cls_sentiment_mistral_v1

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.5972

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7365	0.1986	50	0.7344
0.6778	0.3972	100	0.6852
0.6548	0.5958	150	0.6588
0.6728	0.7944	200	0.6333
0.6148	0.9930	250	0.6106
0.43	1.1917	300	0.6174
0.4575	1.3903	350	0.6081
0.4225	1.5889	400	0.6058
0.4136	1.7875	450	0.5976
0.441	1.9861	500	0.5972

Framework versions

• PEFT 0.11.1
• Transformers 4.41.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1