| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6161616161616161, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9457994579945803e-05, | |
| "loss": 4.3763, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 3.8394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.81029810298103e-05, | |
| "loss": 3.639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7425474254742554e-05, | |
| "loss": 3.7962, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6747967479674795e-05, | |
| "loss": 3.5152, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.607046070460705e-05, | |
| "loss": 3.5752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.53929539295393e-05, | |
| "loss": 3.4463, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4715447154471546e-05, | |
| "loss": 3.5218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.2419066429138184, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 180.4791, | |
| "eval_samples_per_second": 0.15, | |
| "eval_steps_per_second": 0.078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.4037940379403794e-05, | |
| "loss": 3.5264, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.336043360433605e-05, | |
| "loss": 3.6286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.26829268292683e-05, | |
| "loss": 3.4611, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.2005420054200545e-05, | |
| "loss": 3.9319, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.132791327913279e-05, | |
| "loss": 3.7751, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.065040650406504e-05, | |
| "loss": 3.6241, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9972899728997295e-05, | |
| "loss": 3.3906, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.9295392953929537e-05, | |
| "loss": 3.1815, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 3.189028739929199, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 265.9332, | |
| "eval_samples_per_second": 0.102, | |
| "eval_steps_per_second": 0.053, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.861788617886179e-05, | |
| "loss": 3.3673, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.794037940379404e-05, | |
| "loss": 3.3792, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.726287262872629e-05, | |
| "loss": 3.5732, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6585365853658535e-05, | |
| "loss": 3.2772, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.6043360433604336e-05, | |
| "loss": 3.3803, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5365853658536584e-05, | |
| "loss": 3.2597, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.468834688346884e-05, | |
| "loss": 3.4085, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.401084010840109e-05, | |
| "loss": 3.2319, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 3.166618824005127, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 433.3435, | |
| "eval_samples_per_second": 0.062, | |
| "eval_steps_per_second": 0.032, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.6139, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.265582655826558e-05, | |
| "loss": 3.5873, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.197831978319784e-05, | |
| "loss": 3.3622, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.130081300813008e-05, | |
| "loss": 3.4854, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0623306233062334e-05, | |
| "loss": 3.4429, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9945799457994585e-05, | |
| "loss": 3.1618, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.926829268292683e-05, | |
| "loss": 3.428, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.859078590785908e-05, | |
| "loss": 3.2305, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 3.152249336242676, | |
| "eval_rouge2_fmeasure": 0.0037, | |
| "eval_rouge2_precision": 0.0062, | |
| "eval_rouge2_recall": 0.0026, | |
| "eval_runtime": 372.2318, | |
| "eval_samples_per_second": 0.073, | |
| "eval_steps_per_second": 0.038, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7913279132791332e-05, | |
| "loss": 3.0798, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7235772357723577e-05, | |
| "loss": 3.2169, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6558265582655828e-05, | |
| "loss": 3.4364, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.588075880758808e-05, | |
| "loss": 3.2353, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5203252032520324e-05, | |
| "loss": 3.4389, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4525745257452575e-05, | |
| "loss": 3.2847, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3848238482384823e-05, | |
| "loss": 3.0442, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.3170731707317075e-05, | |
| "loss": 3.2043, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 3.1420483589172363, | |
| "eval_rouge2_fmeasure": 0.0032, | |
| "eval_rouge2_precision": 0.0041, | |
| "eval_rouge2_recall": 0.0026, | |
| "eval_runtime": 417.3311, | |
| "eval_samples_per_second": 0.065, | |
| "eval_steps_per_second": 0.034, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 369, | |
| "num_train_epochs": 3, | |
| "total_flos": 7804505869516800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |