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
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')
- Downloads last month
- 2