apart
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.5095
- eval_runtime: 0.2883
- eval_samples_per_second: 31.212
- eval_steps_per_second: 3.468
- epoch: 2.0
- step: 16
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 25
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for amantimalsina/apart
Base model
mistralai/Mistral-7B-Instruct-v0.2 Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ