metadata
library_name: peft
base_model: NousResearch/CodeLlama-7b-hf-flash
tags:
- axolotl
- generated_from_trainer
model-index:
- name: c652616d-b61a-42ad-99f7-0902847573e6
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
- 9a604e0f48f65751_train_data.json
ds_type: json
field: text
path: /workspace/input_data/9a604e0f48f65751_train_data.json
type: completion
debug: null
deepspeed: null
device_map: auto
do_eval: true
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: dada22231/c652616d-b61a-42ad-99f7-0902847573e6
hub_strategy: checkpoint
hub_token: null
hub_username: dada22231
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
0: 70GiB
1: 70GiB
2: 70GiB
3: 70GiB
max_steps: 50
micro_batch_size: 1
mlflow_experiment_name: /tmp/9a604e0f48f65751_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
repository_id: dada22231/c652616d-b61a-42ad-99f7-0902847573e6
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: c652616d-b61a-42ad-99f7-0902847573e6
wandb_project: Public_TuningSN
wandb_runid: c652616d-b61a-42ad-99f7-0902847573e6
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null
c652616d-b61a-42ad-99f7-0902847573e6
This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf-flash on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6576
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
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2
- training_steps: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
99.4744 | 0.0003 | 1 | 3.5344 |
106.9513 | 0.0067 | 25 | 2.6999 |
99.1348 | 0.0133 | 50 | 2.6576 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1