See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: fxmarty/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 971b2aaa030e5806_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/971b2aaa030e5806_train_data.json
  type:
    field_input: messages
    field_instruction: text
    field_output: tools
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: true
hub_model_id: lesso18/9d5aa61f-e7c3-42b4-893d-a9a54bfc947d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000218
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/971b2aaa030e5806_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
seed: 180
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: 2e110dec-528c-4b80-8080-a3402beab1b9
wandb_project: 18a
wandb_run: your_name
wandb_runid: 2e110dec-528c-4b80-8080-a3402beab1b9
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

9d5aa61f-e7c3-42b4-893d-a9a54bfc947d

This model is a fine-tuned version of fxmarty/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.8661

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: 0.000218
• train_batch_size: 4
• eval_batch_size: 4
• seed: 180
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	11.9220
11.8932	0.0037	50	11.9170
11.8712	0.0075	100	11.8979
11.8591	0.0112	150	11.8903
11.857	0.0150	200	11.8837
11.8542	0.0187	250	11.8768
11.8423	0.0224	300	11.8711
11.8339	0.0262	350	11.8683
11.8349	0.0299	400	11.8667
11.8316	0.0336	450	11.8662
11.8342	0.0374	500	11.8661

Framework versions

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