rbelanec commited on
Commit
8dbd6c5
verified
1 Parent(s): 59d9bbf

Training in progress, step 39800

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 sha256:402e03e85246688d1e40ab33da5915b51f33208f62ded640aedeb430fc4477cc
3
  size 460928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29357c69ef6b55c752e9898f1acb751ac4f4861ab9d642508c7d052540cbf175
3
  size 460928
trainer_log.jsonl CHANGED
@@ -8116,3 +8116,44 @@
8116
  {"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 7.625288752117209e-05, "epoch": 280.8199643493761, "percentage": 98.99, "elapsed_time": "4:49:26", "remaining_time": "0:02:57", "throughput": 5820.71, "total_tokens": 101084920}
8117
  {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 7.4386456836667e-05, "epoch": 280.85561497326205, "percentage": 99.0, "elapsed_time": "4:49:28", "remaining_time": "0:02:55", "throughput": 5820.68, "total_tokens": 101096120}
8118
  {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.7351030707359314, "epoch": 280.85561497326205, "percentage": 99.0, "elapsed_time": "4:49:31", "remaining_time": "0:02:55", "throughput": 5819.57, "total_tokens": 101096120}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8116
  {"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 7.625288752117209e-05, "epoch": 280.8199643493761, "percentage": 98.99, "elapsed_time": "4:49:26", "remaining_time": "0:02:57", "throughput": 5820.71, "total_tokens": 101084920}
8117
  {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 7.4386456836667e-05, "epoch": 280.85561497326205, "percentage": 99.0, "elapsed_time": "4:49:28", "remaining_time": "0:02:55", "throughput": 5820.68, "total_tokens": 101096120}
8118
  {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.7351030707359314, "epoch": 280.85561497326205, "percentage": 99.0, "elapsed_time": "4:49:31", "remaining_time": "0:02:55", "throughput": 5819.57, "total_tokens": 101096120}
8119
+ {"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 7.254314656586214e-05, "epoch": 280.89126559714794, "percentage": 99.01, "elapsed_time": "4:49:35", "remaining_time": "0:02:53", "throughput": 5819.17, "total_tokens": 101110520}
8120
+ {"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 7.07229569929968e-05, "epoch": 280.9269162210339, "percentage": 99.02, "elapsed_time": "4:49:37", "remaining_time": "0:02:51", "throughput": 5819.24, "total_tokens": 101123768}
8121
+ {"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 6.892588839879643e-05, "epoch": 280.96256684491976, "percentage": 99.04, "elapsed_time": "4:49:39", "remaining_time": "0:02:48", "throughput": 5819.24, "total_tokens": 101135672}
8122
+ {"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 6.71519410603727e-05, "epoch": 280.9982174688057, "percentage": 99.05, "elapsed_time": "4:49:41", "remaining_time": "0:02:46", "throughput": 5819.27, "total_tokens": 101147992}
8123
+ {"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 6.540111525129011e-05, "epoch": 281.0285204991087, "percentage": 99.06, "elapsed_time": "4:49:43", "remaining_time": "0:02:44", "throughput": 5819.1, "total_tokens": 101156960}
8124
+ {"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 6.367341124154934e-05, "epoch": 281.06417112299465, "percentage": 99.08, "elapsed_time": "4:49:45", "remaining_time": "0:02:42", "throughput": 5819.15, "total_tokens": 101170016}
8125
+ {"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 6.19688292975873e-05, "epoch": 281.0998217468806, "percentage": 99.09, "elapsed_time": "4:49:47", "remaining_time": "0:02:40", "throughput": 5819.23, "total_tokens": 101183584}
8126
+ {"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 6.0287369682260336e-05, "epoch": 281.1354723707665, "percentage": 99.1, "elapsed_time": "4:49:49", "remaining_time": "0:02:37", "throughput": 5819.29, "total_tokens": 101196672}
8127
+ {"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 5.8629032654894384e-05, "epoch": 281.1711229946524, "percentage": 99.11, "elapsed_time": "4:49:51", "remaining_time": "0:02:35", "throughput": 5819.32, "total_tokens": 101209344}
8128
+ {"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 5.699381847120155e-05, "epoch": 281.2067736185383, "percentage": 99.12, "elapsed_time": "4:49:54", "remaining_time": "0:02:33", "throughput": 5819.37, "total_tokens": 101222240}
8129
+ {"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 5.5381727383380094e-05, "epoch": 281.24242424242425, "percentage": 99.14, "elapsed_time": "4:49:56", "remaining_time": "0:02:31", "throughput": 5819.44, "total_tokens": 101235648}
8130
+ {"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 5.379275964001451e-05, "epoch": 281.27807486631013, "percentage": 99.15, "elapsed_time": "4:49:58", "remaining_time": "0:02:29", "throughput": 5819.43, "total_tokens": 101247232}
8131
+ {"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 5.222691548614211e-05, "epoch": 281.3137254901961, "percentage": 99.16, "elapsed_time": "4:50:00", "remaining_time": "0:02:26", "throughput": 5819.5, "total_tokens": 101260512}
8132
+ {"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 5.068419516323641e-05, "epoch": 281.349376114082, "percentage": 99.17, "elapsed_time": "4:50:02", "remaining_time": "0:02:24", "throughput": 5819.58, "total_tokens": 101274016}
8133
+ {"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 4.91645989092071e-05, "epoch": 281.3850267379679, "percentage": 99.19, "elapsed_time": "4:50:04", "remaining_time": "0:02:22", "throughput": 5819.59, "total_tokens": 101285952}
8134
+ {"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 4.7668126958400056e-05, "epoch": 281.42067736185385, "percentage": 99.2, "elapsed_time": "4:50:06", "remaining_time": "0:02:20", "throughput": 5819.67, "total_tokens": 101299488}
8135
+ {"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 4.619477954159734e-05, "epoch": 281.45632798573973, "percentage": 99.21, "elapsed_time": "4:50:08", "remaining_time": "0:02:18", "throughput": 5819.76, "total_tokens": 101313312}
8136
+ {"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 4.4744556885983884e-05, "epoch": 281.4919786096257, "percentage": 99.22, "elapsed_time": "4:50:10", "remaining_time": "0:02:15", "throughput": 5819.81, "total_tokens": 101325920}
8137
+ {"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 4.331745921523078e-05, "epoch": 281.52762923351156, "percentage": 99.24, "elapsed_time": "4:50:12", "remaining_time": "0:02:13", "throughput": 5819.85, "total_tokens": 101338752}
8138
+ {"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 4.191348674937867e-05, "epoch": 281.5632798573975, "percentage": 99.25, "elapsed_time": "4:50:14", "remaining_time": "0:02:11", "throughput": 5819.9, "total_tokens": 101351520}
8139
+ {"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 4.0532639704971006e-05, "epoch": 281.59893048128345, "percentage": 99.26, "elapsed_time": "4:50:16", "remaining_time": "0:02:09", "throughput": 5819.95, "total_tokens": 101364576}
8140
+ {"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 3.917491829493747e-05, "epoch": 281.63458110516933, "percentage": 99.28, "elapsed_time": "4:50:18", "remaining_time": "0:02:07", "throughput": 5820.05, "total_tokens": 101378720}
8141
+ {"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 3.78403227286439e-05, "epoch": 281.6702317290553, "percentage": 99.29, "elapsed_time": "4:50:20", "remaining_time": "0:02:05", "throughput": 5820.04, "total_tokens": 101390144}
8142
+ {"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 3.652885321192567e-05, "epoch": 281.70588235294116, "percentage": 99.3, "elapsed_time": "4:50:22", "remaining_time": "0:02:02", "throughput": 5820.05, "total_tokens": 101402144}
8143
+ {"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 3.524050994702099e-05, "epoch": 281.7415329768271, "percentage": 99.31, "elapsed_time": "4:50:24", "remaining_time": "0:02:00", "throughput": 5820.09, "total_tokens": 101414816}
8144
+ {"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 3.3975293132604276e-05, "epoch": 281.777183600713, "percentage": 99.33, "elapsed_time": "4:50:27", "remaining_time": "0:01:58", "throughput": 5820.19, "total_tokens": 101428992}
8145
+ {"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 3.2733202963786125e-05, "epoch": 281.81283422459893, "percentage": 99.34, "elapsed_time": "4:50:29", "remaining_time": "0:01:56", "throughput": 5820.21, "total_tokens": 101441120}
8146
+ {"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 3.15142396321133e-05, "epoch": 281.8484848484849, "percentage": 99.35, "elapsed_time": "4:50:31", "remaining_time": "0:01:54", "throughput": 5820.23, "total_tokens": 101453408}
8147
+ {"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 3.0318403325552132e-05, "epoch": 281.88413547237076, "percentage": 99.36, "elapsed_time": "4:50:33", "remaining_time": "0:01:51", "throughput": 5820.29, "total_tokens": 101466560}
8148
+ {"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 2.914569422855506e-05, "epoch": 281.9197860962567, "percentage": 99.38, "elapsed_time": "4:50:35", "remaining_time": "0:01:49", "throughput": 5820.4, "total_tokens": 101480768}
8149
+ {"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 2.7996112521927462e-05, "epoch": 281.9554367201426, "percentage": 99.39, "elapsed_time": "4:50:37", "remaining_time": "0:01:47", "throughput": 5820.5, "total_tokens": 101494816}
8150
+ {"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 2.68696583829775e-05, "epoch": 281.99108734402853, "percentage": 99.4, "elapsed_time": "4:50:39", "remaining_time": "0:01:45", "throughput": 5820.56, "total_tokens": 101507936}
8151
+ {"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 2.576633198539957e-05, "epoch": 282.02139037433153, "percentage": 99.41, "elapsed_time": "4:50:41", "remaining_time": "0:01:43", "throughput": 5820.5, "total_tokens": 101519088}
8152
+ {"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 2.46861334993409e-05, "epoch": 282.0570409982175, "percentage": 99.42, "elapsed_time": "4:50:43", "remaining_time": "0:01:40", "throughput": 5820.43, "total_tokens": 101531216}
8153
+ {"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 2.3629063091384903e-05, "epoch": 282.09269162210336, "percentage": 99.44, "elapsed_time": "4:50:46", "remaining_time": "0:01:38", "throughput": 5820.49, "total_tokens": 101544592}
8154
+ {"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 2.2595120924567834e-05, "epoch": 282.1283422459893, "percentage": 99.45, "elapsed_time": "4:50:48", "remaining_time": "0:01:36", "throughput": 5820.52, "total_tokens": 101556912}
8155
+ {"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 2.158430715829551e-05, "epoch": 282.16399286987524, "percentage": 99.46, "elapsed_time": "4:50:50", "remaining_time": "0:01:34", "throughput": 5820.62, "total_tokens": 101570960}
8156
+ {"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 2.059662194849321e-05, "epoch": 282.19964349376113, "percentage": 99.48, "elapsed_time": "4:50:52", "remaining_time": "0:01:32", "throughput": 5820.68, "total_tokens": 101584304}
8157
+ {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "4:50:54", "remaining_time": "0:01:29", "throughput": 5820.74, "total_tokens": 101597328}
8158
+ {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:56", "remaining_time": "0:01:27", "throughput": 5820.78, "total_tokens": 101609904}
8159
+ {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7435283064842224, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:59", "remaining_time": "0:01:27", "throughput": 5819.68, "total_tokens": 101609904}