README.md

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-0.5B-Instruct
tags:
  - generated_from_trainer
datasets:
  - wikitext
metrics:
  - accuracy
model-index:
  - name: llm2vec-qwen2.5-0.5-instruct
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: wikitext wikitext-103-raw-v1
          type: wikitext
          args: wikitext-103-raw-v1
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.629556877924779

llm2vec-qwen2.5-0.5-instruct

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the wikitext wikitext-103-raw-v1 dataset. It achieves the following results on the evaluation set:

• Loss: 1.8264
• Accuracy: 0.6296

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: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0083	100	2.3376	0.5511
No log	0.0166	200	2.1736	0.5765
No log	0.0248	300	2.0679	0.5930
No log	0.0331	400	1.9839	0.6056
2.2761	0.0414	500	1.9611	0.6085
2.2761	0.0497	600	1.9054	0.6203
2.2761	0.0580	700	1.8838	0.6242
2.2761	0.0662	800	1.8403	0.6296
2.2761	0.0745	900	1.8235	0.6300
1.8887	0.0828	1000	1.7920	0.6351

Framework versions

• Transformers 4.40.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1