| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9761904761904762, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.804761904761905e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2679, | |
| "eval_samples_per_second": 32.131, | |
| "eval_steps_per_second": 2.142, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9523809523809523, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6095238095238096e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2909, | |
| "eval_samples_per_second": 31.906, | |
| "eval_steps_per_second": 2.127, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.928571428571429, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4142857142857145e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2747, | |
| "eval_samples_per_second": 32.064, | |
| "eval_steps_per_second": 2.138, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.9047619047619047, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2190476190476192e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2807, | |
| "eval_samples_per_second": 32.006, | |
| "eval_steps_per_second": 2.134, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.880952380952381, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0238095238095238e-05, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2895, | |
| "eval_samples_per_second": 31.919, | |
| "eval_steps_per_second": 2.128, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.285714285714287e-06, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2926, | |
| "eval_samples_per_second": 31.89, | |
| "eval_steps_per_second": 2.126, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 6.833333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.3043, | |
| "eval_samples_per_second": 31.777, | |
| "eval_steps_per_second": 2.118, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 7.809523809523809, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3809523809523815e-06, | |
| "loss": 0.0, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2955, | |
| "eval_samples_per_second": 31.862, | |
| "eval_steps_per_second": 2.124, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 8.785714285714286, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.428571428571429e-06, | |
| "loss": 0.0, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.3393, | |
| "eval_samples_per_second": 31.444, | |
| "eval_steps_per_second": 2.096, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 9.761904761904763, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7619047619047623e-07, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.09523809523809523, | |
| "eval_f1": 0.016563146997929608, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2936, | |
| "eval_samples_per_second": 31.88, | |
| "eval_steps_per_second": 2.125, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 420, | |
| "total_flos": 5.130291560557363e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 523.0916, | |
| "train_samples_per_second": 12.656, | |
| "train_steps_per_second": 0.803 | |
| } | |
| ], | |
| "logging_steps": 41, | |
| "max_steps": 420, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 5.130291560557363e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |