See axolotl config

axolotl version: 0.12.0.dev0

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: AutoTokenizer

datasets:
  - path: /workspace/axolotl/train_model/data/finetune_dataset.jsonl
    type:
      field_instruction: prompt
      field_output: response
      format: "[INST] {instruction} [/INST]"
      no_input_format: "[INST] {instruction} [/INST]"
      system_prompt: ""  # optionnel

val_set_size: 0.05
output_dir: /workspace/outputs-lovelace
hub_model_id: mikefol/test
sequence_len: 2048
sample_packing: true
eval_sample_packing: false

micro_batch_size: 4
gradient_accumulation_steps: 4
num_epochs: 3

optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5

gradient_checkpointing: true
use_wandb: false
push_to_hub: false
hub_private_repo: false
trust_remote_code: true

save_strategy: "no"
save_optimizer: false
save_safetensors: false

test

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the /workspace/axolotl/train_model/data/finetune_dataset.jsonl 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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• training_steps: 21

Training results

Framework versions

• Transformers 4.53.1
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2