| { | |
| "best_metric": 1.671216607093811, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-400", | |
| "epoch": 0.9456264775413712, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2364066193853428, | |
| "grad_norm": 28.178190231323242, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 11.143, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2364066193853428, | |
| "eval_loss": 7.659108638763428, | |
| "eval_runtime": 0.809, | |
| "eval_samples_per_second": 260.829, | |
| "eval_steps_per_second": 65.516, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "grad_norm": 15.27036190032959, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 4.1737, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "eval_loss": 2.2642054557800293, | |
| "eval_runtime": 0.8681, | |
| "eval_samples_per_second": 243.069, | |
| "eval_steps_per_second": 61.055, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 13.071714401245117, | |
| "learning_rate": 5e-06, | |
| "loss": 2.0579, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "eval_loss": 1.7709782123565674, | |
| "eval_runtime": 0.8603, | |
| "eval_samples_per_second": 245.25, | |
| "eval_steps_per_second": 61.603, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "grad_norm": 8.75770092010498, | |
| "learning_rate": 4.8727735368956745e-06, | |
| "loss": 1.6963, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "eval_loss": 1.671216607093811, | |
| "eval_runtime": 0.9312, | |
| "eval_samples_per_second": 226.587, | |
| "eval_steps_per_second": 56.915, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 52695659520000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |