| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006351222610352493, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "grad_norm": 1.8517828721087426e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 4.0154, | |
| "eval_samples_per_second": 165.116, | |
| "eval_steps_per_second": 82.683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012702445220704986, | |
| "grad_norm": 1.7152289728983305e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "grad_norm": 1.2810402949980926e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.9727, | |
| "eval_samples_per_second": 166.888, | |
| "eval_steps_per_second": 83.57, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025404890441409972, | |
| "grad_norm": 2.9741797334281728e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031756113051762463, | |
| "grad_norm": 2.8849135560449213e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "grad_norm": 2.8593454771908e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 4.0193, | |
| "eval_samples_per_second": 164.956, | |
| "eval_steps_per_second": 82.602, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004445855827246745, | |
| "grad_norm": 1.5059550605656113e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0050809780882819944, | |
| "grad_norm": 2.1641260900651105e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "grad_norm": 2.36355081142392e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 4.1426, | |
| "eval_samples_per_second": 160.046, | |
| "eval_steps_per_second": 80.144, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006351222610352493, | |
| "grad_norm": 3.2984498830046505e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 214170943488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |