yashrathod123/equitas-lora-v1

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.13.0.dev0

adapter: lora
base_model: unsloth/Llama-3.3-70B-Instruct-bnb-4bit
bf16: auto
datasets:
- path: yashrathod123/equitas_sft_v2.jsonl
  type: chat_template
  ds_type: json
  chat_template: tokenizer_default
hf_use_auth_token: true
gradient_accumulation_steps: 32
gradient_checkpointing: true
learning_rate: 0.0001
load_in_4bit: true
lora_alpha: 128
lora_dropout: 0.05
lora_r: 64
loraplus_lr_ratio: 20
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: ./outputs/equitas_v1
sample_packing: false
sequence_len: 4096
train_on_inputs: false

</details><br>

outputs/equitas_v1

This model is a fine-tuned version of unsloth/Llama-3.3-70B-Instruct-bnb-4bit on the yashrathod123/equitassftv2.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: 0.0001
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWBNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 2
• —training_steps: 49

Training results

Framework versions

• —PEFT 0.17.1
• —Transformers 4.57.0
• —Pytorch 2.7.1+cu126
• —Datasets 4.0.0
• —Tokenizers 0.22.1