Hugging Face's logo

AayushMathur
/
manim-codellama-7b

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
manim-codellama-7b / README.md
AayushMathur's picture
AayushMathur
Add fine-tuned model
ab202eb
preview code
|
raw
history blame
3.03 kB
metadata
license: llama2
library_name: peft
tags:
  - generated_from_trainer
base_model: codellama/CodeLlama-7b-hf
model-index:
  - name: outputs/lora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: codellama/CodeLlama-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: CodeLlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: AayushMathur/manim_python_alpaca
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience: 
resume_from_checkpoint:
local_rank:
logging_steps: 10
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 10
evals_per_epoch: 2
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

outputs/lora-out

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0169

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: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
No log 0.0140 1 0.8844
0.0605 0.5035 36 0.0284
0.0526 1.0070 72 0.0243
0.0301 1.5105 108 0.0169

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1