rbelanec commited on
Commit
cc04f8d
·
verified ·
1 Parent(s): 2373ba4

Training in progress, step 39600

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +40 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c372eff331d7f193a3aa651e51327a463b3b4902f51a75a6426c02cade197ed
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccceb97718050bdd524d6e0a92c61866053be12108241a56eeee8696b86bb128
3
  size 58745928
trainer_log.jsonl CHANGED
@@ -8076,3 +8076,43 @@
8076
  {"current_steps": 39400, "total_steps": 40000, "loss": 0.0, "lr": 2.784569627101996e-08, "epoch": 6.4274410637082955, "percentage": 98.5, "elapsed_time": "15:41:43", "remaining_time": "0:14:20", "throughput": 1321.25, "total_tokens": 74655728}
8077
  {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.5050707459449768, "epoch": 6.4274410637082955, "percentage": 98.5, "elapsed_time": "15:44:07", "remaining_time": "0:14:22", "throughput": 1317.89, "total_tokens": 74655728}
8078
  {"current_steps": 39405, "total_steps": 40000, "loss": 0.0, "lr": 2.738438508909924e-08, "epoch": 6.4282567909291135, "percentage": 98.51, "elapsed_time": "15:44:12", "remaining_time": "0:14:15", "throughput": 1317.94, "total_tokens": 74665184}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8076
  {"current_steps": 39400, "total_steps": 40000, "loss": 0.0, "lr": 2.784569627101996e-08, "epoch": 6.4274410637082955, "percentage": 98.5, "elapsed_time": "15:41:43", "remaining_time": "0:14:20", "throughput": 1321.25, "total_tokens": 74655728}
8077
  {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.5050707459449768, "epoch": 6.4274410637082955, "percentage": 98.5, "elapsed_time": "15:44:07", "remaining_time": "0:14:22", "throughput": 1317.89, "total_tokens": 74655728}
8078
  {"current_steps": 39405, "total_steps": 40000, "loss": 0.0, "lr": 2.738438508909924e-08, "epoch": 6.4282567909291135, "percentage": 98.51, "elapsed_time": "15:44:12", "remaining_time": "0:14:15", "throughput": 1317.94, "total_tokens": 74665184}
8079
+ {"current_steps": 39410, "total_steps": 40000, "loss": 0.0674, "lr": 2.692692499833005e-08, "epoch": 6.429072518149931, "percentage": 98.52, "elapsed_time": "15:44:16", "remaining_time": "0:14:08", "throughput": 1318.03, "total_tokens": 74675024}
8080
+ {"current_steps": 39415, "total_steps": 40000, "loss": 0.0, "lr": 2.647331606926151e-08, "epoch": 6.429888245370748, "percentage": 98.54, "elapsed_time": "15:44:20", "remaining_time": "0:14:00", "throughput": 1318.12, "total_tokens": 74684736}
8081
+ {"current_steps": 39420, "total_steps": 40000, "loss": 0.0, "lr": 2.6023558371843225e-08, "epoch": 6.430703972591566, "percentage": 98.55, "elapsed_time": "15:44:23", "remaining_time": "0:13:53", "throughput": 1318.2, "total_tokens": 74693536}
8082
+ {"current_steps": 39425, "total_steps": 40000, "loss": 0.0, "lr": 2.557765197543638e-08, "epoch": 6.431519699812383, "percentage": 98.56, "elapsed_time": "15:44:27", "remaining_time": "0:13:46", "throughput": 1318.29, "total_tokens": 74703680}
8083
+ {"current_steps": 39430, "total_steps": 40000, "loss": 0.0328, "lr": 2.513559694880263e-08, "epoch": 6.4323354270332, "percentage": 98.58, "elapsed_time": "15:44:30", "remaining_time": "0:13:39", "throughput": 1318.36, "total_tokens": 74711664}
8084
+ {"current_steps": 39435, "total_steps": 40000, "loss": 0.0, "lr": 2.469739336011523e-08, "epoch": 6.433151154254017, "percentage": 98.59, "elapsed_time": "15:44:33", "remaining_time": "0:13:31", "throughput": 1318.43, "total_tokens": 74719616}
8085
+ {"current_steps": 39440, "total_steps": 40000, "loss": 0.0, "lr": 2.4263041276947894e-08, "epoch": 6.433966881474835, "percentage": 98.6, "elapsed_time": "15:44:36", "remaining_time": "0:13:24", "throughput": 1318.5, "total_tokens": 74727472}
8086
+ {"current_steps": 39445, "total_steps": 40000, "loss": 0.0001, "lr": 2.3832540766283164e-08, "epoch": 6.434782608695652, "percentage": 98.61, "elapsed_time": "15:44:39", "remaining_time": "0:13:17", "throughput": 1318.58, "total_tokens": 74736704}
8087
+ {"current_steps": 39450, "total_steps": 40000, "loss": 0.0, "lr": 2.3405891894512366e-08, "epoch": 6.4355983359164695, "percentage": 98.62, "elapsed_time": "15:44:42", "remaining_time": "0:13:10", "throughput": 1318.65, "total_tokens": 74744784}
8088
+ {"current_steps": 39455, "total_steps": 40000, "loss": 0.0, "lr": 2.29830947274301e-08, "epoch": 6.436414063137287, "percentage": 98.64, "elapsed_time": "15:44:46", "remaining_time": "0:13:03", "throughput": 1318.74, "total_tokens": 74755104}
8089
+ {"current_steps": 39460, "total_steps": 40000, "loss": 0.0001, "lr": 2.2564149330231432e-08, "epoch": 6.437229790358105, "percentage": 98.65, "elapsed_time": "15:44:50", "remaining_time": "0:12:55", "throughput": 1318.84, "total_tokens": 74766288}
8090
+ {"current_steps": 39465, "total_steps": 40000, "loss": 0.0, "lr": 2.2149055767528572e-08, "epoch": 6.438045517578922, "percentage": 98.66, "elapsed_time": "15:44:54", "remaining_time": "0:12:48", "throughput": 1318.92, "total_tokens": 74775120}
8091
+ {"current_steps": 39470, "total_steps": 40000, "loss": 0.0, "lr": 2.1737814103334197e-08, "epoch": 6.438861244799739, "percentage": 98.67, "elapsed_time": "15:44:57", "remaining_time": "0:12:41", "throughput": 1319.0, "total_tokens": 74783968}
8092
+ {"current_steps": 39475, "total_steps": 40000, "loss": 0.0, "lr": 2.1330424401064253e-08, "epoch": 6.439676972020556, "percentage": 98.69, "elapsed_time": "15:45:00", "remaining_time": "0:12:34", "throughput": 1319.08, "total_tokens": 74792480}
8093
+ {"current_steps": 39480, "total_steps": 40000, "loss": 0.0, "lr": 2.092688672354348e-08, "epoch": 6.440492699241374, "percentage": 98.7, "elapsed_time": "15:45:04", "remaining_time": "0:12:26", "throughput": 1319.16, "total_tokens": 74802016}
8094
+ {"current_steps": 39485, "total_steps": 40000, "loss": 0.0, "lr": 2.0527201133005435e-08, "epoch": 6.441308426462191, "percentage": 98.71, "elapsed_time": "15:45:07", "remaining_time": "0:12:19", "throughput": 1319.23, "total_tokens": 74810080}
8095
+ {"current_steps": 39490, "total_steps": 40000, "loss": 0.0, "lr": 2.0131367691084148e-08, "epoch": 6.442124153683008, "percentage": 98.72, "elapsed_time": "15:45:10", "remaining_time": "0:12:12", "throughput": 1319.31, "total_tokens": 74819040}
8096
+ {"current_steps": 39495, "total_steps": 40000, "loss": 0.0001, "lr": 1.9739386458819675e-08, "epoch": 6.442939880903825, "percentage": 98.74, "elapsed_time": "15:45:14", "remaining_time": "0:12:05", "throughput": 1319.39, "total_tokens": 74828128}
8097
+ {"current_steps": 39500, "total_steps": 40000, "loss": 0.0, "lr": 1.9351257496666442e-08, "epoch": 6.443755608124643, "percentage": 98.75, "elapsed_time": "15:45:17", "remaining_time": "0:11:57", "throughput": 1319.48, "total_tokens": 74838368}
8098
+ {"current_steps": 39505, "total_steps": 40000, "loss": 0.0, "lr": 1.896698086447657e-08, "epoch": 6.444571335345461, "percentage": 98.76, "elapsed_time": "15:45:21", "remaining_time": "0:11:50", "throughput": 1319.59, "total_tokens": 74849536}
8099
+ {"current_steps": 39510, "total_steps": 40000, "loss": 0.0, "lr": 1.8586556621505436e-08, "epoch": 6.445387062566278, "percentage": 98.78, "elapsed_time": "15:45:24", "remaining_time": "0:11:43", "throughput": 1319.66, "total_tokens": 74857392}
8100
+ {"current_steps": 39515, "total_steps": 40000, "loss": 0.0, "lr": 1.820998482642833e-08, "epoch": 6.446202789787095, "percentage": 98.79, "elapsed_time": "15:45:28", "remaining_time": "0:11:36", "throughput": 1319.75, "total_tokens": 74867744}
8101
+ {"current_steps": 39520, "total_steps": 40000, "loss": 0.0, "lr": 1.7837265537309912e-08, "epoch": 6.447018517007913, "percentage": 98.8, "elapsed_time": "15:45:32", "remaining_time": "0:11:29", "throughput": 1319.83, "total_tokens": 74876640}
8102
+ {"current_steps": 39525, "total_steps": 40000, "loss": 0.0, "lr": 1.7468398811629206e-08, "epoch": 6.44783424422873, "percentage": 98.81, "elapsed_time": "15:45:35", "remaining_time": "0:11:21", "throughput": 1319.92, "total_tokens": 74886640}
8103
+ {"current_steps": 39530, "total_steps": 40000, "loss": 0.0, "lr": 1.710338470627404e-08, "epoch": 6.448649971449547, "percentage": 98.83, "elapsed_time": "15:45:39", "remaining_time": "0:11:14", "throughput": 1320.0, "total_tokens": 74896256}
8104
+ {"current_steps": 39535, "total_steps": 40000, "loss": 0.0, "lr": 1.6742223277529945e-08, "epoch": 6.449465698670364, "percentage": 98.84, "elapsed_time": "15:45:42", "remaining_time": "0:11:07", "throughput": 1320.09, "total_tokens": 74905696}
8105
+ {"current_steps": 39540, "total_steps": 40000, "loss": 0.0, "lr": 1.6384914581094036e-08, "epoch": 6.450281425891182, "percentage": 98.85, "elapsed_time": "15:45:45", "remaining_time": "0:11:00", "throughput": 1320.15, "total_tokens": 74913088}
8106
+ {"current_steps": 39545, "total_steps": 40000, "loss": 0.0, "lr": 1.6031458672069455e-08, "epoch": 6.451097153111999, "percentage": 98.86, "elapsed_time": "15:45:49", "remaining_time": "0:10:52", "throughput": 1320.24, "total_tokens": 74922432}
8107
+ {"current_steps": 39550, "total_steps": 40000, "loss": 0.0, "lr": 1.5681855604962602e-08, "epoch": 6.4519128803328165, "percentage": 98.88, "elapsed_time": "15:45:52", "remaining_time": "0:10:45", "throughput": 1320.32, "total_tokens": 74931936}
8108
+ {"current_steps": 39555, "total_steps": 40000, "loss": 0.0, "lr": 1.5336105433683135e-08, "epoch": 6.4527286075536345, "percentage": 98.89, "elapsed_time": "15:45:55", "remaining_time": "0:10:38", "throughput": 1320.39, "total_tokens": 74940048}
8109
+ {"current_steps": 39560, "total_steps": 40000, "loss": 0.0, "lr": 1.499420821155506e-08, "epoch": 6.453544334774452, "percentage": 98.9, "elapsed_time": "15:45:59", "remaining_time": "0:10:31", "throughput": 1320.47, "total_tokens": 74949104}
8110
+ {"current_steps": 39565, "total_steps": 40000, "loss": 0.0, "lr": 1.4656163991302874e-08, "epoch": 6.454360061995269, "percentage": 98.91, "elapsed_time": "15:46:03", "remaining_time": "0:10:24", "throughput": 1320.56, "total_tokens": 74959056}
8111
+ {"current_steps": 39570, "total_steps": 40000, "loss": 0.0, "lr": 1.4321972825051544e-08, "epoch": 6.455175789216086, "percentage": 98.92, "elapsed_time": "15:46:06", "remaining_time": "0:10:16", "throughput": 1320.65, "total_tokens": 74968816}
8112
+ {"current_steps": 39575, "total_steps": 40000, "loss": 0.0, "lr": 1.3991634764345951e-08, "epoch": 6.455991516436903, "percentage": 98.94, "elapsed_time": "15:46:10", "remaining_time": "0:10:09", "throughput": 1320.74, "total_tokens": 74978864}
8113
+ {"current_steps": 39580, "total_steps": 40000, "loss": 0.0, "lr": 1.3665149860120352e-08, "epoch": 6.456807243657721, "percentage": 98.95, "elapsed_time": "15:46:14", "remaining_time": "0:10:02", "throughput": 1320.82, "total_tokens": 74988432}
8114
+ {"current_steps": 39585, "total_steps": 40000, "loss": 0.0, "lr": 1.3342518162728912e-08, "epoch": 6.457622970878538, "percentage": 98.96, "elapsed_time": "15:46:17", "remaining_time": "0:09:55", "throughput": 1320.9, "total_tokens": 74997120}
8115
+ {"current_steps": 39590, "total_steps": 40000, "loss": 0.0, "lr": 1.30237397219235e-08, "epoch": 6.458438698099355, "percentage": 98.98, "elapsed_time": "15:46:20", "remaining_time": "0:09:48", "throughput": 1320.99, "total_tokens": 75006896}
8116
+ {"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 1.2708814586862016e-08, "epoch": 6.459254425320173, "percentage": 98.99, "elapsed_time": "15:46:24", "remaining_time": "0:09:40", "throughput": 1321.07, "total_tokens": 75015984}
8117
+ {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "15:46:28", "remaining_time": "0:09:33", "throughput": 1321.16, "total_tokens": 75025808}
8118
+ {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.5072615146636963, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "15:48:52", "remaining_time": "0:09:35", "throughput": 1317.81, "total_tokens": 75025808}