See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/tinyllama-chat
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b7e4e421f9e9ca2d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b7e4e421f9e9ca2d_train_data.json
  type:
    field_instruction: prompt
    field_output: chosen
    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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: surakarteh/758a6077-53fa-4bec-98bf-9f78af1b5e42
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 8.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.025
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 40
micro_batch_size: 8
mlflow_experiment_name: /tmp/b7e4e421f9e9ca2d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
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: 4
sequence_len: 512
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: cc79e130-1503-453f-a157-5a21f41c431d
wandb_project: Gradients-On-Demand
wandb_run: surakarteh
wandb_runid: cc79e130-1503-453f-a157-5a21f41c431d
warmup_steps: 40
weight_decay: 0.03
xformers_attention: null

758a6077-53fa-4bec-98bf-9f78af1b5e42

This model is a fine-tuned version of unsloth/tinyllama-chat 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: 8e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 40
• training_steps: 40

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0022	1	nan
0.0	0.0066	3	nan
0.0	0.0133	6	nan
0.0	0.0199	9	nan
0.0	0.0265	12	nan
0.0	0.0331	15	nan
0.0	0.0398	18	nan
0.0	0.0464	21	nan
0.0	0.0530	24	nan
0.0	0.0597	27	nan
0.0	0.0663	30	nan
0.0	0.0729	33	nan
0.0	0.0796	36	nan
0.0	0.0862	39	nan

Framework versions

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