284.78, "total_tokens": 61073936}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.2698, "lr": 2.7758261855748148e-12, "epoch": 123.44204018547141, "percentage": 99.99, "elapsed_time": "7:25:33", "remaining_time": "0:00:03", "throughput": 2284.81, "total_tokens": 61081840}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.2238, "lr": 7.710628524559838e-14, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:25:37", "remaining_time": "0:00:00", "throughput": 2284.82, "total_tokens": 61089232}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.3018151819705963, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:25:43", "remaining_time": "0:00:00", "throughput": 2284.28, "total_tokens": 61089232}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:25:45", "remaining_time": "0:00:00", "throughput": 2284.12, "total_tokens": 61089232}