tanganke's picture
Upload folder using huggingface_hub
32c1ec9 verified
[2024-12-01 00:02:59,178][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/8
[2024-12-01 00:02:59,183][fusion_bench.programs.fabric_fusion_program][INFO] - Running the model fusion program.
[2024-12-01 00:02:59,184][fusion_bench.programs.fabric_fusion_program][INFO] - loading model pool
[2024-12-01 00:02:59,236][fusion_bench.mixins.serialization][WARNING] - Unused argument: pretrained_model_name_or_path=meta-llama/Llama-3.2-1B-Instruct
[2024-12-01 00:02:59,237][fusion_bench.programs.fabric_fusion_program][INFO] - loading method
[2024-12-01 00:02:59,243][fusion_bench.programs.fabric_fusion_program][INFO] - loading task pool
[2024-12-01 00:02:59,245][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading tokenizer.
[2024-12-01 00:03:00,170][fusion_bench.modelpool.causal_lm.causal_lm][INFO] - Loading model: _pretrained_
[2024-12-01 00:03:08,340][fusion_bench.mixins.fabric_training][INFO] - Expected total steps: 1367
[2024-12-01 00:03:08,344][fusion_bench.method.lm_finetune.bradley_terry_rm][INFO] - Setting key `T_max` of lr_scheduler configuration to 1367
[2024-12-01 00:13:54,904][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
[2024-12-01 00:18:32,680][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4296 > 4096. Truncating input.
[2024-12-01 00:51:55,489][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
[2024-12-01 01:02:14,833][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4360 > 4096. Truncating input.
[2024-12-01 01:29:08,474][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4399 > 4096. Truncating input.
[2024-12-01 01:32:02,731][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4547 > 4096. Truncating input.
[2024-12-01 02:18:09,730][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4291 > 4096. Truncating input.
[2024-12-01 02:24:35,692][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4601 > 4096. Truncating input.
[2024-12-01 02:38:24,510][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4228 > 4096. Truncating input.
[2024-12-01 02:49:27,652][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4257 > 4096. Truncating input.
[2024-12-01 03:49:27,820][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4570 > 4096. Truncating input.
[2024-12-01 04:11:57,917][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5525 > 4096. Truncating input.
[2024-12-01 04:12:32,372][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4642 > 4096. Truncating input.
[2024-12-01 04:16:37,798][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4525 > 4096. Truncating input.
[2024-12-01 04:17:35,384][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4274 > 4096. Truncating input.
[2024-12-01 04:19:11,675][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5526 > 4096. Truncating input.
[2024-12-01 04:52:37,768][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
[2024-12-01 04:53:53,309][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5315 > 4096. Truncating input.
[2024-12-01 06:03:32,001][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4221 > 4096. Truncating input.
[2024-12-01 06:22:05,739][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
[2024-12-01 07:00:23,297][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4555 > 4096. Truncating input.
[2024-12-01 07:19:10,907][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4479 > 4096. Truncating input.
[2024-12-01 07:33:50,729][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4826 > 4096. Truncating input.
[2024-12-01 07:34:53,468][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4582 > 4096. Truncating input.
[2024-12-01 08:10:50,613][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4297 > 4096. Truncating input.
[2024-12-01 08:24:53,508][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4646 > 4096. Truncating input.
[2024-12-01 08:30:08,276][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4250 > 4096. Truncating input.
[2024-12-01 08:42:45,451][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4312 > 4096. Truncating input.
[2024-12-01 08:53:44,394][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
[2024-12-01 09:23:04,435][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5602 > 4096. Truncating input.
[2024-12-01 09:28:58,176][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4699 > 4096. Truncating input.
[2024-12-01 09:36:45,893][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6295 > 4096. Truncating input.
[2024-12-01 09:48:14,500][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4514 > 4096. Truncating input.
[2024-12-01 10:49:52,885][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4849 > 4096. Truncating input.
[2024-12-01 10:56:25,966][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4117 > 4096. Truncating input.
[2024-12-01 11:45:16,117][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4785 > 4096. Truncating input.
[2024-12-01 12:02:40,995][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4393 > 4096. Truncating input.
[2024-12-01 12:04:28,428][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4153 > 4096. Truncating input.
[2024-12-01 13:33:33,082][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4558 > 4096. Truncating input.
[2024-12-01 13:48:57,757][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4587 > 4096. Truncating input.
[2024-12-01 13:51:30,230][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4875 > 4096. Truncating input.
[2024-12-01 14:05:15,857][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4241 > 4096. Truncating input.
[2024-12-01 14:43:29,359][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4103 > 4096. Truncating input.
[2024-12-01 14:55:05,214][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6179 > 4096. Truncating input.
[2024-12-01 14:59:29,757][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4571 > 4096. Truncating input.
[2024-12-01 15:01:46,670][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4800 > 4096. Truncating input.
[2024-12-01 15:09:30,440][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4998 > 4096. Truncating input.
[2024-12-01 15:23:27,067][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4948 > 4096. Truncating input.
[2024-12-01 16:30:16,533][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4545 > 4096. Truncating input.
[2024-12-01 16:52:44,415][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.
[2024-12-01 17:50:56,985][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4434 > 4096. Truncating input.
[2024-12-01 18:35:47,988][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5025 > 4096. Truncating input.
[2024-12-01 18:41:51,220][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4557 > 4096. Truncating input.
[2024-12-01 18:48:31,601][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4524 > 4096. Truncating input.
[2024-12-01 19:13:09,334][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4177 > 4096. Truncating input.
[2024-12-01 19:20:27,822][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4733 > 4096. Truncating input.
[2024-12-01 20:03:19,362][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4505 > 4096. Truncating input.
[2024-12-01 20:48:52,846][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4369 > 4096. Truncating input.
[2024-12-01 20:55:23,249][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4119 > 4096. Truncating input.
[2024-12-01 22:32:18,376][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4963 > 4096. Truncating input.
[2024-12-01 22:33:44,379][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4341 > 4096. Truncating input.
[2024-12-01 22:46:03,520][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5770 > 4096. Truncating input.
[2024-12-01 23:01:48,003][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 8099 > 4096. Truncating input.
[2024-12-01 23:11:30,341][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4585 > 4096. Truncating input.
[2024-12-01 23:24:16,836][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4224 > 4096. Truncating input.
[2024-12-01 23:42:32,402][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4790 > 4096. Truncating input.
[2024-12-01 23:54:36,880][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4828 > 4096. Truncating input.
[2024-12-02 00:00:43,016][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4598 > 4096. Truncating input.
[2024-12-02 00:47:58,909][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4985 > 4096. Truncating input.
[2024-12-02 00:59:32,922][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4663 > 4096. Truncating input.
[2024-12-02 01:05:15,428][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4811 > 4096. Truncating input.
[2024-12-02 01:11:54,229][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4291 > 4096. Truncating input.
[2024-12-02 01:42:01,942][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
[2024-12-02 01:44:43,177][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4142 > 4096. Truncating input.
[2024-12-02 03:48:28,140][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4140 > 4096. Truncating input.
[2024-12-02 04:02:00,107][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5839 > 4096. Truncating input.
[2024-12-02 04:15:23,453][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4362 > 4096. Truncating input.
[2024-12-02 04:17:47,445][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6295 > 4096. Truncating input.
[2024-12-02 04:39:12,111][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4752 > 4096. Truncating input.
[2024-12-02 04:47:16,553][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4164 > 4096. Truncating input.
[2024-12-02 06:07:56,326][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4665 > 4096. Truncating input.
[2024-12-02 06:27:16,794][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4239 > 4096. Truncating input.
[2024-12-02 06:30:32,196][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4102 > 4096. Truncating input.
[2024-12-02 06:54:11,922][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4722 > 4096. Truncating input.
[2024-12-02 07:12:25,268][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5603 > 4096. Truncating input.
[2024-12-02 07:57:00,936][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4699 > 4096. Truncating input.
[2024-12-02 08:05:24,091][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5032 > 4096. Truncating input.
[2024-12-02 08:46:30,033][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5082 > 4096. Truncating input.
[2024-12-02 09:09:02,594][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4302 > 4096. Truncating input.
[2024-12-02 09:20:05,038][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4917 > 4096. Truncating input.
[2024-12-02 09:42:50,646][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4414 > 4096. Truncating input.
[2024-12-02 11:36:16,670][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4926 > 4096. Truncating input.
[2024-12-02 11:38:03,763][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4162 > 4096. Truncating input.
[2024-12-02 11:47:25,860][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4537 > 4096. Truncating input.
[2024-12-02 12:19:29,169][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4846 > 4096. Truncating input.
[2024-12-02 12:25:16,281][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5195 > 4096. Truncating input.
[2024-12-02 14:25:30,297][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4310 > 4096. Truncating input.
[2024-12-02 14:56:36,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4705 > 4096. Truncating input.
[2024-12-02 15:09:47,465][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4380 > 4096. Truncating input.
[2024-12-02 15:22:15,867][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 6428 > 4096. Truncating input.
[2024-12-02 15:24:55,716][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4710 > 4096. Truncating input.
[2024-12-02 15:36:18,579][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4259 > 4096. Truncating input.
[2024-12-02 15:43:18,015][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4203 > 4096. Truncating input.
[2024-12-02 15:44:31,177][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 5525 > 4096. Truncating input.
[2024-12-02 16:21:47,561][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4492 > 4096. Truncating input.
[2024-12-02 16:27:50,367][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4177 > 4096. Truncating input.
[2024-12-02 16:34:12,479][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4130 > 4096. Truncating input.
[2024-12-02 16:59:17,693][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4984 > 4096. Truncating input.
[2024-12-02 17:02:57,992][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4292 > 4096. Truncating input.
[2024-12-02 17:30:41,525][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4718 > 4096. Truncating input.
[2024-12-02 17:45:13,002][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 4569 > 4096. Truncating input.
[2024-12-02 18:19:00,014][fusion_bench.method.lm_finetune.bradley_terry_rm][WARNING] - Input length exceeds max_length: 9431 > 4096. Truncating input.