Training in progress, step 40000
Browse files- adapter_model.safetensors +1 -1
- 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:
|
3 |
size 1638528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04835ae6b75a703cda5f66b895e1f4642ab9688419b66061fb29ef8a571ee0e5
|
3 |
size 1638528
|
trainer_log.jsonl
CHANGED
@@ -5082,3 +5082,45 @@
|
|
5082 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0827, "lr": 1.9632065447422463e-05, "epoch": 1.8015120306027752, "percentage": 99.49, "elapsed_time": "2 days, 2:05:30", "remaining_time": "0:15:28", "throughput": 360.41, "total_tokens": 64992016}
|
5083 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0352, "lr": 1.8690637803880916e-05, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "2 days, 2:05:33", "remaining_time": "0:15:06", "throughput": 360.44, "total_tokens": 64999728}
|
5084 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08225549757480621, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "2 days, 2:18:21", "remaining_time": "0:15:10", "throughput": 358.91, "total_tokens": 64999728}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5082 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0827, "lr": 1.9632065447422463e-05, "epoch": 1.8015120306027752, "percentage": 99.49, "elapsed_time": "2 days, 2:05:30", "remaining_time": "0:15:28", "throughput": 360.41, "total_tokens": 64992016}
|
5083 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0352, "lr": 1.8690637803880916e-05, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "2 days, 2:05:33", "remaining_time": "0:15:06", "throughput": 360.44, "total_tokens": 64999728}
|
5084 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08225549757480621, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "2 days, 2:18:21", "remaining_time": "0:15:10", "throughput": 358.91, "total_tokens": 64999728}
|
5085 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0569, "lr": 1.7772339163019123e-05, "epoch": 1.801964734376061, "percentage": 99.51, "elapsed_time": "2 days, 2:18:27", "remaining_time": "0:14:47", "throughput": 358.95, "total_tokens": 65007856}
|
5086 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.1054, "lr": 1.6877169666457138e-05, "epoch": 1.802191086262704, "percentage": 99.52, "elapsed_time": "2 days, 2:18:30", "remaining_time": "0:14:24", "throughput": 358.99, "total_tokens": 65016432}
|
5087 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0745, "lr": 1.6005129452234532e-05, "epoch": 1.802417438149347, "percentage": 99.54, "elapsed_time": "2 days, 2:18:33", "remaining_time": "0:14:01", "throughput": 359.02, "total_tokens": 65024112}
|
5088 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0543, "lr": 1.5156218654843733e-05, "epoch": 1.80264379003599, "percentage": 99.55, "elapsed_time": "2 days, 2:18:37", "remaining_time": "0:13:38", "throughput": 359.06, "total_tokens": 65031920}
|
5089 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0753, "lr": 1.4330437405196683e-05, "epoch": 1.802870141922633, "percentage": 99.56, "elapsed_time": "2 days, 2:18:40", "remaining_time": "0:13:15", "throughput": 359.1, "total_tokens": 65039536}
|
5090 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.1265, "lr": 1.352778583062486e-05, "epoch": 1.803096493809276, "percentage": 99.58, "elapsed_time": "2 days, 2:18:44", "remaining_time": "0:12:53", "throughput": 359.13, "total_tokens": 65047632}
|
5091 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0375, "lr": 1.2748264054929237e-05, "epoch": 1.8033228456959187, "percentage": 99.59, "elapsed_time": "2 days, 2:18:47", "remaining_time": "0:12:30", "throughput": 359.17, "total_tokens": 65055792}
|
5092 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0797, "lr": 1.1991872198297004e-05, "epoch": 1.8035491975825617, "percentage": 99.6, "elapsed_time": "2 days, 2:18:51", "remaining_time": "0:12:07", "throughput": 359.21, "total_tokens": 65064240}
|
5093 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0938, "lr": 1.1258610377384847e-05, "epoch": 1.8037755494692047, "percentage": 99.61, "elapsed_time": "2 days, 2:18:54", "remaining_time": "0:11:44", "throughput": 359.25, "total_tokens": 65072528}
|
5094 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0578, "lr": 1.0548478705268982e-05, "epoch": 1.8040019013558477, "percentage": 99.62, "elapsed_time": "2 days, 2:18:58", "remaining_time": "0:11:21", "throughput": 359.29, "total_tokens": 65080432}
|
5095 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0628, "lr": 9.86147729147846e-06, "epoch": 1.8042282532424907, "percentage": 99.64, "elapsed_time": "2 days, 2:19:01", "remaining_time": "0:10:59", "throughput": 359.33, "total_tokens": 65088720}
|
5096 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0739, "lr": 9.197606241928557e-06, "epoch": 1.8044546051291337, "percentage": 99.65, "elapsed_time": "2 days, 2:19:04", "remaining_time": "0:10:36", "throughput": 359.36, "total_tokens": 65096752}
|
5097 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.1043, "lr": 8.556865659004042e-06, "epoch": 1.8046809570157767, "percentage": 99.66, "elapsed_time": "2 days, 2:19:08", "remaining_time": "0:10:13", "throughput": 359.4, "total_tokens": 65105328}
|
5098 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.1094, "lr": 7.939255641525867e-06, "epoch": 1.8049073089024197, "percentage": 99.67, "elapsed_time": "2 days, 2:19:11", "remaining_time": "0:09:50", "throughput": 359.44, "total_tokens": 65113456}
|
5099 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.049, "lr": 7.344776284751164e-06, "epoch": 1.8051336607890627, "percentage": 99.69, "elapsed_time": "2 days, 2:19:15", "remaining_time": "0:09:27", "throughput": 359.48, "total_tokens": 65121552}
|
5100 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.077, "lr": 6.773427680323296e-06, "epoch": 1.8053600126757057, "percentage": 99.7, "elapsed_time": "2 days, 2:19:18", "remaining_time": "0:09:05", "throughput": 359.51, "total_tokens": 65129296}
|
5101 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0719, "lr": 6.225209916355112e-06, "epoch": 1.8055863645623487, "percentage": 99.71, "elapsed_time": "2 days, 2:19:22", "remaining_time": "0:08:42", "throughput": 359.55, "total_tokens": 65137808}
|
5102 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.094, "lr": 5.7001230774123e-06, "epoch": 1.8058127164489917, "percentage": 99.72, "elapsed_time": "2 days, 2:19:25", "remaining_time": "0:08:19", "throughput": 359.59, "total_tokens": 65145744}
|
5103 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0489, "lr": 5.198167244446772e-06, "epoch": 1.8060390683356347, "percentage": 99.74, "elapsed_time": "2 days, 2:19:29", "remaining_time": "0:07:56", "throughput": 359.63, "total_tokens": 65153872}
|
5104 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.086, "lr": 4.71934249487993e-06, "epoch": 1.8062654202222777, "percentage": 99.75, "elapsed_time": "2 days, 2:19:32", "remaining_time": "0:07:34", "throughput": 359.67, "total_tokens": 65162704}
|
5105 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0682, "lr": 4.2636489025527075e-06, "epoch": 1.8064917721089206, "percentage": 99.76, "elapsed_time": "2 days, 2:19:36", "remaining_time": "0:07:11", "throughput": 359.71, "total_tokens": 65171152}
|
5106 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0628, "lr": 3.831086537742223e-06, "epoch": 1.8067181239955636, "percentage": 99.78, "elapsed_time": "2 days, 2:19:39", "remaining_time": "0:06:48", "throughput": 359.75, "total_tokens": 65179472}
|
5107 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0929, "lr": 3.4216554671451236e-06, "epoch": 1.8069444758822066, "percentage": 99.79, "elapsed_time": "2 days, 2:19:43", "remaining_time": "0:06:25", "throughput": 359.79, "total_tokens": 65187056}
|
5108 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0654, "lr": 3.035355753894242e-06, "epoch": 1.8071708277688494, "percentage": 99.8, "elapsed_time": "2 days, 2:19:46", "remaining_time": "0:06:03", "throughput": 359.83, "total_tokens": 65195984}
|
5109 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0837, "lr": 2.6721874575752477e-06, "epoch": 1.8073971796554924, "percentage": 99.81, "elapsed_time": "2 days, 2:19:50", "remaining_time": "0:05:40", "throughput": 359.87, "total_tokens": 65204432}
|
5110 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0586, "lr": 2.3321506341933418e-06, "epoch": 1.8076235315421354, "percentage": 99.83, "elapsed_time": "2 days, 2:19:53", "remaining_time": "0:05:17", "throughput": 359.9, "total_tokens": 65212528}
|
5111 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0266, "lr": 2.0152453361732546e-06, "epoch": 1.8078498834287784, "percentage": 99.84, "elapsed_time": "2 days, 2:19:57", "remaining_time": "0:04:54", "throughput": 359.94, "total_tokens": 65220112}
|
5112 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0601, "lr": 1.7214716123925554e-06, "epoch": 1.8080762353154214, "percentage": 99.85, "elapsed_time": "2 days, 2:20:00", "remaining_time": "0:04:32", "throughput": 359.98, "total_tokens": 65228112}
|
5113 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0732, "lr": 1.4508295081649968e-06, "epoch": 1.8083025872020644, "percentage": 99.86, "elapsed_time": "2 days, 2:20:03", "remaining_time": "0:04:09", "throughput": 360.02, "total_tokens": 65236176}
|
5114 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0808, "lr": 1.2033190652238623e-06, "epoch": 1.8085289390887072, "percentage": 99.88, "elapsed_time": "2 days, 2:20:07", "remaining_time": "0:03:46", "throughput": 360.05, "total_tokens": 65244080}
|
5115 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.052, "lr": 9.78940321721966e-07, "epoch": 1.8087552909753501, "percentage": 99.89, "elapsed_time": "2 days, 2:20:10", "remaining_time": "0:03:24", "throughput": 360.09, "total_tokens": 65251696}
|
5116 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.063, "lr": 7.776933122816132e-07, "epoch": 1.8089816428619931, "percentage": 99.9, "elapsed_time": "2 days, 2:20:14", "remaining_time": "0:03:01", "throughput": 360.12, "total_tokens": 65259664}
|
5117 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.086, "lr": 5.99578067927986e-07, "epoch": 1.8092079947486361, "percentage": 99.91, "elapsed_time": "2 days, 2:20:17", "remaining_time": "0:02:38", "throughput": 360.17, "total_tokens": 65268368}
|
5118 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0511, "lr": 4.445946161224512e-07, "epoch": 1.8094343466352791, "percentage": 99.92, "elapsed_time": "2 days, 2:20:21", "remaining_time": "0:02:16", "throughput": 360.2, "total_tokens": 65276176}
|
5119 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0616, "lr": 3.127429807792126e-07, "epoch": 1.8096606985219221, "percentage": 99.94, "elapsed_time": "2 days, 2:20:24", "remaining_time": "0:01:53", "throughput": 360.24, "total_tokens": 65284688}
|
5120 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0729, "lr": 2.040231822320049e-07, "epoch": 1.8098870504085651, "percentage": 99.95, "elapsed_time": "2 days, 2:20:28", "remaining_time": "0:01:30", "throughput": 360.28, "total_tokens": 65293424}
|
5121 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0558, "lr": 1.1843523723409354e-07, "epoch": 1.8101134022952081, "percentage": 99.96, "elapsed_time": "2 days, 2:20:31", "remaining_time": "0:01:07", "throughput": 360.32, "total_tokens": 65301296}
|
5122 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.1183, "lr": 5.597915897492811e-08, "epoch": 1.8103397541818511, "percentage": 99.98, "elapsed_time": "2 days, 2:20:35", "remaining_time": "0:00:45", "throughput": 360.36, "total_tokens": 65309104}
|
5123 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0612, "lr": 1.6654957113448885e-08, "epoch": 1.810566106068494, "percentage": 99.99, "elapsed_time": "2 days, 2:20:38", "remaining_time": "0:00:22", "throughput": 360.4, "total_tokens": 65317552}
|
5124 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0702, "lr": 4.626377114735902e-10, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "2 days, 2:20:42", "remaining_time": "0:00:00", "throughput": 360.43, "total_tokens": 65325648}
|
5125 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.08223152905702591, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "2 days, 2:33:30", "remaining_time": "0:00:00", "throughput": 358.91, "total_tokens": 65325648}
|
5126 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "2 days, 2:33:31", "remaining_time": "0:00:00", "throughput": 358.91, "total_tokens": 65325648}
|