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

hub_model_id: noeloco/camel-lora

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: noeloco/fizzbuzz-sft
    type: alpaca
    ds_type: json

hf_use_auth_token: true
push_dataset_to_hub: noeloco
val_set_size: 0.05
output_dir: ./lora-out
chat_template: chatml

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: false
lora_fan_in_fan_out:
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj

wandb_project: runpod1
wandb_entity:
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug: true
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

camel-lora

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0294

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
1.7211	0.06	1	2.5058
1.834	0.29	5	2.4238
1.1688	0.57	10	1.3647
0.483	0.86	15	0.7108
0.3742	1.14	20	0.3942
0.1581	1.43	25	0.2196
0.2905	1.71	30	0.0822
0.1803	2.0	35	0.0548
0.0799	2.29	40	0.0543
0.0932	2.57	45	0.0390
0.0851	2.86	50	0.0328
0.096	3.14	55	0.0287
0.086	3.43	60	0.0289
0.0459	3.71	65	0.0294

Framework versions

PEFT 0.10.1.dev0
Transformers 4.40.0.dev0
Pytorch 2.1.2+cu118
Datasets 2.15.0
Tokenizers 0.15.0