rbelanec commited on
Commit
d278ca6
·
verified ·
1 Parent(s): 30800f8

Training in progress, step 40000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +41 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ad7e3809ed92bc1a4c66f301ada7e31dc68bdc6bc8a084a7bec4f950e343195
3
  size 18124968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1737cc6a8647c5fcc634858e72c48dabfb129a53bfa16e8994073bc08bdd5f
3
  size 18124968
trainer_log.jsonl CHANGED
@@ -8158,3 +8158,44 @@
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:16:16", "remaining_time": "0:01:53", "throughput": 1526.33, "total_tokens": 34458576}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.1087936162948608, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:16:42", "remaining_time": "0:01:53", "throughput": 1524.53, "total_tokens": 34458576}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 18.767090994813767, "percentage": 99.51, "elapsed_time": "6:16:46", "remaining_time": "0:01:50", "throughput": 1524.45, "total_tokens": 34462688}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:16:16", "remaining_time": "0:01:53", "throughput": 1526.33, "total_tokens": 34458576}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.1087936162948608, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:16:42", "remaining_time": "0:01:53", "throughput": 1524.53, "total_tokens": 34458576}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 18.767090994813767, "percentage": 99.51, "elapsed_time": "6:16:46", "remaining_time": "0:01:50", "throughput": 1524.45, "total_tokens": 34462688}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 18.76944837340877, "percentage": 99.52, "elapsed_time": "6:16:48", "remaining_time": "0:01:47", "throughput": 1524.48, "total_tokens": 34466688}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 18.77180575200377, "percentage": 99.54, "elapsed_time": "6:16:50", "remaining_time": "0:01:45", "throughput": 1524.53, "total_tokens": 34471056}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 18.774163130598772, "percentage": 99.55, "elapsed_time": "6:16:53", "remaining_time": "0:01:42", "throughput": 1524.64, "total_tokens": 34476880}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 18.776520509193777, "percentage": 99.56, "elapsed_time": "6:16:55", "remaining_time": "0:01:39", "throughput": 1524.66, "total_tokens": 34480576}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 18.778877887788777, "percentage": 99.58, "elapsed_time": "6:16:57", "remaining_time": "0:01:36", "throughput": 1524.71, "total_tokens": 34484960}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 18.78123526638378, "percentage": 99.59, "elapsed_time": "6:16:59", "remaining_time": "0:01:33", "throughput": 1524.77, "total_tokens": 34489392}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 18.783592644978782, "percentage": 99.6, "elapsed_time": "6:17:01", "remaining_time": "0:01:30", "throughput": 1524.83, "total_tokens": 34494096}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 18.785950023573786, "percentage": 99.61, "elapsed_time": "6:17:03", "remaining_time": "0:01:28", "throughput": 1524.92, "total_tokens": 34499232}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 18.788307402168787, "percentage": 99.62, "elapsed_time": "6:17:05", "remaining_time": "0:01:25", "throughput": 1524.95, "total_tokens": 34503120}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 18.79066478076379, "percentage": 99.64, "elapsed_time": "6:17:07", "remaining_time": "0:01:22", "throughput": 1524.96, "total_tokens": 34506656}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 18.79302215935879, "percentage": 99.65, "elapsed_time": "6:17:10", "remaining_time": "0:01:19", "throughput": 1524.96, "total_tokens": 34509840}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 18.795379537953796, "percentage": 99.66, "elapsed_time": "6:17:12", "remaining_time": "0:01:16", "throughput": 1525.01, "total_tokens": 34514320}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 18.797736916548796, "percentage": 99.67, "elapsed_time": "6:17:14", "remaining_time": "0:01:13", "throughput": 1525.06, "total_tokens": 34518480}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 18.8000942951438, "percentage": 99.69, "elapsed_time": "6:17:16", "remaining_time": "0:01:10", "throughput": 1525.09, "total_tokens": 34522592}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 18.8024516737388, "percentage": 99.7, "elapsed_time": "6:17:18", "remaining_time": "0:01:08", "throughput": 1525.18, "total_tokens": 34527728}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 18.804809052333805, "percentage": 99.71, "elapsed_time": "6:17:20", "remaining_time": "0:01:05", "throughput": 1525.21, "total_tokens": 34531584}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 18.807166430928806, "percentage": 99.72, "elapsed_time": "6:17:22", "remaining_time": "0:01:02", "throughput": 1525.25, "total_tokens": 34535776}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 18.80952380952381, "percentage": 99.74, "elapsed_time": "6:17:24", "remaining_time": "0:00:59", "throughput": 1525.32, "total_tokens": 34540704}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 18.81188118811881, "percentage": 99.75, "elapsed_time": "6:17:26", "remaining_time": "0:00:56", "throughput": 1525.39, "total_tokens": 34545504}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 18.814238566713815, "percentage": 99.76, "elapsed_time": "6:17:29", "remaining_time": "0:00:53", "throughput": 1525.43, "total_tokens": 34549600}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 18.816595945308816, "percentage": 99.78, "elapsed_time": "6:17:31", "remaining_time": "0:00:51", "throughput": 1525.48, "total_tokens": 34553872}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 18.81895332390382, "percentage": 99.79, "elapsed_time": "6:17:33", "remaining_time": "0:00:48", "throughput": 1525.53, "total_tokens": 34558400}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 18.82131070249882, "percentage": 99.8, "elapsed_time": "6:17:35", "remaining_time": "0:00:45", "throughput": 1525.57, "total_tokens": 34562400}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 18.823668081093825, "percentage": 99.81, "elapsed_time": "6:17:37", "remaining_time": "0:00:42", "throughput": 1525.63, "total_tokens": 34567024}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 18.826025459688825, "percentage": 99.83, "elapsed_time": "6:17:39", "remaining_time": "0:00:39", "throughput": 1525.69, "total_tokens": 34571696}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 18.82838283828383, "percentage": 99.84, "elapsed_time": "6:17:41", "remaining_time": "0:00:36", "throughput": 1525.73, "total_tokens": 34575904}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 18.83074021687883, "percentage": 99.85, "elapsed_time": "6:17:43", "remaining_time": "0:00:34", "throughput": 1525.75, "total_tokens": 34579440}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 18.833097595473834, "percentage": 99.86, "elapsed_time": "6:17:46", "remaining_time": "0:00:31", "throughput": 1525.79, "total_tokens": 34583632}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 18.835454974068835, "percentage": 99.88, "elapsed_time": "6:17:48", "remaining_time": "0:00:28", "throughput": 1525.85, "total_tokens": 34588304}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 18.83781235266384, "percentage": 99.89, "elapsed_time": "6:17:50", "remaining_time": "0:00:25", "throughput": 1525.89, "total_tokens": 34592464}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 18.84016973125884, "percentage": 99.9, "elapsed_time": "6:17:52", "remaining_time": "0:00:22", "throughput": 1525.95, "total_tokens": 34597024}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 18.842527109853844, "percentage": 99.91, "elapsed_time": "6:17:54", "remaining_time": "0:00:19", "throughput": 1526.01, "total_tokens": 34601488}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 18.844884488448844, "percentage": 99.92, "elapsed_time": "6:17:56", "remaining_time": "0:00:17", "throughput": 1526.07, "total_tokens": 34606048}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 18.84724186704385, "percentage": 99.94, "elapsed_time": "6:17:58", "remaining_time": "0:00:14", "throughput": 1526.16, "total_tokens": 34611376}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 18.84959924563885, "percentage": 99.95, "elapsed_time": "6:18:00", "remaining_time": "0:00:11", "throughput": 1526.23, "total_tokens": 34616288}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 18.851956624233853, "percentage": 99.96, "elapsed_time": "6:18:02", "remaining_time": "0:00:08", "throughput": 1526.27, "total_tokens": 34620368}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 18.854314002828854, "percentage": 99.98, "elapsed_time": "6:18:05", "remaining_time": "0:00:05", "throughput": 1526.33, "total_tokens": 34624976}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 18.85667138142386, "percentage": 99.99, "elapsed_time": "6:18:07", "remaining_time": "0:00:02", "throughput": 1526.37, "total_tokens": 34629024}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "6:18:09", "remaining_time": "0:00:00", "throughput": 1526.4, "total_tokens": 34633072}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.11021089553833, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "6:18:36", "remaining_time": "0:00:00", "throughput": 1524.61, "total_tokens": 34633072}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "6:18:37", "remaining_time": "0:00:00", "throughput": 1524.48, "total_tokens": 34633072}