mistral-7b-json-quizz-fine-tuned-trl – AI Model by fbellame | AlphaNeural AI

You can deploy this model and start earning money today!

fbellame/
mistral-7b-json-quizz-fine-tuned-trl

like

0

generated_from_trainer

mistralai/Mistral-7B-Instruct-v0.2

Views

No views yet

mistral-7b-json-quizz-fine-tuned-trl

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 48
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	4.36	48	0.6321

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Training procedure

The following bitsandbytes quantization config was used during training:

quant_method: bitsandbytes
load_in_8bit: True
load_in_4bit: False
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

Framework versions

PEFT 0.6.2