Download trainer_state.json from hannah-khallaf/Readme-Rbinary-mBERT-bert-base-multilingual-cased_fold_0: direct link, hf CLI and curl.
- Browser
- Download file 2.14 kB
-
https://huggingface.co/hannah-khallaf/Readme-Rbinary-mBERT-bert-base-multilingual-cased_fold_0/resolve/main/trainer_state.json
- Command line
-
hf download hf://hannah-khallaf/Readme-Rbinary-mBERT-bert-base-multilingual-cased_fold_0/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/hannah-khallaf/Readme-Rbinary-mBERT-bert-base-multilingual-cased_fold_0/resolve/main/trainer_state.json
2.14 kB
| { | |
| "best_global_step": 1244, | |
| "best_metric": 0.8507081171349183, | |
| "best_model_checkpoint": "./results-PR/bert-base-multilingual-cased_fold_0/checkpoint-1244", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1244, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8038585209003215, | |
| "grad_norm": 7.114378929138184, | |
| "learning_rate": 2.0056270096463023e-05, | |
| "loss": 0.5627, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6967015285599356, | |
| "eval_f1": 0.7010085418034284, | |
| "eval_loss": 0.598173975944519, | |
| "eval_precision": 0.8246874487091888, | |
| "eval_recall": 0.6967015285599356, | |
| "eval_runtime": 5.247, | |
| "eval_samples_per_second": 236.898, | |
| "eval_steps_per_second": 29.731, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.607717041800643, | |
| "grad_norm": 5.695389747619629, | |
| "learning_rate": 4.0152733118971066e-05, | |
| "loss": 0.5187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8487530168946098, | |
| "eval_f1": 0.8507081171349183, | |
| "eval_loss": 0.5054676532745361, | |
| "eval_precision": 0.8555064529752252, | |
| "eval_recall": 0.8487530168946098, | |
| "eval_runtime": 5.797, | |
| "eval_samples_per_second": 214.42, | |
| "eval_steps_per_second": 26.91, | |
| "step": 1244 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2615323890278400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |