| { | |
| "best_metric": 0.8076923076923077, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-uit74zky/checkpoint-50", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.8091522455215454, | |
| "learning_rate": 5.364935037637319e-05, | |
| "loss": 0.5441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 4.8837361335754395, | |
| "learning_rate": 4.023701278227989e-05, | |
| "loss": 0.4031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.855, | |
| "eval_f1": 0.7867647058823529, | |
| "eval_loss": 0.3269094228744507, | |
| "eval_precision": 0.7181208053691275, | |
| "eval_recall": 0.8699186991869918, | |
| "eval_runtime": 1.5265, | |
| "eval_samples_per_second": 262.042, | |
| "eval_steps_per_second": 16.378, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.886763572692871, | |
| "learning_rate": 2.6824675188186596e-05, | |
| "loss": 0.319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.65802526473999, | |
| "learning_rate": 1.3412337594093298e-05, | |
| "loss": 0.2827, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.284539222717285, | |
| "learning_rate": 0.0, | |
| "loss": 0.257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.875, | |
| "eval_f1": 0.8076923076923077, | |
| "eval_loss": 0.3172125518321991, | |
| "eval_precision": 0.7664233576642335, | |
| "eval_recall": 0.8536585365853658, | |
| "eval_runtime": 1.5651, | |
| "eval_samples_per_second": 255.58, | |
| "eval_steps_per_second": 15.974, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 423630740901888.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 6.706168797046648e-05, | |
| "metric": "eval/loss", | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 64, | |
| "seed": 40 | |
| } | |
| } | |