swt/DITS_math_sft_iteration_0

---

sft_iteration_0

This model is a fine-tuned version of /home/wentaos/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a on the /data/group_data/cx_group/MCTS-agent/my_datasets/math_sft_dpo_DI/sft/iteration_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7719

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: 1e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.5289	0.9988	217	0.5940
0.4472	1.9977	434	0.6037
0.2872	2.9965	651	0.6949
0.2589	3.9954	868	0.7719

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1