Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
working
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the Amod/mental_health_counseling_conversationsdataset. It achieves the following results on the evaluation set:
- Loss: 1.2984
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1139 | 0.9412 | 12 | 2.3084 |
| 1.9191 | 1.9608 | 25 | 1.7055 |
| 1.6083 | 2.9804 | 38 | 1.5741 |
| 1.496 | 4.0 | 51 | 1.4695 |
| 1.5309 | 4.9412 | 63 | 1.4038 |
| 1.3627 | 5.9608 | 76 | 1.3573 |
| 1.3111 | 6.9804 | 89 | 1.3281 |
| 1.2995 | 8.0 | 102 | 1.3092 |
| 1.3866 | 8.9412 | 114 | 1.2998 |
| 1.18 | 9.4118 | 120 | 1.2984 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for mohityadav/mental-health-advisorGpt
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ