swt/DITS_arc_sft_iteration_0

---

sft_iteration_0

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

• Loss: nan

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: 2
• total_train_batch_size: 16
• 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
0.386	0.9994	857	nan
0.2178	2.0	1715	nan
0.1194	2.9994	2572	nan
0.0704	3.9977	3428	nan

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1
• Datasets 3.2.0
• Tokenizers 0.19.1