onereason-llmrec-final-v8

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

lf_final_v8

This model is a fine-tuned version of /mnt/dolphinfs/hdd_pool/docker/user/hadoop-ht-oedatamining/wujintao09-2/LLM-Rec-Train/output/platform_best on the llmrec_final_v8 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: 5e-07
• train_batch_size: 2
• eval_batch_size: 8
• seed: 2026
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use 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_ratio: 0.05
• training_steps: 150

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.10.0+cu128
• Datasets 5.0.0
• Tokenizers 0.21.4