shubham24/CodeLlama-7b-hf-manim-fine-tuned

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: 4096
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: 4
micro_batch_size: 2
num_epochs: 4
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: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 10
evals_per_epoch: 4
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: 0.0039

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.7377	0.0140	1	0.7414
0.1444	0.2526	18	0.0560
0.0349	0.5053	36	0.0280
0.0429	0.7579	54	0.0206
0.0625	1.0105	72	0.0251
0.0496	1.2632	90	0.0157
0.032	1.5158	108	0.0126
0.0094	1.7684	126	0.0104
0.0453	2.0211	144	0.0087
0.0005	2.2737	162	0.0104
0.0373	2.5263	180	0.0069
0.0262	2.7789	198	0.0056
0.0088	3.0316	216	0.0048
0.0266	3.2842	234	0.0045
0.013	3.5368	252	0.0041
0.0141	3.7895	270	0.0039

Framework versions

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