gpt-j-claim-generator

This model is a fine-tuned version of EleutherAI/gpt-j-6b on the anli dataset. It achieves the following results on the evaluation set:

• Loss: 0.0232
• Rouge1: 0.8914
• Rouge2: 0.8240
• Rougel: 0.8863
• Rougelsum: 0.8864

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: 1e-05
• train_batch_size: 12
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• total_train_batch_size: 36
• total_eval_batch_size: 3
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.013	1.79	5000	0.0200	0.8921	0.8194	0.8859	0.8860
0.0085	3.58	10000	0.0232	0.8914	0.8240	0.8863	0.8864

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3