pythia-1b-deduped-wiki_r_64_alpha_16

This model is a fine-tuned version of EleutherAI/pythia-1b-deduped on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0297

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.0892	0.3	71	2.0820
1.9761	0.61	142	2.0623
1.9197	0.91	213	2.0522
1.8748	1.21	284	2.0495
1.9705	1.51	355	2.0388
1.946	1.82	426	2.0349
2.002	2.12	497	2.0329
1.8831	2.42	568	2.0358
1.8374	2.73	639	2.0297

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.13.0
• Tokenizers 0.13.3