See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: peft-internal-testing/tiny-dummy-qwen2
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 025a531564778051_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/025a531564778051_train_data.json
  type:
    field_input: article
    field_instruction: title
    field_output: summary
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 5
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/4850948a-242d-4247-ae08-bb9e94455433
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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: true
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_steps: 2073
micro_batch_size: 4
mlflow_experiment_name: /tmp/025a531564778051_train_data.json
model_type: AutoModelForCausalLM
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: 100
sequence_len: 1024
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: a4d4ccf6-0bb8-4170-ae19-2a650c5d1201
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a4d4ccf6-0bb8-4170-ae19-2a650c5d1201
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

4850948a-242d-4247-ae08-bb9e94455433

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: 11.9140

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• 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: 10
• training_steps: 588

Training results

Training Loss	Epoch	Step	Validation Loss
11.9313	0.0017	1	11.9307
11.9273	0.0851	50	11.9263
11.9212	0.1702	100	11.9201
11.9177	0.2553	150	11.9176
11.9175	0.3405	200	11.9163
11.9175	0.4256	250	11.9154
11.9151	0.5107	300	11.9148
11.9146	0.5958	350	11.9145
11.915	0.6809	400	11.9142
11.9131	0.7660	450	11.9141
11.9143	0.8512	500	11.9140
11.9143	0.9363	550	11.9140

Framework versions

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