See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/zephyr-sft
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cf2fde8cf8e94dcd_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cf2fde8cf8e94dcd_train_data.json
  type:
    field_input: distraction
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
eval_batch_size: 4
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: null
# load_best_model_at_end: true
early_stopping_patience: 2
save_steps: 100
eval_steps: 100
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: baby-dev/test-default-06-01
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00025
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 1000
micro_batch_size: 4
mlflow_experiment_name: /tmp/cf2fde8cf8e94dcd_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_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: null
sequence_len: 512
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: 3a663e10-c37c-4bb9-a725-a32f441f1634
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: 3a663e10-c37c-4bb9-a725-a32f441f1634
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

test-default-06-01

This model is a fine-tuned version of unsloth/zephyr-sft on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4388

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: 0.00025
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB 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: constant
• lr_scheduler_warmup_steps: 50
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	3.0643
8.9435	0.0137	100	2.4706
8.9737	0.0273	200	2.4184
8.804	0.0410	300	2.3906
8.7399	0.0546	400	2.4476
8.8788	0.0683	500	2.3084
9.0255	0.0819	600	2.3585
9.2502	0.0956	700	2.4388

Framework versions

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