| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0032601431202829803, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.520286240565961e-05, | |
| "eval_loss": 3.0824153423309326, | |
| "eval_runtime": 361.6861, | |
| "eval_samples_per_second": 17.855, | |
| "eval_steps_per_second": 8.928, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032601431202829807, | |
| "grad_norm": 2.5320794582366943, | |
| "learning_rate": 5e-05, | |
| "loss": 12.694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006520286240565961, | |
| "grad_norm": 6.463990688323975, | |
| "learning_rate": 0.0001, | |
| "loss": 12.6127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006520286240565961, | |
| "eval_loss": 2.92987322807312, | |
| "eval_runtime": 362.2474, | |
| "eval_samples_per_second": 17.828, | |
| "eval_steps_per_second": 8.914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009780429360848942, | |
| "grad_norm": 10.645001411437988, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.5666, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013040572481131923, | |
| "grad_norm": 13.266217231750488, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013040572481131923, | |
| "eval_loss": 2.6472702026367188, | |
| "eval_runtime": 362.2482, | |
| "eval_samples_per_second": 17.828, | |
| "eval_steps_per_second": 8.914, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016300715601414901, | |
| "grad_norm": 10.522175788879395, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.834, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0019560858721697884, | |
| "grad_norm": 9.86556625366211, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019560858721697884, | |
| "eval_loss": 2.5723369121551514, | |
| "eval_runtime": 361.8657, | |
| "eval_samples_per_second": 17.846, | |
| "eval_steps_per_second": 8.923, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022821001841980865, | |
| "grad_norm": 8.9501371383667, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 9.8223, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026081144962263846, | |
| "grad_norm": 8.541926383972168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.513, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026081144962263846, | |
| "eval_loss": 2.542236804962158, | |
| "eval_runtime": 361.8354, | |
| "eval_samples_per_second": 17.848, | |
| "eval_steps_per_second": 8.924, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002934128808254682, | |
| "grad_norm": 10.6914701461792, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 9.9373, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0032601431202829803, | |
| "grad_norm": 10.446704864501953, | |
| "learning_rate": 0.0, | |
| "loss": 9.6477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0032601431202829803, | |
| "eval_loss": 2.536726713180542, | |
| "eval_runtime": 361.4827, | |
| "eval_samples_per_second": 17.865, | |
| "eval_steps_per_second": 8.933, | |
| "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": 8162390153625600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |