wandb:               eval/loss █▂▂▁▁▁▁▁▁▁
wandb:            eval/runtime █▆▁▆▃▆▇▄▅▅
wandb: eval/samples_per_second ▁▃█▃▆▃▂▄▄▄
wandb:   eval/steps_per_second ▁▃█▃▆▃▂▅▄▄
wandb:             train/epoch ▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇▇██
wandb:       train/global_step ▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇▇██
wandb:         train/grad_norm █▆▅▅▅▂▁▁▁▁▁▁▁▁▂▁▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:     train/learning_rate ▁▂▃▄▄▅▆▇▇██▇▇▇▆▆▆▅▅▅▅▄▄▄▃▃▃▂▂▂▁▁
wandb:              train/loss █▇▆▅▄▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb: 
wandb: Run summary:
wandb:                eval/loss 0.50256
wandb:             eval/runtime 29.4524
wandb:  eval/samples_per_second 11.408
wandb:    eval/steps_per_second 5.704
wandb:               total_flos 9.346402366921114e+16
wandb:              train/epoch 7.97568
wandb:        train/global_step 328
wandb:          train/grad_norm 0.24235
wandb:      train/learning_rate 0.0
wandb:               train/loss 0.5278
wandb:               train_loss 0.8828
wandb:            train_runtime 3380.2353
wandb: train_samples_per_second 6.229
wandb:   train_steps_per_second 0.097


Llama-3.2-3B-ocr-correction-3-instruction-corrected-real-data-full-params-real-data-eval.json
Average PCIS: -0.00377946
Average Dataset CER: 0.01391665
Average Model CER: 0.01754558
Average Dataset WER: 0.06207812
Average Model WER: 0.08189486

Llama-3.2-3B-ocr-correction-3-instruction-corrected-real-data-full-params-synth-data-eval.json
Average PCIS: -0.09734535
Average Dataset CER: 0.09836092
Average Model CER: 0.19219267
Average Dataset WER: 0.21986217
Average Model WER: 1.01884786



training_arguments = SFTConfig(
    output_dir=new_model,
    run_name="fine_tune_ocr_correction",
    per_device_train_batch_size=4, # max 4 batches
    per_device_eval_batch_size=2,
    gradient_accumulation_steps=16, # the bigger the better for GPUs
    optim="paged_adamw_32bit",
    num_train_epochs=8, 
    eval_strategy="steps",
    eval_steps=30,  
    save_steps=30,
    logging_steps=10,  
    warmup_steps=100,
    logging_strategy="steps",
    learning_rate= 5e-5, # 5e-5 = 0.00005 ; 2e-4 = 0.0002, 
    fp16=use_fp16, 
    bf16=use_bf16,  
    group_by_length=True,
    report_to="wandb",
    max_seq_length=1220,
    save_strategy="steps",
    dataset_text_field="text",
    max_grad_norm=1.0,
    warmup_ratio=0.05,
    load_best_model_at_end = True
)

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

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]