bart_tech_keywords

This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8912

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.4049	0.4447	50	1.1729
1.1023	0.8894	100	1.0794
0.9659	1.3341	150	0.9492
0.9226	1.7788	200	0.8965
0.8488	2.2235	250	0.8998
0.8581	2.6681	300	0.8912

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1
• Datasets 2.21.0
• Tokenizers 0.19.1