| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 7950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.685534591194969e-05, | |
| "loss": 3.2357, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3710691823899376e-05, | |
| "loss": 2.6834, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0566037735849064e-05, | |
| "loss": 2.4737, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7421383647798744e-05, | |
| "loss": 2.3981, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.4276729559748424e-05, | |
| "loss": 2.2355, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.113207547169811e-05, | |
| "loss": 1.9009, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7987421383647798e-05, | |
| "loss": 1.7445, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4842767295597485e-05, | |
| "loss": 1.7823, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.1698113207547172e-05, | |
| "loss": 1.7014, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.8553459119496856e-05, | |
| "loss": 1.7119, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.540880503144654e-05, | |
| "loss": 1.4952, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.2264150943396227e-05, | |
| "loss": 1.2917, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.119496855345912e-06, | |
| "loss": 1.2734, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.974842767295598e-06, | |
| "loss": 1.3188, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.830188679245283e-06, | |
| "loss": 1.2928, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 7950, | |
| "total_flos": 5838088796626944.0, | |
| "train_loss": 1.867107309785279, | |
| "train_runtime": 3985.5921, | |
| "train_samples_per_second": 7.978, | |
| "train_steps_per_second": 1.995 | |
| } | |
| ], | |
| "max_steps": 7950, | |
| "num_train_epochs": 3, | |
| "total_flos": 5838088796626944.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |