| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 15915, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.056573390960693, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.4245, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.744064211845398, | |
| "eval_runtime": 51.3994, | |
| "eval_samples_per_second": 17.393, | |
| "eval_steps_per_second": 1.09, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 16.25078773498535, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 2.0113, | |
| "step": 2122 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7332948446273804, | |
| "eval_runtime": 51.7885, | |
| "eval_samples_per_second": 17.263, | |
| "eval_steps_per_second": 1.081, | |
| "step": 2122 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.307107925415039, | |
| "learning_rate": 4e-05, | |
| "loss": 1.869, | |
| "step": 3183 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.7425885200500488, | |
| "eval_runtime": 51.851, | |
| "eval_samples_per_second": 17.242, | |
| "eval_steps_per_second": 1.08, | |
| "step": 3183 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 5.612180233001709, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 1.7756, | |
| "step": 4244 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.7457906007766724, | |
| "eval_runtime": 51.5711, | |
| "eval_samples_per_second": 17.335, | |
| "eval_steps_per_second": 1.086, | |
| "step": 4244 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 5.046538352966309, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7034, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7198069095611572, | |
| "eval_runtime": 52.1824, | |
| "eval_samples_per_second": 17.132, | |
| "eval_steps_per_second": 1.073, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 4.726966381072998, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6286, | |
| "step": 6366 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.7528493404388428, | |
| "eval_runtime": 52.0378, | |
| "eval_samples_per_second": 17.18, | |
| "eval_steps_per_second": 1.076, | |
| "step": 6366 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 4.87706184387207, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.5654, | |
| "step": 7427 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7497186660766602, | |
| "eval_runtime": 52.0226, | |
| "eval_samples_per_second": 17.185, | |
| "eval_steps_per_second": 1.076, | |
| "step": 7427 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 4.516915798187256, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.5124, | |
| "step": 8488 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.7384775876998901, | |
| "eval_runtime": 52.0172, | |
| "eval_samples_per_second": 17.187, | |
| "eval_steps_per_second": 1.077, | |
| "step": 8488 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 4.607875347137451, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4688, | |
| "step": 9549 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6982604265213013, | |
| "eval_runtime": 51.9662, | |
| "eval_samples_per_second": 17.203, | |
| "eval_steps_per_second": 1.078, | |
| "step": 9549 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.221675395965576, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.4296, | |
| "step": 10610 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.7344964742660522, | |
| "eval_runtime": 51.2487, | |
| "eval_samples_per_second": 17.444, | |
| "eval_steps_per_second": 1.093, | |
| "step": 10610 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 4.773486137390137, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.3963, | |
| "step": 11671 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.7325119972229004, | |
| "eval_runtime": 51.5417, | |
| "eval_samples_per_second": 17.345, | |
| "eval_steps_per_second": 1.086, | |
| "step": 11671 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 4.954598426818848, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3703, | |
| "step": 12732 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.7416211366653442, | |
| "eval_runtime": 51.7473, | |
| "eval_samples_per_second": 17.276, | |
| "eval_steps_per_second": 1.082, | |
| "step": 12732 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 4.158045768737793, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3447, | |
| "step": 13793 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.7334271669387817, | |
| "eval_runtime": 51.5979, | |
| "eval_samples_per_second": 17.326, | |
| "eval_steps_per_second": 1.085, | |
| "step": 13793 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 6.926255226135254, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.3276, | |
| "step": 14854 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.7397375106811523, | |
| "eval_runtime": 51.6734, | |
| "eval_samples_per_second": 17.301, | |
| "eval_steps_per_second": 1.084, | |
| "step": 14854 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15915, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 1.970105106825216e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |