chexagent-8b-instruct-trl-sft-ChartQA-24012025_test
This model is a fine-tuned version of StanfordAIMI/CheXagent-8b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0456
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1 | 7.9586 |
| No log | 2.0 | 2 | 7.3588 |
| No log | 3.0 | 3 | 6.6116 |
| No log | 4.0 | 4 | 5.9511 |
| No log | 5.0 | 5 | 5.4401 |
| No log | 6.0 | 6 | 4.9619 |
| No log | 7.0 | 7 | 4.4922 |
| No log | 8.0 | 8 | 4.0456 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for duongdqq/chexagent-8b-instruct-trl-sft-ChartQA-24012025_test
Base model
StanfordAIMI/CheXagent-8b