distilgpt2-career-guidance

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.2505

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.8998	0.3106	100	2.6409
2.6535	0.6211	200	2.4926
2.5251	0.9317	300	2.4158
2.4797	1.2422	400	2.3657
2.4611	1.5528	500	2.3165
2.4078	1.8634	600	2.2876
2.4076	2.1739	700	2.2705
2.3711	2.4845	800	2.2552
2.38	2.7950	900	2.2425
2.3517	3.1056	1000	2.2352
2.3454	3.4161	1100	2.2327
2.3901	3.7267	1200	2.2306

Framework versions

• PEFT 0.18.1
• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 4.5.0
• Tokenizers 0.20.3