rbelanec commited on
Commit
80b464f
·
verified ·
1 Parent(s): 0a0ebc8

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 sha256:877ef41e57a741285c8769cd4fe333ac5bf03ff14ef9b51d8b3100ad7696148c
3
  size 1074144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bb3222a8ed02aafd303ca300c3746dbf94154fe5c922198ff1b42cd6870e02
3
  size 1074144
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 82.73388773388774, "percentage": 99.49, "elapsed_time": "6:26:50", "remaining_time": "0:01:59", "throughput": 1307.72, "total_tokens": 30352568}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "6:26:52", "remaining_time": "0:01:56", "throughput": 1307.74, "total_tokens": 30356408}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.8783833384513855, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "6:27:01", "remaining_time": "0:01:56", "throughput": 1307.28, "total_tokens": 30356408}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 82.73388773388774, "percentage": 99.49, "elapsed_time": "6:26:50", "remaining_time": "0:01:59", "throughput": 1307.72, "total_tokens": 30352568}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "6:26:52", "remaining_time": "0:01:56", "throughput": 1307.74, "total_tokens": 30356408}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.8783833384513855, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "6:27:01", "remaining_time": "0:01:56", "throughput": 1307.28, "total_tokens": 30356408}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 82.75467775467776, "percentage": 99.51, "elapsed_time": "6:27:04", "remaining_time": "0:01:53", "throughput": 1307.23, "total_tokens": 30360216}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 82.76507276507276, "percentage": 99.52, "elapsed_time": "6:27:07", "remaining_time": "0:01:50", "throughput": 1307.24, "total_tokens": 30363896}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 82.77546777546777, "percentage": 99.54, "elapsed_time": "6:27:10", "remaining_time": "0:01:47", "throughput": 1307.25, "total_tokens": 30367672}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 82.78586278586279, "percentage": 99.55, "elapsed_time": "6:27:12", "remaining_time": "0:01:45", "throughput": 1307.27, "total_tokens": 30371480}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 82.79625779625779, "percentage": 99.56, "elapsed_time": "6:27:15", "remaining_time": "0:01:42", "throughput": 1307.28, "total_tokens": 30375256}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 82.8066528066528, "percentage": 99.58, "elapsed_time": "6:27:18", "remaining_time": "0:01:39", "throughput": 1307.3, "total_tokens": 30379160}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0038, "lr": 2.1247106758215397e-09, "epoch": 82.81704781704782, "percentage": 99.59, "elapsed_time": "6:27:20", "remaining_time": "0:01:36", "throughput": 1307.31, "total_tokens": 30383064}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 82.82744282744282, "percentage": 99.6, "elapsed_time": "6:27:23", "remaining_time": "0:01:33", "throughput": 1307.33, "total_tokens": 30386872}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 82.83783783783784, "percentage": 99.61, "elapsed_time": "6:27:26", "remaining_time": "0:01:30", "throughput": 1307.35, "total_tokens": 30390808}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 82.84823284823285, "percentage": 99.62, "elapsed_time": "6:27:28", "remaining_time": "0:01:27", "throughput": 1307.35, "total_tokens": 30394488}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 82.85862785862786, "percentage": 99.64, "elapsed_time": "6:27:31", "remaining_time": "0:01:24", "throughput": 1307.36, "total_tokens": 30398168}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 82.86902286902287, "percentage": 99.65, "elapsed_time": "6:27:34", "remaining_time": "0:01:21", "throughput": 1307.38, "total_tokens": 30402072}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 82.87941787941789, "percentage": 99.66, "elapsed_time": "6:27:36", "remaining_time": "0:01:18", "throughput": 1307.39, "total_tokens": 30405944}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 82.88981288981289, "percentage": 99.67, "elapsed_time": "6:27:39", "remaining_time": "0:01:15", "throughput": 1307.4, "total_tokens": 30409592}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 82.9002079002079, "percentage": 99.69, "elapsed_time": "6:27:42", "remaining_time": "0:01:12", "throughput": 1307.41, "total_tokens": 30413272}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 82.9106029106029, "percentage": 99.7, "elapsed_time": "6:27:44", "remaining_time": "0:01:10", "throughput": 1307.42, "total_tokens": 30417016}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0167, "lr": 1.0375349860591853e-09, "epoch": 82.92099792099792, "percentage": 99.71, "elapsed_time": "6:27:47", "remaining_time": "0:01:07", "throughput": 1307.43, "total_tokens": 30420824}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0041, "lr": 9.5002051290205e-10, "epoch": 82.93139293139293, "percentage": 99.72, "elapsed_time": "6:27:50", "remaining_time": "0:01:04", "throughput": 1307.44, "total_tokens": 30424664}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 82.94178794178794, "percentage": 99.74, "elapsed_time": "6:27:53", "remaining_time": "0:01:01", "throughput": 1307.46, "total_tokens": 30428632}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 82.95218295218295, "percentage": 99.75, "elapsed_time": "6:27:55", "remaining_time": "0:00:58", "throughput": 1307.47, "total_tokens": 30432344}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 82.96257796257797, "percentage": 99.76, "elapsed_time": "6:27:58", "remaining_time": "0:00:55", "throughput": 1307.48, "total_tokens": 30435928}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 82.97297297297297, "percentage": 99.78, "elapsed_time": "6:28:01", "remaining_time": "0:00:52", "throughput": 1307.49, "total_tokens": 30439832}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 82.98336798336798, "percentage": 99.79, "elapsed_time": "6:28:03", "remaining_time": "0:00:49", "throughput": 1307.51, "total_tokens": 30443736}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 82.993762993763, "percentage": 99.8, "elapsed_time": "6:28:06", "remaining_time": "0:00:46", "throughput": 1307.52, "total_tokens": 30447576}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 83.004158004158, "percentage": 99.81, "elapsed_time": "6:28:09", "remaining_time": "0:00:43", "throughput": 1307.51, "total_tokens": 30451280}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 83.01455301455302, "percentage": 99.83, "elapsed_time": "6:28:12", "remaining_time": "0:00:40", "throughput": 1307.52, "total_tokens": 30455088}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 83.02494802494803, "percentage": 99.84, "elapsed_time": "6:28:14", "remaining_time": "0:00:37", "throughput": 1307.54, "total_tokens": 30458960}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 83.03534303534303, "percentage": 99.85, "elapsed_time": "6:28:17", "remaining_time": "0:00:34", "throughput": 1307.55, "total_tokens": 30462640}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 83.04573804573805, "percentage": 99.86, "elapsed_time": "6:28:20", "remaining_time": "0:00:32", "throughput": 1307.56, "total_tokens": 30466512}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 83.05613305613305, "percentage": 99.88, "elapsed_time": "6:28:22", "remaining_time": "0:00:29", "throughput": 1307.57, "total_tokens": 30470224}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 83.06652806652806, "percentage": 99.89, "elapsed_time": "6:28:25", "remaining_time": "0:00:26", "throughput": 1307.58, "total_tokens": 30473872}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0012, "lr": 1.2961555204693555e-10, "epoch": 83.07692307692308, "percentage": 99.9, "elapsed_time": "6:28:28", "remaining_time": "0:00:23", "throughput": 1307.59, "total_tokens": 30477680}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 83.08731808731808, "percentage": 99.91, "elapsed_time": "6:28:30", "remaining_time": "0:00:20", "throughput": 1307.6, "total_tokens": 30481456}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0118, "lr": 7.409910268707521e-11, "epoch": 83.0977130977131, "percentage": 99.92, "elapsed_time": "6:28:33", "remaining_time": "0:00:17", "throughput": 1307.62, "total_tokens": 30485360}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0001, "lr": 5.212383012986877e-11, "epoch": 83.10810810810811, "percentage": 99.94, "elapsed_time": "6:28:36", "remaining_time": "0:00:14", "throughput": 1307.63, "total_tokens": 30489200}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 83.11850311850311, "percentage": 99.95, "elapsed_time": "6:28:38", "remaining_time": "0:00:11", "throughput": 1307.65, "total_tokens": 30493136}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 83.12889812889813, "percentage": 99.96, "elapsed_time": "6:28:41", "remaining_time": "0:00:08", "throughput": 1307.66, "total_tokens": 30496880}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 83.13929313929314, "percentage": 99.98, "elapsed_time": "6:28:44", "remaining_time": "0:00:05", "throughput": 1307.67, "total_tokens": 30500656}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0009, "lr": 2.7758261855748148e-12, "epoch": 83.14968814968815, "percentage": 99.99, "elapsed_time": "6:28:47", "remaining_time": "0:00:02", "throughput": 1307.69, "total_tokens": 30504496}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "6:28:49", "remaining_time": "0:00:00", "throughput": 1307.7, "total_tokens": 30508240}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.8806253671646118, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "6:28:57", "remaining_time": "0:00:00", "throughput": 1307.24, "total_tokens": 30508240}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "6:28:58", "remaining_time": "0:00:00", "throughput": 1307.19, "total_tokens": 30508240}