StanfordAIMI/GREEN-RadPhi2

outputs_20240325

This model is a fine-tuned version of StanfordAIMI/RadPhi-2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0816

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 32
• total_train_batch_size: 2048
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 12.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.1831	0.64	25	0.1257
0.1239	1.28	50	0.1044
0.108	1.92	75	0.0995
0.0976	2.56	100	0.0978
0.094	3.2	125	0.0886
0.0828	3.84	150	0.0893
0.078	4.48	175	0.0907
0.0767	5.12	200	0.0866
0.0697	5.76	225	0.0840
0.0646	6.39	250	0.0819
0.0594	7.03	275	0.0795
0.052	7.67	300	0.0795
0.0478	8.31	325	0.0803
0.0447	8.95	350	0.0786
0.0392	9.59	375	0.0800
0.038	10.23	400	0.0813
0.0357	10.87	425	0.0810
0.035	11.51	450	0.0816

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2