Instructions to use YeRyeongLee/test3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YeRyeongLee/test3 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="YeRyeongLee/test3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("YeRyeongLee/test3") model = AutoModelForQuestionAnswering.from_pretrained("YeRyeongLee/test3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from YeRyeongLee/test3: direct link, hf CLI and curl.
- Browser
- Download file 1.19 kB
-
https://huggingface.co/YeRyeongLee/test3/resolve/main/trainer_state.json
- Command line
-
hf download hf://YeRyeongLee/test3/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/YeRyeongLee/test3/resolve/main/trainer_state.json
1.19 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 2994, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1649966599866405e-05, | |
| "loss": 1.6003, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.32999331997328e-05, | |
| "loss": 1.0598, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.49498997995992e-05, | |
| "loss": 0.3999, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.65998663994656e-05, | |
| "loss": 0.3829, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.249832999331998e-06, | |
| "loss": 0.131, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2994, | |
| "total_flos": 4688778409821792.0, | |
| "train_loss": 0.616782742018053, | |
| "train_runtime": 696.2812, | |
| "train_samples_per_second": 34.374, | |
| "train_steps_per_second": 4.3 | |
| } | |
| ], | |
| "max_steps": 2994, | |
| "num_train_epochs": 3, | |
| "total_flos": 4688778409821792.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |