See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: codellama/CodeLlama-7b-hf
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 7cce8ab125db1226_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7cce8ab125db1226_train_data.json
  type:
    field_instruction: text
    field_output: answers
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso01/f5336dce-868b-4be2-b698-933b994f5f71
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 80GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/7cce8ab125db1226_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
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: null
wandb_mode: online
wandb_name: f5336dce-868b-4be2-b698-933b994f5f71
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f5336dce-868b-4be2-b698-933b994f5f71
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

f5336dce-868b-4be2-b698-933b994f5f71

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: nan

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0054	1	nan
0.0	0.0488	9	nan
0.0	0.0976	18	nan
0.0	0.1463	27	nan
0.0	0.1951	36	nan
0.0	0.2439	45	nan
0.0	0.2927	54	nan
0.0	0.3415	63	nan
0.0	0.3902	72	nan
0.0	0.4390	81	nan
0.0	0.4878	90	nan
0.0	0.5366	99	nan

Framework versions

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