seq2seq_huggingface_mix_results

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

• Loss: 7.9457

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: 12
• eval_batch_size: 12
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
10.7021	0.0480	10	10.6458
10.5611	0.0959	20	10.4143
10.2935	0.1439	30	10.0786
9.9673	0.1918	40	9.7462
9.6468	0.2398	50	9.4724
9.4303	0.2878	60	9.2583
9.2452	0.3357	70	9.1136
9.1357	0.3837	80	9.0100
9.0307	0.4317	90	8.9296
8.9363	0.4796	100	8.8591
8.8781	0.5276	110	8.7821
8.7907	0.5755	120	8.7088
8.7214	0.6235	130	8.6329
8.6375	0.6715	140	8.5511
8.5439	0.7194	150	8.4701
8.4715	0.7674	160	8.3835
8.389	0.8153	170	8.2962
8.2787	0.8633	180	8.2072
8.1826	0.9113	190	8.1146
8.0848	0.9592	200	8.0225

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1