| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00843775049571784, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016875500991435683, | |
| "eval_loss": 1.6930816173553467, | |
| "eval_runtime": 56.4463, | |
| "eval_samples_per_second": 44.201, | |
| "eval_steps_per_second": 22.11, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "grad_norm": 3.0491347312927246, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.7121, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021938151288866388, | |
| "eval_loss": 1.4784473180770874, | |
| "eval_runtime": 55.3991, | |
| "eval_samples_per_second": 45.037, | |
| "eval_steps_per_second": 22.527, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "grad_norm": 4.672301292419434, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.4902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0043876302577732776, | |
| "eval_loss": 1.2732303142547607, | |
| "eval_runtime": 55.4671, | |
| "eval_samples_per_second": 44.982, | |
| "eval_steps_per_second": 22.5, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "grad_norm": 10.396780967712402, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.2737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006581445386659917, | |
| "eval_loss": 1.236678123474121, | |
| "eval_runtime": 55.4168, | |
| "eval_samples_per_second": 45.022, | |
| "eval_steps_per_second": 22.52, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "grad_norm": 4.811294078826904, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.2779, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "grad_norm": 6.542264938354492, | |
| "learning_rate": 0.0, | |
| "loss": 1.2403, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 3269109743616000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |