| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 9920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9994959677419356e-05, | |
| "loss": 10.8957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.7479838709677423e-05, | |
| "loss": 5.955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.495967741935484e-05, | |
| "loss": 5.2306, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.243951612903226e-05, | |
| "loss": 5.1627, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.991935483870968e-05, | |
| "loss": 5.1156, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.7399193548387094e-05, | |
| "loss": 5.1212, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.487903225806452e-05, | |
| "loss": 5.1012, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.2358870967741936e-05, | |
| "loss": 5.0911, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 5.0799, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.7318548387096775e-05, | |
| "loss": 5.0627, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.4798387096774196e-05, | |
| "loss": 5.0703, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.2278225806451614e-05, | |
| "loss": 5.0741, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.975806451612903e-05, | |
| "loss": 5.0708, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.7237903225806452e-05, | |
| "loss": 5.0604, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.4717741935483872e-05, | |
| "loss": 5.0575, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 1.2197580645161291e-05, | |
| "loss": 5.08, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 5.0736, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 7.15725806451613e-06, | |
| "loss": 5.0615, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.637096774193548e-06, | |
| "loss": 5.0382, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.1169354838709676e-06, | |
| "loss": 5.0565, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 9920, | |
| "total_flos": 2.4004406372562e+16, | |
| "train_loss": 5.131693365496973, | |
| "train_runtime": 5547.9529, | |
| "train_samples_per_second": 14.295, | |
| "train_steps_per_second": 1.788 | |
| } | |
| ], | |
| "max_steps": 9920, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.4004406372562e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |