Image Classification
Transformers
Safetensors
English
metaclip_2
text-generation-inference
open-scene
Instructions to use prithivMLmods/MetaCLIP-2-Open-Scene with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/MetaCLIP-2-Open-Scene with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="prithivMLmods/MetaCLIP-2-Open-Scene") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("prithivMLmods/MetaCLIP-2-Open-Scene") model = AutoModelForImageClassification.from_pretrained("prithivMLmods/MetaCLIP-2-Open-Scene") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 1022, | |
| "best_metric": 0.12706944346427917, | |
| "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-1022", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1022, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9784735812133072, | |
| "grad_norm": 13.377490043640137, | |
| "learning_rate": 1.5496489468405215e-05, | |
| "loss": 0.3912, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.933435301315387, | |
| "eval_loss": 0.18303145468235016, | |
| "eval_model_preparation_time": 0.013, | |
| "eval_runtime": 81.9678, | |
| "eval_samples_per_second": 199.408, | |
| "eval_steps_per_second": 24.937, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.9569471624266144, | |
| "grad_norm": 30.63884925842285, | |
| "learning_rate": 1.0481444332998999e-05, | |
| "loss": 0.1978, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9562557356989905, | |
| "eval_loss": 0.12706944346427917, | |
| "eval_model_preparation_time": 0.013, | |
| "eval_runtime": 78.5588, | |
| "eval_samples_per_second": 208.061, | |
| "eval_steps_per_second": 26.019, | |
| "step": 1022 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2044, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.375153034156032e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |