Instructions to use Abhiram4/VitTea with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Abhiram4/VitTea with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Abhiram4/VitTea") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("Abhiram4/VitTea") model = AutoModelForImageClassification.from_pretrained("Abhiram4/VitTea", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from Abhiram4/VitTea: direct link, hf CLI and curl.
- Browser
- Download file 1.41 kB
-
https://huggingface.co/Abhiram4/VitTea/resolve/main/trainer_state.json
- Command line
-
hf download hf://Abhiram4/VitTea/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Abhiram4/VitTea/resolve/main/trainer_state.json
1.41 kB
| { | |
| "best_metric": 0.5056179775280899, | |
| "best_model_checkpoint": "VitTea/checkpoint-6", | |
| "epoch": 2.4, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.24719101123595505, | |
| "eval_loss": 2.0342581272125244, | |
| "eval_runtime": 7.6205, | |
| "eval_samples_per_second": 11.679, | |
| "eval_steps_per_second": 0.262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.48314606741573035, | |
| "eval_loss": 1.937175989151001, | |
| "eval_runtime": 7.7661, | |
| "eval_samples_per_second": 11.46, | |
| "eval_steps_per_second": 0.258, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.5056179775280899, | |
| "eval_loss": 1.9271498918533325, | |
| "eval_runtime": 7.771, | |
| "eval_samples_per_second": 11.453, | |
| "eval_steps_per_second": 0.257, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "step": 6, | |
| "total_flos": 1.1577925830662554e+17, | |
| "train_loss": 2.0264652570088706, | |
| "train_runtime": 486.3273, | |
| "train_samples_per_second": 3.818, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.1577925830662554e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |