d2a21a7d-9af7-48da-b2c8-47da10abd770

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: 2.6581

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: 80
• 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	0.0000	1	3.1069
12.4427	0.0014	50	2.9512
11.3815	0.0027	100	2.7796
10.8345	0.0041	150	2.7294
10.5576	0.0054	200	2.6998
10.6862	0.0068	250	2.6820
11.1711	0.0081	300	2.6700
10.8965	0.0095	350	2.6634
10.6425	0.0108	400	2.6595
10.8171	0.0122	450	2.6582
10.5469	0.0135	500	2.6581

Framework versions

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