See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-14B-Instruct
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2faaa280684be4c0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2faaa280684be4c0_train_data.json
  type:
    field_input: song
    field_instruction: artist
    field_output: text
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 2
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/7b47b128-d1e3-40c4-93dd-fcfece88c160
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 3000
micro_batch_size: 4
mlflow_experiment_name: /tmp/2faaa280684be4c0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 150
saves_per_epoch: null
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: 35de617b-f853-4dd3-bd2a-8c2a53791a53
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 35de617b-f853-4dd3-bd2a-8c2a53791a53
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

7b47b128-d1e3-40c4-93dd-fcfece88c160

This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8755

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: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	2.2741
1.9671	0.0440	150	1.9967
1.9987	0.0879	300	1.9891
1.9462	0.1319	450	1.9864
1.9484	0.1759	600	1.9794
1.9302	0.2199	750	1.9671
1.9155	0.2638	900	1.9604
1.9415	0.3078	1050	1.9499
1.9503	0.3518	1200	1.9351
1.9144	0.3957	1350	1.9282
1.9094	0.4397	1500	1.9173
1.8951	0.4837	1650	1.9070
1.9383	0.5277	1800	1.9004
1.8939	0.5716	1950	1.8924
1.8584	0.6156	2100	1.8878
1.9155	0.6596	2250	1.8829
1.8812	0.7036	2400	1.8793
1.8444	0.7475	2550	1.8771
1.8464	0.7915	2700	1.8758
1.8568	0.8355	2850	1.8753
1.8577	0.8794	3000	1.8755

Framework versions

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