2bf162ab-36fe-480c-8e10-1d75b91db0ac

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0596

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-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 60
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0002	1	0.3447
0.8973	0.0087	50	0.1969
0.6048	0.0173	100	0.0803
0.4019	0.0260	150	0.0729
0.2058	0.0346	200	0.0674
0.2319	0.0433	250	0.0644
0.2904	0.0520	300	0.0627
0.149	0.0606	350	0.0609
0.2515	0.0693	400	0.0601
0.2848	0.0779	450	0.0601
0.2237	0.0866	500	0.0596

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1