See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-13b-128k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 69eaf128756faf6f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/69eaf128756faf6f_train_data.json
  type:
    field_instruction: inputs
    field_output: targets
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 5
eval_max_new_tokens: 128
eval_steps: 500
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 10
gradient_checkpointing: true
group_by_length: true
hub_model_id: surakarteh/323c2fb2-ee9c-4b15-a58d-a935a8dbc898
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000267
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 160
lora_dropout: 0.18
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 80
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 625
micro_batch_size: 5
mlflow_experiment_name: /tmp/69eaf128756faf6f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 12
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
seed: 140
sequence_len: 1280
special_tokens:
  pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 27879a52-b637-4c28-9745-9930e577c1f5
wandb_project: surakarteh
wandb_run: your_name
wandb_runid: 27879a52-b637-4c28-9745-9930e577c1f5
warmup_steps: 125
weight_decay: 0.0
xformers_attention: null

323c2fb2-ee9c-4b15-a58d-a935a8dbc898

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-13b-128k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3594

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: 0.000267
• train_batch_size: 5
• eval_batch_size: 5
• seed: 140
• gradient_accumulation_steps: 10
• total_train_batch_size: 50
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 125
• training_steps: 625

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	1.9872
13.1427	0.1296	500	1.3594

Framework versions

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