| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00015950588621027308, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7722876245585897e-05, | |
| "grad_norm": 0.9799976944923401, | |
| "learning_rate": 2e-05, | |
| "loss": 1.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7722876245585897e-05, | |
| "eval_loss": 1.7362161874771118, | |
| "eval_runtime": 749.8716, | |
| "eval_samples_per_second": 31.683, | |
| "eval_steps_per_second": 15.841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.5445752491171794e-05, | |
| "grad_norm": 0.5454490780830383, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.316862873675769e-05, | |
| "grad_norm": 0.8450607657432556, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.316862873675769e-05, | |
| "eval_loss": 1.7307437658309937, | |
| "eval_runtime": 748.9623, | |
| "eval_samples_per_second": 31.721, | |
| "eval_steps_per_second": 15.861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.089150498234359e-05, | |
| "grad_norm": 0.8474843502044678, | |
| "learning_rate": 8e-05, | |
| "loss": 1.792, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.861438122792948e-05, | |
| "grad_norm": 0.8669983148574829, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9209, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010633725747351538, | |
| "grad_norm": 1.082075834274292, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7186, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010633725747351538, | |
| "eval_loss": 1.6226059198379517, | |
| "eval_runtime": 749.0877, | |
| "eval_samples_per_second": 31.716, | |
| "eval_steps_per_second": 15.858, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00012406013371910128, | |
| "grad_norm": 0.7685911655426025, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0244, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00014178300996468718, | |
| "grad_norm": 1.1620005369186401, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015950588621027308, | |
| "grad_norm": 1.1282984018325806, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1027, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00015950588621027308, | |
| "eval_loss": 1.106915831565857, | |
| "eval_runtime": 749.5623, | |
| "eval_samples_per_second": 31.696, | |
| "eval_steps_per_second": 15.848, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1606627350282240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |