| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002856530743412126, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.713061486824252e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 622.4173, | |
| "eval_samples_per_second": 11.841, | |
| "eval_steps_per_second": 5.92, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028565307434121257, | |
| "grad_norm": 6.127974033355713, | |
| "learning_rate": 5e-05, | |
| "loss": 4.386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005713061486824251, | |
| "grad_norm": 3.208916187286377, | |
| "learning_rate": 0.0001, | |
| "loss": 3.815, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005713061486824251, | |
| "eval_loss": NaN, | |
| "eval_runtime": 624.0487, | |
| "eval_samples_per_second": 11.81, | |
| "eval_steps_per_second": 5.905, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008569592230236378, | |
| "grad_norm": 3.069624662399292, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7243, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011426122973648503, | |
| "grad_norm": 2.991121530532837, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011426122973648503, | |
| "eval_loss": NaN, | |
| "eval_runtime": 623.8701, | |
| "eval_samples_per_second": 11.813, | |
| "eval_steps_per_second": 5.907, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001428265371706063, | |
| "grad_norm": 4.1910505294799805, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9362, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017139184460472755, | |
| "grad_norm": 5.376562118530273, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017139184460472755, | |
| "eval_loss": NaN, | |
| "eval_runtime": 623.2871, | |
| "eval_samples_per_second": 11.824, | |
| "eval_steps_per_second": 5.912, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019995715203884883, | |
| "grad_norm": 2.4734044075012207, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2701, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0022852245947297006, | |
| "grad_norm": 0.6052327156066895, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022852245947297006, | |
| "eval_loss": NaN, | |
| "eval_runtime": 623.4549, | |
| "eval_samples_per_second": 11.821, | |
| "eval_steps_per_second": 5.911, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0025708776690709133, | |
| "grad_norm": 0.7822670936584473, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2546, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002856530743412126, | |
| "grad_norm": 1.9285300970077515, | |
| "learning_rate": 0.0, | |
| "loss": 0.2735, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002856530743412126, | |
| "eval_loss": NaN, | |
| "eval_runtime": 626.0841, | |
| "eval_samples_per_second": 11.772, | |
| "eval_steps_per_second": 5.886, | |
| "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": 1.2299602250170368e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |