See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3f04769e23461448_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3f04769e23461448_train_data.json
  type:
    field_input: text
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: tryingpro/0ae523de-1b1b-4d1b-b5d7-f297c5c65b03
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
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
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 90
micro_batch_size: 2
mlflow_experiment_name: /tmp/3f04769e23461448_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: tryingpro-unicourt
wandb_mode: online
wandb_name: 906b0229-8d6c-434f-83f6-3c3edcbe4bb7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 906b0229-8d6c-434f-83f6-3c3edcbe4bb7
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

0ae523de-1b1b-4d1b-b5d7-f297c5c65b03

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: 0.0000

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: 32
• total_train_batch_size: 64
• 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-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 90

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0259	1	0.2131
6.3657	0.2073	8	0.1076
0.4109	0.4146	16	0.0013
0.0077	0.6219	24	0.0008
0.0045	0.8291	32	0.0002
0.0021	1.0470	40	0.0000
0.0008	1.2543	48	0.0000
0.0006	1.4615	56	0.0000
0.001	1.6688	64	0.0000
0.0009	1.8761	72	0.0000
0.0008	2.0939	80	0.0000
0.0003	2.3012	88	0.0000

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1