| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.915151515151515, | |
| "global_step": 360, | |
| "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 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.2493224932249323e-05, | |
| "loss": 3.4208, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.181571815718157e-05, | |
| "loss": 3.7157, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.1138211382113822e-05, | |
| "loss": 3.0534, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.046070460704607e-05, | |
| "loss": 3.2667, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.978319783197832e-05, | |
| "loss": 3.3489, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.9105691056910573e-05, | |
| "loss": 3.3139, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.842818428184282e-05, | |
| "loss": 3.3155, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.775067750677507e-05, | |
| "loss": 3.603, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 3.135263681411743, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 517.2838, | |
| "eval_samples_per_second": 0.052, | |
| "eval_steps_per_second": 0.027, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.707317073170732e-05, | |
| "loss": 3.4609, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.6395663956639568e-05, | |
| "loss": 3.2715, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.5718157181571816e-05, | |
| "loss": 3.91, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.5040650406504067e-05, | |
| "loss": 3.0947, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.4498644986449867e-05, | |
| "loss": 3.2667, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.3821138211382115e-05, | |
| "loss": 3.5289, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.3143631436314363e-05, | |
| "loss": 3.3016, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2466124661246612e-05, | |
| "loss": 3.2669, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 3.130876064300537, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 441.1701, | |
| "eval_samples_per_second": 0.061, | |
| "eval_steps_per_second": 0.032, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1788617886178862e-05, | |
| "loss": 3.0182, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 3.4221, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0433604336043361e-05, | |
| "loss": 3.1717, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.756097560975611e-06, | |
| "loss": 3.309, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.078590785907859e-06, | |
| "loss": 3.215, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.401084010840109e-06, | |
| "loss": 3.2693, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.723577235772358e-06, | |
| "loss": 3.3973, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.046070460704607e-06, | |
| "loss": 3.3138, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 3.127232074737549, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 495.8047, | |
| "eval_samples_per_second": 0.054, | |
| "eval_steps_per_second": 0.028, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.368563685636857e-06, | |
| "loss": 3.5124, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.6910569105691056e-06, | |
| "loss": 3.128, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.013550135501355e-06, | |
| "loss": 3.6112, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.336043360433605e-06, | |
| "loss": 3.0695, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.6585365853658537e-06, | |
| "loss": 3.4197, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.116531165311653e-06, | |
| "loss": 3.2216, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.4390243902439027e-06, | |
| "loss": 3.1863, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.7615176151761518e-06, | |
| "loss": 3.3628, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 3.125962972640991, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 439.7386, | |
| "eval_samples_per_second": 0.061, | |
| "eval_steps_per_second": 0.032, | |
| "step": 360 | |
| } | |
| ], | |
| "max_steps": 369, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.404811056513024e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |