| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 11646, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7853340202644685e-05, | |
| "loss": 3.1971, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.570668040528937e-05, | |
| "loss": 2.7354, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.356002060793406e-05, | |
| "loss": 2.5217, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1413360810578746e-05, | |
| "loss": 2.3945, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.926670101322343e-05, | |
| "loss": 2.2924, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.712004121586811e-05, | |
| "loss": 2.2309, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.4973381418512793e-05, | |
| "loss": 2.1581, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.282672162115748e-05, | |
| "loss": 2.1062, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.0680061823802165e-05, | |
| "loss": 2.0668, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.8533402026446848e-05, | |
| "loss": 2.017, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6386742229091534e-05, | |
| "loss": 1.9905, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.424008243173622e-05, | |
| "loss": 1.9665, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2093422634380902e-05, | |
| "loss": 1.9443, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.994676283702559e-05, | |
| "loss": 1.9293, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7800103039670274e-05, | |
| "loss": 1.8996, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.5653443242314956e-05, | |
| "loss": 1.8974, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3506783444959644e-05, | |
| "loss": 1.8627, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1360123647604328e-05, | |
| "loss": 1.868, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.213463850249012e-06, | |
| "loss": 1.8579, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.066804052893698e-06, | |
| "loss": 1.8435, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.9201442555383824e-06, | |
| "loss": 1.8395, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.7734844581830675e-06, | |
| "loss": 1.8345, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.26824660827752e-07, | |
| "loss": 1.8475, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 11646, | |
| "total_flos": 5065259927605248.0, | |
| "train_loss": 2.0967203749837324, | |
| "train_runtime": 2434.7534, | |
| "train_samples_per_second": 76.526, | |
| "train_steps_per_second": 4.783 | |
| } | |
| ], | |
| "max_steps": 11646, | |
| "num_train_epochs": 3, | |
| "total_flos": 5065259927605248.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |