See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-1.5B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 4b5ce55c2fd4f9e6_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/4b5ce55c2fd4f9e6_train_data.json
  type:
    field_input: lyrics
    field_instruction: track_name
    field_output: sentiment
    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: 5
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: false
group_by_length: false
hub_model_id: tuanna08go/6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
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: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/4b5ce55c2fd4f9e6_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
saves_per_epoch: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
warmup_steps: 2
weight_decay: 0.0
xformers_attention: null

6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3794

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: 16
• total_train_batch_size: 128
• 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: 2
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0091	1	13.9445
12.18	0.0911	10	8.5189
5.7398	0.1822	20	2.1543
1.0209	0.2733	30	0.4289
0.4525	0.3645	40	0.3867
0.3723	0.4556	50	0.3794

Framework versions

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