See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: true
chat_template: llama3
datasets:
- data_files:
  - a1cfdc0440fffdd7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a1cfdc0440fffdd7_train_data.json
  type:
    field_input: text
    field_instruction: query
    field_output: answer
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso02/1560f82d-2991-4c9a-825e-c2509dfc6265
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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_memory:
  0: 77GiB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/a1cfdc0440fffdd7_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: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 1560f82d-2991-4c9a-825e-c2509dfc6265
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1560f82d-2991-4c9a-825e-c2509dfc6265
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

1560f82d-2991-4c9a-825e-c2509dfc6265

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

• Loss: 11.9186

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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
11.9238	0.0024	1	11.9229
11.9239	0.0121	5	11.9228
11.9215	0.0242	10	11.9222
11.9211	0.0362	15	11.9215
11.9207	0.0483	20	11.9208
11.9201	0.0604	25	11.9201
11.9198	0.0725	30	11.9195
11.9178	0.0845	35	11.9190
11.9181	0.0966	40	11.9187
11.9185	0.1087	45	11.9186
11.9185	0.1208	50	11.9186

Framework versions

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