| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 8420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.406175771971498e-06, | |
| "loss": 0.3692, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.812351543942995e-06, | |
| "loss": 0.2463, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.21852731591449e-06, | |
| "loss": 0.2089, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.624703087885986e-06, | |
| "loss": 0.1926, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.030878859857483e-06, | |
| "loss": 0.1504, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 6.437054631828979e-06, | |
| "loss": 0.1411, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 5.843230403800475e-06, | |
| "loss": 0.1425, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 5.2494061757719716e-06, | |
| "loss": 0.1351, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.6555819477434686e-06, | |
| "loss": 0.1067, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.061757719714965e-06, | |
| "loss": 0.1002, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.467933491686461e-06, | |
| "loss": 0.1048, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.874109263657958e-06, | |
| "loss": 0.1099, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.280285035629454e-06, | |
| "loss": 0.0836, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.6864608076009503e-06, | |
| "loss": 0.071, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.0926365795724466e-06, | |
| "loss": 0.0729, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.988123515439431e-07, | |
| "loss": 0.0837, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 8420, | |
| "total_flos": 1609513255434240.0, | |
| "train_loss": 0.14146648778485005, | |
| "train_runtime": 6028.0345, | |
| "train_samples_per_second": 44.691, | |
| "train_steps_per_second": 1.397 | |
| } | |
| ], | |
| "max_steps": 8420, | |
| "num_train_epochs": 4, | |
| "total_flos": 1609513255434240.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |