Instructions to use nijji/lr_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nijji/lr_3 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nijji/lr_3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from nijji/lr_3: direct link, hf CLI and curl.
- Browser
- Download file 4.32 kB
-
https://huggingface.co/nijji/lr_3/resolve/main/trainer_state.json
- Command line
-
hf download hf://nijji/lr_3/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/nijji/lr_3/resolve/main/trainer_state.json
4.32 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 225, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 2.429300546646118, | |
| "learning_rate": 0.001, | |
| "loss": 1.0583, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 2.37762451171875, | |
| "learning_rate": 0.001, | |
| "loss": 1.0795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.886047601699829, | |
| "learning_rate": 0.001, | |
| "loss": 1.0465, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.9647541642189026, | |
| "learning_rate": 0.001, | |
| "loss": 1.0078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 4.47161865234375, | |
| "learning_rate": 0.001, | |
| "loss": 1.0215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.3636322021484375, | |
| "learning_rate": 0.001, | |
| "loss": 0.9128, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 1.1846381425857544, | |
| "learning_rate": 0.001, | |
| "loss": 0.9122, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 5.121966361999512, | |
| "learning_rate": 0.001, | |
| "loss": 0.729, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.8247140645980835, | |
| "learning_rate": 0.001, | |
| "loss": 0.5656, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.7469320297241211, | |
| "learning_rate": 0.001, | |
| "loss": 0.913, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": 3.267280101776123, | |
| "learning_rate": 0.001, | |
| "loss": 0.4554, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.3719987869262695, | |
| "learning_rate": 0.001, | |
| "loss": 0.6588, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": 5.573326110839844, | |
| "learning_rate": 0.001, | |
| "loss": 0.3037, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.9611998796463013, | |
| "learning_rate": 0.001, | |
| "loss": 0.8231, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.474925994873047, | |
| "learning_rate": 0.001, | |
| "loss": 0.5229, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 23.831850051879883, | |
| "learning_rate": 0.001, | |
| "loss": 0.7581, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.2666666666666666, | |
| "grad_norm": 1.9515756368637085, | |
| "learning_rate": 0.001, | |
| "loss": 0.4908, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 4.731529712677002, | |
| "learning_rate": 0.001, | |
| "loss": 0.4331, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.533333333333333, | |
| "grad_norm": 1.9901970624923706, | |
| "learning_rate": 0.001, | |
| "loss": 0.5386, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.9275996685028076, | |
| "learning_rate": 0.001, | |
| "loss": 0.3859, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.4204686880111694, | |
| "learning_rate": 0.001, | |
| "loss": 0.4254, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 1.0124672651290894, | |
| "learning_rate": 0.001, | |
| "loss": 0.3515, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 225, | |
| "total_flos": 1.05836359974912e+16, | |
| "train_loss": 0.696545786327786, | |
| "train_runtime": 520.0969, | |
| "train_samples_per_second": 0.433, | |
| "train_steps_per_second": 0.433 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 225, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.05836359974912e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |