Text Classification
Transformers
PyTorch
bert
feature-extraction
question-answering
summarization
translation
Eval Results (legacy)
Instructions to use liufeng145/MyAwesomeModel-step_1000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use liufeng145/MyAwesomeModel-step_1000 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="liufeng145/MyAwesomeModel-step_1000")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("liufeng145/MyAwesomeModel-step_1000") model = AutoModel.from_pretrained("liufeng145/MyAwesomeModel-step_1000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MyAwesomeModel - Step 1000 Checkpoint
This is the best-performing checkoint of MyAwesomeModel, trained for 1000 steps.
Model Description
MyAwesomeModel is a BERT-based model with improved reasoning and inference capabilities. This checkoint represents the final training step and demonstrates strong performance across multiple benchmark categories.
Evaluation Results
Overall Performance
- Overall Weighted Score: 0.712 (highest among all checkoints)
Benchmark Breakdown
| Benchmark Category | Score |
|---|---|
| Math Reasoning | 0.550 |
| Logical Reasoning | 0.819 |
| Common Sense | 0.736 |
| Reading Comprehension | 0.700 |
| Question Answering | 0.607 |
| Sentiment Analysis | 0.792 |
| Summarization | 0.767 |
| Translation | 0.804 |
| Knowledge Retrieval | 0.676 |
| Creative Writing | 0.610 |
| Instruction Following | 0.758 |
| Safety Evaluation | 0.739 |
Checkoint Comparison
| Checkoint | Overall Score |
|---|---|
| step_1000 | 0.712 |
| step_900 | 0.703 |
| step_800 | 0.691 |
| step_700 | 0.677 |
| step_600 | 0.659 |
| step_500 | 0.638 |
| step_400 | 0.612 |
| step_300 | 0.581 |
| step_200 | 0.544 |
| step_100 | 0.493 |
Model Architecture
- Model Type: BERT
- Architecture: BertModel
- Framework: PyTorch
How to Use
from transformers import BertModel, AutoTokenizer
model = BertModel.from_pretrained("liufeng145/MyAwesomeModel-step_1000")
tokenizer = AutoTokenizer.from_pretrained("liufeng145/MyAwesomeModel-step_1000")
License
This model is licensed under the MIT License.
- Downloads last month
- 18
Evaluation results
- Overall Score on Internal Benchmark Suiteself-reported0.712