| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 13088, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.88539119804401e-05, | |
| "loss": 2.3229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.7707823960880195e-05, | |
| "loss": 1.7926, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.6561735941320294e-05, | |
| "loss": 1.6682, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.5415647921760392e-05, | |
| "loss": 1.6135, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.4269559902200488e-05, | |
| "loss": 1.5343, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.3123471882640587e-05, | |
| "loss": 1.4642, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.1977383863080685e-05, | |
| "loss": 1.423, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.083129584352078e-05, | |
| "loss": 1.41, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9685207823960883e-05, | |
| "loss": 1.3659, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8539119804400978e-05, | |
| "loss": 1.3153, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.7393031784841077e-05, | |
| "loss": 1.2976, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6246943765281176e-05, | |
| "loss": 1.2462, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5100855745721271e-05, | |
| "loss": 1.2594, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.395476772616137e-05, | |
| "loss": 1.0087, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2808679706601467e-05, | |
| "loss": 1.0272, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1662591687041566e-05, | |
| "loss": 1.0037, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.0516503667481663e-05, | |
| "loss": 0.968, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.37041564792176e-06, | |
| "loss": 0.9763, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.224327628361858e-06, | |
| "loss": 0.9705, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.078239608801956e-06, | |
| "loss": 0.9548, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.932151589242053e-06, | |
| "loss": 0.955, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.786063569682151e-06, | |
| "loss": 0.932, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.6399755501222492e-06, | |
| "loss": 0.9331, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.493887530562347e-06, | |
| "loss": 0.9126, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.347799511002445e-06, | |
| "loss": 0.909, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.0171149144254277e-07, | |
| "loss": 0.89, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 13088, | |
| "total_flos": 2.5921698247213056e+16, | |
| "train_loss": 1.2332238556411854, | |
| "train_runtime": 1237.3872, | |
| "train_samples_per_second": 211.523, | |
| "train_steps_per_second": 10.577 | |
| } | |
| ], | |
| "max_steps": 13088, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.5921698247213056e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |