bcf502a9-30b0-411f-911e-b137fff629d3

This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.2967

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: 0.000214
• train_batch_size: 4
• eval_batch_size: 4
• seed: 140
• gradient_accumulation_steps: 2
• 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	6.0451
12.0004	0.0082	50	5.0641
11.026	0.0164	100	4.6035
11.1297	0.0246	150	4.6697
10.8286	0.0328	200	4.5791
11.4491	0.0410	250	4.4946
11.2258	0.0492	300	4.3788
10.5566	0.0573	350	4.4341
10.7347	0.0655	400	4.3284
10.5176	0.0737	450	4.3048
10.7225	0.0819	500	4.2967

Framework versions

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