| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028180921516133578, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005636184303226716, | |
| "eval_loss": 11.894136428833008, | |
| "eval_runtime": 47.443, | |
| "eval_samples_per_second": 15.745, | |
| "eval_steps_per_second": 7.883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028180921516133576, | |
| "grad_norm": 22.021039962768555, | |
| "learning_rate": 5e-05, | |
| "loss": 12.5352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005636184303226715, | |
| "grad_norm": 19.067848205566406, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8637, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005636184303226715, | |
| "eval_loss": 5.757726192474365, | |
| "eval_runtime": 47.5479, | |
| "eval_samples_per_second": 15.71, | |
| "eval_steps_per_second": 7.866, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008454276454840074, | |
| "grad_norm": 24.24180793762207, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2601, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01127236860645343, | |
| "grad_norm": 9.227785110473633, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3134, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01127236860645343, | |
| "eval_loss": 1.3870593309402466, | |
| "eval_runtime": 47.6111, | |
| "eval_samples_per_second": 15.69, | |
| "eval_steps_per_second": 7.855, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014090460758066789, | |
| "grad_norm": 26.356706619262695, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3428, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016908552909680147, | |
| "grad_norm": 13.62512493133545, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5582, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016908552909680147, | |
| "eval_loss": 0.9215185642242432, | |
| "eval_runtime": 47.6285, | |
| "eval_samples_per_second": 15.684, | |
| "eval_steps_per_second": 7.852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019726645061293506, | |
| "grad_norm": 5.192386627197266, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.623, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02254473721290686, | |
| "grad_norm": 6.412773609161377, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4103, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02254473721290686, | |
| "eval_loss": 0.7003613114356995, | |
| "eval_runtime": 47.7974, | |
| "eval_samples_per_second": 15.628, | |
| "eval_steps_per_second": 7.825, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02536282936452022, | |
| "grad_norm": 4.594435691833496, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3075, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028180921516133578, | |
| "grad_norm": 5.985153675079346, | |
| "learning_rate": 0.0, | |
| "loss": 0.2875, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028180921516133578, | |
| "eval_loss": 0.6660094857215881, | |
| "eval_runtime": 47.9977, | |
| "eval_samples_per_second": 15.563, | |
| "eval_steps_per_second": 7.792, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3700720247242752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |