rbelanec commited on
Commit
62d3581
·
verified ·
1 Parent(s): ce8e2ce

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 sha256:04e7ba2a885fa1df77cfdc09ba8efdf2c7574cf570d8f0d459f90478e13856a6
3
  size 460928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03aa5ea1a2ea1915e63faa5271338d2a616b3d9d2323b477a07fe70b2e4925b6
3
  size 460928
trainer_log.jsonl CHANGED
@@ -8158,3 +8158,44 @@
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.1974, "lr": 1.8690637803880916e-05, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "6:26:49", "remaining_time": "0:01:56", "throughput": 3299.55, "total_tokens": 76581104}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.1904086470603943, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "6:27:57", "remaining_time": "0:01:56", "throughput": 3289.89, "total_tokens": 76581104}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.1806, "lr": 1.7772339163019123e-05, "epoch": 6.493514968594502, "percentage": 99.51, "elapsed_time": "6:28:00", "remaining_time": "0:01:54", "throughput": 3289.91, "total_tokens": 76590896}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.1974, "lr": 1.8690637803880916e-05, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "6:26:49", "remaining_time": "0:01:56", "throughput": 3299.55, "total_tokens": 76581104}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.1904086470603943, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "6:27:57", "remaining_time": "0:01:56", "throughput": 3289.89, "total_tokens": 76581104}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.1806, "lr": 1.7772339163019123e-05, "epoch": 6.493514968594502, "percentage": 99.51, "elapsed_time": "6:28:00", "remaining_time": "0:01:54", "throughput": 3289.91, "total_tokens": 76590896}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.2058, "lr": 1.6877169666457138e-05, "epoch": 6.49433069581532, "percentage": 99.52, "elapsed_time": "6:28:01", "remaining_time": "0:01:51", "throughput": 3290.15, "total_tokens": 76600464}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.1725, "lr": 1.6005129452234532e-05, "epoch": 6.495146423036137, "percentage": 99.54, "elapsed_time": "6:28:02", "remaining_time": "0:01:48", "throughput": 3290.42, "total_tokens": 76610864}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.2651, "lr": 1.5156218654843733e-05, "epoch": 6.495962150256954, "percentage": 99.55, "elapsed_time": "6:28:04", "remaining_time": "0:01:45", "throughput": 3290.68, "total_tokens": 76620688}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.1395, "lr": 1.4330437405196683e-05, "epoch": 6.496777877477771, "percentage": 99.56, "elapsed_time": "6:28:05", "remaining_time": "0:01:42", "throughput": 3290.92, "total_tokens": 76630128}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.2264, "lr": 1.352778583062486e-05, "epoch": 6.497593604698589, "percentage": 99.58, "elapsed_time": "6:28:06", "remaining_time": "0:01:39", "throughput": 3291.11, "total_tokens": 76638128}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.1109, "lr": 1.2748264054929237e-05, "epoch": 6.498409331919406, "percentage": 99.59, "elapsed_time": "6:28:07", "remaining_time": "0:01:36", "throughput": 3291.29, "total_tokens": 76646032}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.229, "lr": 1.1991872198297004e-05, "epoch": 6.499225059140223, "percentage": 99.6, "elapsed_time": "6:28:08", "remaining_time": "0:01:33", "throughput": 3291.57, "total_tokens": 76656768}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.1825, "lr": 1.1258610377384847e-05, "epoch": 6.5000407863610405, "percentage": 99.61, "elapsed_time": "6:28:10", "remaining_time": "0:01:30", "throughput": 3291.88, "total_tokens": 76667984}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.1799, "lr": 1.0548478705268982e-05, "epoch": 6.500856513581859, "percentage": 99.62, "elapsed_time": "6:28:11", "remaining_time": "0:01:27", "throughput": 3292.12, "total_tokens": 76677392}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.145, "lr": 9.86147729147846e-06, "epoch": 6.501672240802676, "percentage": 99.64, "elapsed_time": "6:28:12", "remaining_time": "0:01:24", "throughput": 3292.37, "total_tokens": 76687072}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.1557, "lr": 9.197606241928557e-06, "epoch": 6.502487968023493, "percentage": 99.65, "elapsed_time": "6:28:13", "remaining_time": "0:01:21", "throughput": 3292.62, "total_tokens": 76696976}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.1433, "lr": 8.556865659004042e-06, "epoch": 6.50330369524431, "percentage": 99.66, "elapsed_time": "6:28:14", "remaining_time": "0:01:18", "throughput": 3292.87, "total_tokens": 76706512}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.1818, "lr": 7.939255641525867e-06, "epoch": 6.504119422465128, "percentage": 99.67, "elapsed_time": "6:28:15", "remaining_time": "0:01:15", "throughput": 3293.13, "total_tokens": 76716496}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.1476, "lr": 7.344776284751164e-06, "epoch": 6.504935149685945, "percentage": 99.69, "elapsed_time": "6:28:17", "remaining_time": "0:01:13", "throughput": 3293.36, "total_tokens": 76725744}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.1769, "lr": 6.773427680323296e-06, "epoch": 6.505750876906762, "percentage": 99.7, "elapsed_time": "6:28:18", "remaining_time": "0:01:10", "throughput": 3293.64, "total_tokens": 76736368}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.2424, "lr": 6.225209916355112e-06, "epoch": 6.506566604127579, "percentage": 99.71, "elapsed_time": "6:28:19", "remaining_time": "0:01:07", "throughput": 3293.92, "total_tokens": 76747024}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.108, "lr": 5.7001230774123e-06, "epoch": 6.507382331348397, "percentage": 99.72, "elapsed_time": "6:28:20", "remaining_time": "0:01:04", "throughput": 3294.11, "total_tokens": 76754944}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.2331, "lr": 5.198167244446772e-06, "epoch": 6.5081980585692145, "percentage": 99.74, "elapsed_time": "6:28:21", "remaining_time": "0:01:01", "throughput": 3294.35, "total_tokens": 76764368}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.1131, "lr": 4.71934249487993e-06, "epoch": 6.509013785790032, "percentage": 99.75, "elapsed_time": "6:28:23", "remaining_time": "0:00:58", "throughput": 3294.61, "total_tokens": 76774384}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.1656, "lr": 4.2636489025527075e-06, "epoch": 6.50982951301085, "percentage": 99.76, "elapsed_time": "6:28:24", "remaining_time": "0:00:55", "throughput": 3294.86, "total_tokens": 76784208}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.1535, "lr": 3.831086537742223e-06, "epoch": 6.510645240231667, "percentage": 99.78, "elapsed_time": "6:28:25", "remaining_time": "0:00:52", "throughput": 3295.1, "total_tokens": 76793600}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.109, "lr": 3.4216554671451236e-06, "epoch": 6.511460967452484, "percentage": 99.79, "elapsed_time": "6:28:26", "remaining_time": "0:00:49", "throughput": 3295.31, "total_tokens": 76802192}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.1754, "lr": 3.035355753894242e-06, "epoch": 6.512276694673301, "percentage": 99.8, "elapsed_time": "6:28:27", "remaining_time": "0:00:46", "throughput": 3295.53, "total_tokens": 76811264}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0973, "lr": 2.6721874575752477e-06, "epoch": 6.513092421894118, "percentage": 99.81, "elapsed_time": "6:28:28", "remaining_time": "0:00:43", "throughput": 3295.76, "total_tokens": 76820224}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.1774, "lr": 2.3321506341933418e-06, "epoch": 6.513908149114936, "percentage": 99.83, "elapsed_time": "6:28:30", "remaining_time": "0:00:40", "throughput": 3296.0, "total_tokens": 76829824}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.2046, "lr": 2.0152453361732546e-06, "epoch": 6.514723876335753, "percentage": 99.84, "elapsed_time": "6:28:31", "remaining_time": "0:00:37", "throughput": 3296.23, "total_tokens": 76838992}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.1736, "lr": 1.7214716123925554e-06, "epoch": 6.5155396035565705, "percentage": 99.85, "elapsed_time": "6:28:32", "remaining_time": "0:00:35", "throughput": 3296.47, "total_tokens": 76848464}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.1486, "lr": 1.4508295081649968e-06, "epoch": 6.5163553307773885, "percentage": 99.86, "elapsed_time": "6:28:33", "remaining_time": "0:00:32", "throughput": 3296.72, "total_tokens": 76858288}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.1376, "lr": 1.2033190652238623e-06, "epoch": 6.517171057998206, "percentage": 99.88, "elapsed_time": "6:28:34", "remaining_time": "0:00:29", "throughput": 3296.95, "total_tokens": 76867280}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.1764, "lr": 9.78940321721966e-07, "epoch": 6.517986785219023, "percentage": 99.89, "elapsed_time": "6:28:35", "remaining_time": "0:00:26", "throughput": 3297.2, "total_tokens": 76876992}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.1644, "lr": 7.776933122816132e-07, "epoch": 6.51880251243984, "percentage": 99.9, "elapsed_time": "6:28:37", "remaining_time": "0:00:23", "throughput": 3297.46, "total_tokens": 76887008}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.174, "lr": 5.99578067927986e-07, "epoch": 6.519618239660657, "percentage": 99.91, "elapsed_time": "6:28:38", "remaining_time": "0:00:20", "throughput": 3297.69, "total_tokens": 76896288}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.1172, "lr": 4.445946161224512e-07, "epoch": 6.520433966881475, "percentage": 99.92, "elapsed_time": "6:28:39", "remaining_time": "0:00:17", "throughput": 3297.95, "total_tokens": 76906288}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.1329, "lr": 3.127429807792126e-07, "epoch": 6.521249694102292, "percentage": 99.94, "elapsed_time": "6:28:40", "remaining_time": "0:00:14", "throughput": 3298.13, "total_tokens": 76914000}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.1612, "lr": 2.040231822320049e-07, "epoch": 6.522065421323109, "percentage": 99.95, "elapsed_time": "6:28:41", "remaining_time": "0:00:11", "throughput": 3298.35, "total_tokens": 76923104}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.1581, "lr": 1.1843523723409354e-07, "epoch": 6.522881148543927, "percentage": 99.96, "elapsed_time": "6:28:42", "remaining_time": "0:00:08", "throughput": 3298.63, "total_tokens": 76933424}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.2303, "lr": 5.597915897492811e-08, "epoch": 6.523696875764744, "percentage": 99.98, "elapsed_time": "6:28:44", "remaining_time": "0:00:05", "throughput": 3298.89, "total_tokens": 76943616}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.1853, "lr": 1.6654957113448885e-08, "epoch": 6.524512602985562, "percentage": 99.99, "elapsed_time": "6:28:45", "remaining_time": "0:00:02", "throughput": 3299.14, "total_tokens": 76953296}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.1542, "lr": 4.626377114735902e-10, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "6:28:46", "remaining_time": "0:00:00", "throughput": 3299.39, "total_tokens": 76963024}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.18989315629005432, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "6:29:54", "remaining_time": "0:00:00", "throughput": 3289.79, "total_tokens": 76963024}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "6:29:56", "remaining_time": "0:00:00", "throughput": 3289.55, "total_tokens": 76963024}