base_model: Qwen/Qwen2.5-3B-Instruct
load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: VinitT/Cricket-Commentary-Sample
    type: alpaca
dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir: 

sequence_len: 1024
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

hub_model_id: Commentary-qwen-3B

wandb_project: Cricket-Commentary-1
wandb_entity: 
wandb_watch: all
wandb_name: Cricket-Commentary-1
wandb_log_model: 

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.2
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: false
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false

#gpu_memory_limit: 20GiB
#lora_on_cpu: true         

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.0
special_tokens:
   pad_token: <|end_of_text|>

Commentary-qwen-3B

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the VinitT/Cricket-Commentary-Sample dataset.

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use 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
num_epochs: 1.0

Training results

Framework versions

PEFT 0.14.0
Transformers 4.49.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

VinitT/Commentary-qwen-3B

Commentary-qwen-3B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

VinitT/
Commentary-qwen-3B