See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/llama-3-8b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 531c5d561743d5fd_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/531c5d561743d5fd_train_data.json
  type:
    field_input: dataset
    field_instruction: model_input
    field_output: primary_tag
    format: '{instruction} {input}'
    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: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 0.5
group_by_length: false
hub_model_id: leixa/d221bcbc-7f80-4318-88af-aef86bd8fc56
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.00005
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 1
mlflow_experiment_name: /tmp/531c5d561743d5fd_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: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: d221bcbc-7f80-4318-88af-aef86bd8fc56
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d221bcbc-7f80-4318-88af-aef86bd8fc56
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

d221bcbc-7f80-4318-88af-aef86bd8fc56

This model is a fine-tuned version of unsloth/llama-3-8b 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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0051	1	nan
0.0	0.0256	5	nan
0.0	0.0512	10	nan
0.0	0.0767	15	nan
0.0	0.1023	20	nan
0.0	0.1279	25	nan
0.0	0.1535	30	nan
0.0	0.1790	35	nan
0.0	0.2046	40	nan
0.0	0.2302	45	nan
0.0	0.2558	50	nan

Framework versions

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