355 Commits

Author SHA1 Message Date
gongjy f7127e4310 update lora-sft 2024-11-10 20:40:49 +08:00
gongjy 1240829c89 update train_tokenizer 2024-11-06 17:48:33 +08:00
gongjy 7c67ba0b92 update fast_inference 2024-10-30 15:26:28 +08:00
gongjy db39571493 update readme 2024-10-30 10:39:29 +08:00
gongjy 0bce9e5a31 update eval-chat 2024-10-28 12:57:25 +08:00
gongjy 6d7a988365 update readme 2024-10-27 21:25:55 +08:00
gongjy 0d10efeeed update process 2024-10-27 17:21:29 +08:00
gongjy 517e0a4e7c update readme 2024-10-26 14:35:22 +08:00
gongjy d63c525d04 update readme 2024-10-26 14:32:55 +08:00
gongjy a9e65969c8 update sft-lr 2024-10-24 08:58:31 +08:00
gongjy 42bd06e55d update data_process 2024-10-23 12:25:45 +08:00
gongjy 69bcb8dc90 update data_process 2024-10-23 12:02:28 +08:00
gongjy 3ff66f7221 update model 2024-10-20 15:13:58 +08:00
gongjy 00e09efb5b update num_workers 2024-10-19 06:31:15 +08:00
gongjy f16991d7ec update sft 2024-10-16 22:58:06 +08:00
gongjy 6861d1af56 update rlhf 2024-10-15 15:20:31 +08:00
gongjy c59b8b3e26 update rlhf 2024-10-15 15:04:38 +08:00
gongjy 11d5cadb9c update rlhf 2024-10-15 10:30:32 +08:00
gongjy 02adb7bc0d update trl 2024-10-13 22:44:28 +08:00
gongjy 5c4b34bbe3 update inference 2024-10-13 13:11:41 +08:00
gongjy ad6fc92399 update inference 2024-10-13 13:09:52 +08:00
gongjy 135421690e update data_process 2024-10-12 19:46:08 +08:00
gongjy 2698f6b57d update data_process 2024-10-12 18:47:08 +08:00
gongjy 36fadc7ef1 update lora-sft 2024-10-11 17:43:52 +08:00
gongjy 3a034a47c8 update readme 2024-10-10 22:13:10 +08:00
gongjy 5dbd6174b3 update readme 2024-10-09 09:12:55 +08:00
gongjy 4542ecf858 update readme 2024-10-09 00:03:07 +08:00
gongjy 772834148e update readme 2024-10-08 23:40:29 +08:00
gongjy 000b0a496b update readme 2024-10-08 23:16:29 +08:00
gongjy 5929d0f8b1 update readme 2024-10-07 18:42:53 +08:00
gongjy e4b8789d8c update readme 2024-10-05 22:59:00 +08:00
gongjy eb875da306 update readme 2024-10-05 00:35:54 +08:00
gongjy 1b864453fa update requirements.txt 2024-10-03 14:45:58 +08:00
gongjy a87f628400 update model (fix loss bug) 2024-09-29 16:58:48 +08:00
gongjy 4ef9c41563 fix deepspeed local_rank bug 2024-09-27 23:25:56 +08:00
gongjy 2981d3ea86 Update data preprocessing methods 2024-09-27 22:34:30 +08:00
gongjy 75753ea765 Update data preprocessing methods 2024-09-27 17:19:03 +08:00
gongjy 1cc73836d4 update readme info 2024-09-27 16:38:18 +08:00
gongjy a8ae342775 Update data preprocessing methods 2024-09-27 16:19:30 +08:00
gongjy d57037624b update batchsize 2024-09-25 12:35:29 +08:00
gongjy 89d260145f fix dtype bug 2024-09-25 10:07:30 +08:00
jingyaogong 13105cfa0c Merge pull request #44 from iomgaa-ycz/wandb
修复wandb bug & 添加了argparse
2024-09-24 14:10:05 +08:00
jingyaogong 5dd4e15aa2 Merge branch 'master' into wandb 2024-09-24 14:09:54 +08:00
Yu Chengzhang d7a056a545 更新了ReadMe 2024-09-24 12:45:21 +08:00
Yu Chengzhang 51dcf51c5d 添加了argparse,方便命令行输入参数 2024-09-24 12:41:58 +08:00
Yu Chengzhang ef9a592d14 修复了wandb的bug,避免了多次产生项目 2024-09-24 11:43:30 +08:00
gongjy 7947fa17fb update wandb monitor 2024-09-23 22:16:21 +08:00
gongjy 235b6c6fd3 update wandb monitor 2024-09-23 22:14:52 +08:00
jingyaogong 15f8242ba7 Merge pull request #43 from iomgaa-ycz/wandb
use wandb to monitor training process
2024-09-23 21:54:48 +08:00
Yu Chengzhang 06a66d88c9 添加了wandb 2024-09-23 20:11:45 +08:00