cbb3edea-f44f-4f5d-a741-114ab3c41308

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: 2.6588

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: 15
• 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
12.4594	0.0014	50	2.9532
11.3756	0.0027	100	2.7818
11.153	0.0041	150	2.7319
10.5846	0.0054	200	2.7018
10.3557	0.0068	250	2.6821
10.4586	0.0081	300	2.6713
10.797	0.0095	350	2.6639
11.2314	0.0108	400	2.6611
10.727	0.0122	450	2.6592
10.859	0.0135	500	2.6588

Framework versions

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