See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-dummy-qwen2
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 2ee322a09b47afa9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2ee322a09b47afa9_train_data.json
  type:
    field_instruction: instruction
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: bbytxt/a2ae530a-991c-4435-97a5-372f28eb8126
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
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_memory:
  0: 70GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/2ee322a09b47afa9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
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
sequence_len: 1028
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: a2ae530a-991c-4435-97a5-372f28eb8126
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a2ae530a-991c-4435-97a5-372f28eb8126
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

a2ae530a-991c-4435-97a5-372f28eb8126

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: 11.9209

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
11.9336	0.0047	1	11.9337
11.9333	0.1168	25	11.9327
11.932	0.2336	50	11.9274
11.9249	0.3505	75	11.9222
11.9257	0.4673	100	11.9213
11.9222	0.5841	125	11.9212
11.9209	0.7009	150	11.9205
11.9215	0.8178	175	11.9202
11.9231	0.9346	200	11.9209

Framework versions

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