llm2vec-occiglot-mntp

This model is a fine-tuned version of occiglot/occiglot-7b-fr-en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6350
• Accuracy: 0.8495

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0312	100	1.0654	0.7634
No log	0.0624	200	0.8477	0.8062
No log	0.0936	300	0.7627	0.8233
No log	0.1248	400	0.7124	0.8337
1.0065	0.1560	500	0.6822	0.8395
1.0065	0.1871	600	0.6665	0.8435
1.0065	0.2183	700	0.6565	0.8454
1.0065	0.2495	800	0.6352	0.8490
1.0065	0.2807	900	0.6251	0.8517
0.6298	0.3119	1000	0.6350	0.8495

Framework versions

• Transformers 4.40.2
• Pytorch 2.0.1+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1