lldois/v43_v29_paper_mix_low_lr25e7_ep15
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
v43_v29_paper_mix_low_lr25e…/README.md
ModelHub XC 12bf328a3f 初始化项目，由ModelHub XC社区提供模型 
Model: lldois/v43_v29_paper_mix_low_lr25e7_ep15
Source: Original Platform
2026-07-19 02:01:10 +08:00

1.4 KiB
Raw Permalink Blame History

library_name, license, base_model, tags, model-index
library_name license base_model tags model-index
transformers other lldois/v29_v19_user_world_guard_lr8e7_ep018
llama-factory
full
generated_from_trainer
name results
v43_v29_paper_mix_low_lr25e7_ep15

v43_v29_paper_mix_low_lr25e7_ep15

This model is a fine-tuned version of lldois/v29_v19_user_world_guard_lr8e7_ep018 on the exp_v43_paper_mix_low dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2.5e-07
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 202607193
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 0.03
  • num_epochs: 1.5

Training results

Framework versions

  • Transformers 5.6.0
  • Pytorch 2.7.1+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.2