rbelanec commited on
Commit
fb03127
verified
1 Parent(s): 227b206

Training in progress, step 40000

Browse files
Files changed (1) hide show
  1. trainer_log.jsonl +34 -0
trainer_log.jsonl CHANGED
@@ -8165,3 +8165,37 @@
8165
  {"current_steps": 39830, "total_steps": 40000, "loss": 2.7126, "lr": 2.25463097177081e-09, "epoch": 18.778877887788777, "percentage": 99.58, "elapsed_time": "4:48:18", "remaining_time": "0:01:13", "throughput": 1993.47, "total_tokens": 34484960}
8166
  {"current_steps": 39835, "total_steps": 40000, "loss": 2.9239, "lr": 2.1247106758215397e-09, "epoch": 18.78123526638378, "percentage": 99.59, "elapsed_time": "4:48:20", "remaining_time": "0:01:11", "throughput": 1993.54, "total_tokens": 34489392}
8167
  {"current_steps": 39840, "total_steps": 40000, "loss": 2.8779, "lr": 1.998645366382834e-09, "epoch": 18.783592644978782, "percentage": 99.6, "elapsed_time": "4:48:22", "remaining_time": "0:01:09", "throughput": 1993.62, "total_tokens": 34494096}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8165
  {"current_steps": 39830, "total_steps": 40000, "loss": 2.7126, "lr": 2.25463097177081e-09, "epoch": 18.778877887788777, "percentage": 99.58, "elapsed_time": "4:48:18", "remaining_time": "0:01:13", "throughput": 1993.47, "total_tokens": 34484960}
8166
  {"current_steps": 39835, "total_steps": 40000, "loss": 2.9239, "lr": 2.1247106758215397e-09, "epoch": 18.78123526638378, "percentage": 99.59, "elapsed_time": "4:48:20", "remaining_time": "0:01:11", "throughput": 1993.54, "total_tokens": 34489392}
8167
  {"current_steps": 39840, "total_steps": 40000, "loss": 2.8779, "lr": 1.998645366382834e-09, "epoch": 18.783592644978782, "percentage": 99.6, "elapsed_time": "4:48:22", "remaining_time": "0:01:09", "throughput": 1993.62, "total_tokens": 34494096}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 3.3228, "lr": 1.876435062897475e-09, "epoch": 18.785950023573786, "percentage": 99.61, "elapsed_time": "4:48:23", "remaining_time": "0:01:07", "throughput": 1993.73, "total_tokens": 34499232}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 2.8716, "lr": 1.758079784211497e-09, "epoch": 18.788307402168787, "percentage": 99.62, "elapsed_time": "4:48:25", "remaining_time": "0:01:05", "throughput": 1993.77, "total_tokens": 34503120}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 3.8198, "lr": 1.6435795485797434e-09, "epoch": 18.79066478076379, "percentage": 99.64, "elapsed_time": "4:48:27", "remaining_time": "0:01:02", "throughput": 1993.79, "total_tokens": 34506656}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 2.6018, "lr": 1.5329343736547596e-09, "epoch": 18.79302215935879, "percentage": 99.65, "elapsed_time": "4:48:28", "remaining_time": "0:01:00", "throughput": 1993.79, "total_tokens": 34509840}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 2.8018, "lr": 1.4261442765006739e-09, "epoch": 18.795379537953796, "percentage": 99.66, "elapsed_time": "4:48:30", "remaining_time": "0:00:58", "throughput": 1993.86, "total_tokens": 34514320}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 2.5712, "lr": 1.3232092735876445e-09, "epoch": 18.797736916548796, "percentage": 99.67, "elapsed_time": "4:48:31", "remaining_time": "0:00:56", "throughput": 1993.91, "total_tokens": 34518480}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 2.4877, "lr": 1.2241293807918607e-09, "epoch": 18.8000942951438, "percentage": 99.69, "elapsed_time": "4:48:33", "remaining_time": "0:00:54", "throughput": 1993.96, "total_tokens": 34522592}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 2.8133, "lr": 1.128904613387216e-09, "epoch": 18.8024516737388, "percentage": 99.7, "elapsed_time": "4:48:35", "remaining_time": "0:00:52", "throughput": 1994.07, "total_tokens": 34527728}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 2.6114, "lr": 1.0375349860591853e-09, "epoch": 18.804809052333805, "percentage": 99.71, "elapsed_time": "4:48:36", "remaining_time": "0:00:49", "throughput": 1994.11, "total_tokens": 34531584}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 3.037, "lr": 9.5002051290205e-10, "epoch": 18.807166430928806, "percentage": 99.72, "elapsed_time": "4:48:38", "remaining_time": "0:00:47", "throughput": 1994.17, "total_tokens": 34535776}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 2.8981, "lr": 8.663612074077954e-10, "epoch": 18.80952380952381, "percentage": 99.74, "elapsed_time": "4:48:39", "remaining_time": "0:00:45", "throughput": 1994.27, "total_tokens": 34540704}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 3.1379, "lr": 7.865570824799884e-10, "epoch": 18.81188118811881, "percentage": 99.75, "elapsed_time": "4:48:41", "remaining_time": "0:00:43", "throughput": 1994.36, "total_tokens": 34545504}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 2.9067, "lr": 7.106081504254514e-10, "epoch": 18.814238566713815, "percentage": 99.76, "elapsed_time": "4:48:43", "remaining_time": "0:00:41", "throughput": 1994.41, "total_tokens": 34549600}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 2.6965, "lr": 6.385144229570372e-10, "epoch": 18.816595945308816, "percentage": 99.78, "elapsed_time": "4:48:44", "remaining_time": "0:00:39", "throughput": 1994.47, "total_tokens": 34553872}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 3.5139, "lr": 5.70275911190854e-10, "epoch": 18.81895332390382, "percentage": 99.79, "elapsed_time": "4:48:46", "remaining_time": "0:00:36", "throughput": 1994.54, "total_tokens": 34558400}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 3.2675, "lr": 5.058926256490403e-10, "epoch": 18.82131070249882, "percentage": 99.8, "elapsed_time": "4:48:48", "remaining_time": "0:00:34", "throughput": 1994.59, "total_tokens": 34562400}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 2.8594, "lr": 4.4536457626254134e-10, "epoch": 18.823668081093825, "percentage": 99.81, "elapsed_time": "4:48:49", "remaining_time": "0:00:32", "throughput": 1994.67, "total_tokens": 34567024}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 3.3057, "lr": 3.88691772365557e-10, "epoch": 18.826025459688825, "percentage": 99.83, "elapsed_time": "4:48:51", "remaining_time": "0:00:30", "throughput": 1994.76, "total_tokens": 34571696}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 2.587, "lr": 3.358742226955425e-10, "epoch": 18.82838283828383, "percentage": 99.84, "elapsed_time": "4:48:52", "remaining_time": "0:00:28", "throughput": 1994.81, "total_tokens": 34575904}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 3.0663, "lr": 2.8691193539875925e-10, "epoch": 18.83074021687883, "percentage": 99.85, "elapsed_time": "4:48:54", "remaining_time": "0:00:26", "throughput": 1994.83, "total_tokens": 34579440}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 2.4521, "lr": 2.418049180274995e-10, "epoch": 18.833097595473834, "percentage": 99.86, "elapsed_time": "4:48:56", "remaining_time": "0:00:23", "throughput": 1994.89, "total_tokens": 34583632}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 3.6089, "lr": 2.005531775373104e-10, "epoch": 18.835454974068835, "percentage": 99.88, "elapsed_time": "4:48:57", "remaining_time": "0:00:21", "throughput": 1994.97, "total_tokens": 34588304}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 3.0946, "lr": 1.6315672028699435e-10, "epoch": 18.83781235266384, "percentage": 99.89, "elapsed_time": "4:48:59", "remaining_time": "0:00:19", "throughput": 1995.03, "total_tokens": 34592464}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 3.0563, "lr": 1.2961555204693555e-10, "epoch": 18.84016973125884, "percentage": 99.9, "elapsed_time": "4:49:00", "remaining_time": "0:00:17", "throughput": 1995.1, "total_tokens": 34597024}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 2.6256, "lr": 9.992967798799768e-11, "epoch": 18.842527109853844, "percentage": 99.91, "elapsed_time": "4:49:02", "remaining_time": "0:00:15", "throughput": 1995.17, "total_tokens": 34601488}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 2.7651, "lr": 7.409910268707521e-11, "epoch": 18.844884488448844, "percentage": 99.92, "elapsed_time": "4:49:04", "remaining_time": "0:00:13", "throughput": 1995.25, "total_tokens": 34606048}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 3.581, "lr": 5.212383012986877e-11, "epoch": 18.84724186704385, "percentage": 99.94, "elapsed_time": "4:49:05", "remaining_time": "0:00:10", "throughput": 1995.37, "total_tokens": 34611376}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 3.1716, "lr": 3.400386370533415e-11, "epoch": 18.84959924563885, "percentage": 99.95, "elapsed_time": "4:49:07", "remaining_time": "0:00:08", "throughput": 1995.47, "total_tokens": 34616288}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 2.9376, "lr": 1.9739206205682258e-11, "epoch": 18.851956624233853, "percentage": 99.96, "elapsed_time": "4:49:09", "remaining_time": "0:00:06", "throughput": 1995.52, "total_tokens": 34620368}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 2.9238, "lr": 9.329859829154685e-12, "epoch": 18.854314002828854, "percentage": 99.98, "elapsed_time": "4:49:10", "remaining_time": "0:00:04", "throughput": 1995.6, "total_tokens": 34624976}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 2.8333, "lr": 2.7758261855748148e-12, "epoch": 18.85667138142386, "percentage": 99.99, "elapsed_time": "4:49:12", "remaining_time": "0:00:02", "throughput": 1995.65, "total_tokens": 34629024}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 3.5334, "lr": 7.710628524559838e-14, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "4:49:13", "remaining_time": "0:00:00", "throughput": 1995.7, "total_tokens": 34633072}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 2.9843902587890625, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "4:49:34", "remaining_time": "0:00:00", "throughput": 1993.34, "total_tokens": 34633072}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "4:49:36", "remaining_time": "0:00:00", "throughput": 1993.12, "total_tokens": 34633072}