Text Classification
Transformers
Safetensors
English
roberta
ag-news
salient-keywords
experiment
text-embeddings-inference
Instructions to use martian786/agnews-salient-random-k16-seed-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use martian786/agnews-salient-random-k16-seed-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="martian786/agnews-salient-random-k16-seed-1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("martian786/agnews-salient-random-k16-seed-1") model = AutoModelForSequenceClassification.from_pretrained("martian786/agnews-salient-random-k16-seed-1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "run_name": "random_k16", | |
| "variant": "random", | |
| "hf_repo_id": "martian786/agnews-salient-random-k16-seed-1", | |
| "fraction": 0.25, | |
| "train_examples": 28500, | |
| "val_examples": 6000, | |
| "test_examples": 7600, | |
| "val_eval_loss": 0.38659048080444336, | |
| "val_eval_accuracy": 0.8825, | |
| "val_eval_macro_f1": 0.8822514612482859, | |
| "test_accuracy": 0.8698684210526316, | |
| "test_precision_macro": 0.8697436317086674, | |
| "test_recall_macro": 0.8698684210526315, | |
| "test_f1_macro": 0.8696299974829994, | |
| "accuracy_ci_lower": 0.862116882759214, | |
| "accuracy_ci_upper": 0.8772462307490949, | |
| "num_misclassified": 989, | |
| "accuracy_per_1k_train_examples": 0.030521698984302865, | |
| "representation_preprocess_time_s": 3.5573337269997864, | |
| "tokenization_time_s": 5.769618768000328, | |
| "classifier_train_time_s": 655.2569652520006, | |
| "batched_predict_total_s": 15.153196565999679, | |
| "inference_latency_mean_ms": 8.140939455010994, | |
| "inference_latency_median_ms": 7.902555000327993, | |
| "inference_latency_p95_ms": 9.573150999995047, | |
| "inference_throughput_sps": 122.83594608782772, | |
| "batched_predict_latency_mean_ms": 1.9938416534210106, | |
| "trainer_reported_train_runtime_s": 654.6613, | |
| "learning_curve_outputs": { | |
| "trainer_log_history_csv": "agnews_salient_runs_second_seed_1/random_k16/trainer_log_history.csv", | |
| "loss_curve_png": "agnews_salient_runs_second_seed_1/random_k16/loss_curve.png", | |
| "validation_accuracy_curve_png": "agnews_salient_runs_second_seed_1/random_k16/validation_accuracy_curve.png", | |
| "validation_macro_f1_curve_png": "agnews_salient_runs_second_seed_1/random_k16/validation_macro_f1_curve.png" | |
| }, | |
| "test_plot_outputs": { | |
| "test_macro_metrics_bar_png": "agnews_salient_runs_second_seed_1/random_k16/test_macro_metrics_bar.png", | |
| "test_per_class_f1_bar_png": "agnews_salient_runs_second_seed_1/random_k16/test_per_class_f1_bar.png", | |
| "test_confusion_matrix_png": "agnews_salient_runs_second_seed_1/random_k16/test_confusion_matrix.png" | |
| } | |
| } |