beneyal/code-llama-7b-spider-qpl-lora

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: beneyal/spider-qpl-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: spider-qpl
wandb_entity:
wandb_watch:
wandb_name: codellama-7b-lora
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: 0.2055

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
2.0333	0.0013	1	1.9589
0.0474	0.2505	195	0.1516
0.0585	0.5010	390	0.1433
0.0321	0.7514	585	0.1540
0.0195	1.0019	780	0.1493
0.0314	1.2524	975	0.1599
0.0053	1.5029	1170	0.1737
0.0095	1.7534	1365	0.1667
0.0237	2.0039	1560	0.1730
0.0131	2.2543	1755	0.1917
0.0038	2.5048	1950	0.1907
0.0089	2.7553	2145	0.1851
0.0025	3.0058	2340	0.1894
0.0018	3.2563	2535	0.2001
0.0039	3.5067	2730	0.2026
0.0014	3.7572	2925	0.2055

Framework versions

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