dolo650/flan-t5-base-qlora-peft

Model Card for Model ID

This is a flan-t5-base model finetuned using QLoRA (PEFT) on dialogSum dataset : https://huggingface.co/datasets/knkarthick/dialogsum

Model Details

Training Details:

This is just a basic fine tuned model using below training args and params

lora_config = LoraConfig( r=16, lora_alpha=32, target_modules=['q','k','v','o'], lora_dropout=.05, bias='none', task_type=TaskType.SEQ_2_SEQ_LM #flan-t5 )

output_dir = f'/kaggle/working/qlora-peft-flant5-base-dialogue-summary-training-{str(int(time.time()))}'

peft_training_args_4bit = TrainingArguments( output_dir=output_dir, auto_find_batch_size=True, learning_rate=1e-3, # Higher learning rate than full fine-tuning. num_train_epochs=200, logging_steps=10, max_steps=200
)

peft_trainer_4bit = Trainer( model=peft_model_4bit, args=peft_training_args_4bit, train_dataset=tokenized_dataset_cleaned["train"], eval_dataset=tokenized_dataset_cleaned['validation'] )

Recorded training loss as below:

Step Training Loss 10 29.131100 20 4.856900 30 3.241400 40 1.346500 50 0.560900 60 0.344000 70 0.258600 80 0.201600 90 0.202900 100 0.198700 110 0.185000 120 0.177200 130 0.161400 140 0.164200 150 0.164300 160 0.165800 170 0.168700 180 0.155100 190 0.161200 200 0.170300

Rouge1 score for 100 test dataset(out of 1500) is : ORIGINAL MODEL: {'rouge1': 0.2232663790087573, 'rouge2': 0.06084131871447254, 'rougeL': 0.1936115999187245, 'rougeLsum': 0.19319411133637282} PEFT MODEL: {'rouge1': 0.34502805897556865, 'rouge2': 0.11517693222074701, 'rougeL': 0.2800665095598698, 'rougeLsum': 0.27941257109947587}

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.7.1