metadata
license: other
base_model: Qwen/Qwen1.5-4B
tags:
- generated_from_trainer
datasets:
- tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
metrics:
- accuracy
model-index:
- name: lmind_hotpot_train8000_eval7405_v1_qa_Qwen_Qwen1.5-4B_lora2
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
type: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
metrics:
- name: Accuracy
type: accuracy
value: 0.49263492063492065
library_name: peft
lmind_hotpot_train8000_eval7405_v1_qa_Qwen_Qwen1.5-4B_lora2
This model is a fine-tuned version of Qwen/Qwen1.5-4B on the tyzhu/lmind_hotpot_train8000_eval7405_v1_qa dataset. It achieves the following results on the evaluation set:
- Loss: 3.4933
- Accuracy: 0.4926
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: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2624 | 1.0 | 250 | 2.3220 | 0.5159 |
| 2.0942 | 2.0 | 500 | 2.3289 | 0.5176 |
| 1.8479 | 3.0 | 750 | 2.3997 | 0.5148 |
| 1.6153 | 4.0 | 1000 | 2.5067 | 0.5107 |
| 1.3618 | 5.0 | 1250 | 2.6641 | 0.5052 |
| 1.1477 | 6.0 | 1500 | 2.8411 | 0.5016 |
| 0.9248 | 7.0 | 1750 | 3.0246 | 0.4978 |
| 0.7705 | 8.0 | 2000 | 3.2090 | 0.4954 |
| 0.6344 | 9.0 | 2250 | 3.3400 | 0.4935 |
| 0.5612 | 10.0 | 2500 | 3.4933 | 0.4926 |
Framework versions
- PEFT 0.5.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1