| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 12330, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.797242497972425e-05, | |
| "loss": 0.6204, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.59448499594485e-05, | |
| "loss": 0.48, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.3917274939172754e-05, | |
| "loss": 0.4046, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.1889699918897e-05, | |
| "loss": 0.3753, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.986212489862125e-05, | |
| "loss": 0.3585, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.78345498783455e-05, | |
| "loss": 0.3135, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.580697485806975e-05, | |
| "loss": 0.3133, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.3779399837794e-05, | |
| "loss": 0.2859, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.175182481751825e-05, | |
| "loss": 0.2699, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.9724249797242497e-05, | |
| "loss": 0.2659, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.7696674776966745e-05, | |
| "loss": 0.2406, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.5669099756691e-05, | |
| "loss": 0.243, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.3641524736415248e-05, | |
| "loss": 0.2233, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.1613949716139496e-05, | |
| "loss": 0.2175, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.9586374695863748e-05, | |
| "loss": 0.2141, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.7558799675587996e-05, | |
| "loss": 0.1998, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1.5531224655312247e-05, | |
| "loss": 0.1982, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.3503649635036497e-05, | |
| "loss": 0.188, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.1476074614760747e-05, | |
| "loss": 0.1835, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 9.448499594484997e-06, | |
| "loss": 0.1825, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 7.420924574209247e-06, | |
| "loss": 0.1745, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 5.393349553933496e-06, | |
| "loss": 0.1752, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.365774533657746e-06, | |
| "loss": 0.17, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.3381995133819951e-06, | |
| "loss": 0.167, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 12330, | |
| "total_flos": 1.2986290396643328e+16, | |
| "train_loss": 0.26658661773508385, | |
| "train_runtime": 2799.7511, | |
| "train_samples_per_second": 70.438, | |
| "train_steps_per_second": 4.404 | |
| } | |
| ], | |
| "max_steps": 12330, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.2986290396643328e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |