| | --- |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: CoM_Small_AIL |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # None |
| |
|
| | This model was trained from scratch on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - eval_loss: 0.0211 |
| | - eval_runtime: 11.1994 |
| | - eval_samples_per_second: 596.995 |
| | - eval_steps_per_second: 9.375 |
| | - step: 0 |
| |
|
| | ## Model description |
| |
|
| | The model is a fine-tuned version of BERT for text classification on a specific dataset. It takes a text sequence as input and outputs a probability distribution over the possible classes. |
| |
|
| | ## Intended uses & limitations |
| |
|
| | The model is intended to be used for text classification tasks similar to the one it was fine-tuned on. It may not perform well on datasets with significantly different characteristics. Additionally, the model may not be suitable for tasks requiring real-time inference due to its relatively large size and computational requirements. |
| |
|
| | ## Training and evaluation data |
| |
|
| | Data From : Nielzac/CoM_Audio_Image_LLM_Generation |
| |
|
| | ## Training procedure |
| |
|
| | ### Training hyperparameters |
| |
|
| | The following hyperparameters were used during training: |
| | - learning_rate: 5e-05 |
| | - train_batch_size: 34 |
| | - eval_batch_size: 64 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 500 |
| | - num_epochs: 1 |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.38.2 |
| | - Pytorch 2.2.1+cu121 |
| | - Datasets 2.18.0 |
| | - Tokenizers 0.15.2 |
| | |
| | |
| | ```code python |
| | from transformers import BertForSequenceClassification, TrainingArguments, Trainer, AutoTokenizer, DataCollatorWithPadding |
| | model_id = "bert-base-uncased" |
| | model = BertForSequenceClassification.from_pretrained(model_id, num_labels=3) |
| | tokenizer = AutoTokenizer.from_pretrained(model_id) |
| | |
| | def tokenize(batch): |
| | return tokenizer(batch["text"], truncation=True, padding="max_length", max_length=max_source_length, add_special_tokens=True, return_tensors='pt') |
| | ``` |
