metadata
base_model: Qwen/Qwen2-VL-2B-Instruct
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: qwen2-2b-instruct-trl-sft-mrg
results: []
qwen2-2b-instruct-trl-sft-mrg
This model is a fine-tuned version of Qwen/Qwen2-VL-2B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2108
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1076 | 0.7722 | 50 | 2.0130 |
| 1.7006 | 1.5444 | 100 | 1.6928 |
| 1.5932 | 2.3166 | 150 | 1.5687 |
| 1.5092 | 3.0888 | 200 | 1.4995 |
| 1.4633 | 3.8610 | 250 | 1.4468 |
| 1.3849 | 4.6332 | 300 | 1.4023 |
| 1.3616 | 5.4054 | 350 | 1.3673 |
| 1.361 | 6.1776 | 400 | 1.3386 |
| 1.3253 | 6.9498 | 450 | 1.3159 |
| 1.3204 | 7.7220 | 500 | 1.2976 |
| 1.1944 | 8.4942 | 550 | 1.2814 |
| 1.2286 | 9.2664 | 600 | 1.2703 |
| 1.3097 | 10.0386 | 650 | 1.2532 |
| 1.263 | 10.8108 | 700 | 1.2466 |
| 1.1474 | 11.5830 | 750 | 1.2374 |
| 1.191 | 12.3552 | 800 | 1.2298 |
| 1.09 | 13.1274 | 850 | 1.2246 |
| 1.1622 | 13.8996 | 900 | 1.2130 |
| 1.1883 | 14.6718 | 950 | 1.2108 |
Framework versions
- PEFT 0.11.1
- Transformers 4.45.2
- Pytorch 2.3.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0