Text Classification
Transformers
PyTorch
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Instructions to use HealthNLP/pubmedbert_tlink with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HealthNLP/pubmedbert_tlink with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="HealthNLP/pubmedbert_tlink")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("HealthNLP/pubmedbert_tlink") model = AutoModelForSequenceClassification.from_pretrained("HealthNLP/pubmedbert_tlink", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from HealthNLP/pubmedbert_tlink: direct link, hf CLI and curl.
- Browser
- Download file 841 Bytes
-
https://huggingface.co/HealthNLP/pubmedbert_tlink/resolve/main/trainer_state.json
- Command line
-
hf download hf://HealthNLP/pubmedbert_tlink/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/HealthNLP/pubmedbert_tlink/resolve/main/trainer_state.json
841 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 1140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 1.6842105263157893e-05, | |
| "loss": 0.1909, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 3.6842105263157892e-06, | |
| "loss": 0.0196, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1140, | |
| "total_flos": 931250075040000.0, | |
| "train_loss": 0.09304492578171847, | |
| "train_runtime": 41.8899, | |
| "train_samples_per_second": 432.562, | |
| "train_steps_per_second": 27.214 | |
| } | |
| ], | |
| "max_steps": 1140, | |
| "num_train_epochs": 10, | |
| "total_flos": 931250075040000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |