adapter: qlora
base_model: Qwen/Qwen1.5-7B
bf16: true
chat_template: llama3
dataloader_num_workers: 6
dataset_prepared_path: null
datasets:
- data_files:
  - 8b6d8b452d565bc9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8b6d8b452d565bc9_train_data.json
  type:
    field_instruction: context
    field_output: utterance
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping:
  metric: eval_loss
  mode: min
  patience: 3
eval_max_new_tokens: 128
eval_steps: 50
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: error577/f19104f9-3bbb-4c28-bc68-79e78aebec79
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: true  
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.1  
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_steps: 100
micro_batch_size: 1
mlflow_experiment_name: /tmp/8b6d8b452d565bc9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: paged_adamw_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: 8e4427c2-93b3-4538-9764-87f93b792e71
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 8e4427c2-93b3-4538-9764-87f93b792e71
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

f19104f9-3bbb-4c28-bc68-79e78aebec79

This model is a fine-tuned version of Qwen/Qwen1.5-7B on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.7084

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
2.6534	0.0000	1	3.5774
3.3615	0.0018	50	2.9334
3.0055	0.0035	100	2.7084

Framework versions

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