{ "best_metric": 1.2897050380706787, "best_model_checkpoint": " vicuna-sentiment-fintuned/checkpoint-250", "epoch": 1.2903225806451613, "eval_steps": 50, "global_step": 250, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05, "learning_rate": 2.9999999999999997e-05, "loss": 2.9781, "step": 10 }, { "epoch": 0.1, "learning_rate": 5.9999999999999995e-05, "loss": 2.8488, "step": 20 }, { "epoch": 0.15, "learning_rate": 8.999999999999999e-05, "loss": 2.5361, "step": 30 }, { "epoch": 0.21, "learning_rate": 0.00011999999999999999, "loss": 2.0695, "step": 40 }, { "epoch": 0.26, "learning_rate": 0.00015, "loss": 1.6545, "step": 50 }, { "epoch": 0.26, "eval_loss": 1.5430564880371094, "eval_runtime": 40.717, "eval_samples_per_second": 4.912, "eval_steps_per_second": 0.614, "step": 50 }, { "epoch": 0.31, "learning_rate": 0.00017999999999999998, "loss": 1.4716, "step": 60 }, { "epoch": 0.36, "learning_rate": 0.00020999999999999998, "loss": 1.4078, "step": 70 }, { "epoch": 0.41, "learning_rate": 0.00023999999999999998, "loss": 1.3884, "step": 80 }, { "epoch": 0.46, "learning_rate": 0.00027, "loss": 1.4108, "step": 90 }, { "epoch": 0.52, "learning_rate": 0.0003, "loss": 1.3022, "step": 100 }, { "epoch": 0.52, "eval_loss": 1.3164671659469604, "eval_runtime": 40.8127, "eval_samples_per_second": 4.9, "eval_steps_per_second": 0.613, "step": 100 }, { "epoch": 0.57, "learning_rate": 0.000285, "loss": 1.2699, "step": 110 }, { "epoch": 0.62, "learning_rate": 0.00027, "loss": 1.2852, "step": 120 }, { "epoch": 0.67, "learning_rate": 0.00025499999999999996, "loss": 1.278, "step": 130 }, { "epoch": 0.72, "learning_rate": 0.00023999999999999998, "loss": 1.2947, "step": 140 }, { "epoch": 0.77, "learning_rate": 0.000225, "loss": 1.2836, "step": 150 }, { "epoch": 0.77, "eval_loss": 1.2997195720672607, "eval_runtime": 40.7239, "eval_samples_per_second": 4.911, "eval_steps_per_second": 0.614, "step": 150 }, { "epoch": 0.83, "learning_rate": 0.00020999999999999998, "loss": 1.2874, "step": 160 }, { "epoch": 0.88, "learning_rate": 0.000195, "loss": 1.3118, "step": 170 }, { "epoch": 0.93, "learning_rate": 0.00017999999999999998, "loss": 1.2895, "step": 180 }, { "epoch": 0.98, "learning_rate": 0.000165, "loss": 1.2736, "step": 190 }, { "epoch": 1.03, "learning_rate": 0.00015, "loss": 1.2634, "step": 200 }, { "epoch": 1.03, "eval_loss": 1.2936323881149292, "eval_runtime": 40.7736, "eval_samples_per_second": 4.905, "eval_steps_per_second": 0.613, "step": 200 }, { "epoch": 1.08, "learning_rate": 0.000135, "loss": 1.2726, "step": 210 }, { "epoch": 1.14, "learning_rate": 0.00011999999999999999, "loss": 1.2617, "step": 220 }, { "epoch": 1.19, "learning_rate": 0.00010499999999999999, "loss": 1.2632, "step": 230 }, { "epoch": 1.24, "learning_rate": 8.999999999999999e-05, "loss": 1.2847, "step": 240 }, { "epoch": 1.29, "learning_rate": 7.5e-05, "loss": 1.2622, "step": 250 }, { "epoch": 1.29, "eval_loss": 1.2897050380706787, "eval_runtime": 40.6649, "eval_samples_per_second": 4.918, "eval_steps_per_second": 0.615, "step": 250 } ], "logging_steps": 10, "max_steps": 300, "num_train_epochs": 2, "save_steps": 50, "total_flos": 2.6747817642983424e+17, "trial_name": null, "trial_params": null }