| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 39300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.0473, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.034566044807434, | |
| "eval_runtime": 35.414, | |
| "eval_samples_per_second": 22.166, | |
| "eval_steps_per_second": 1.412, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.936386768447838e-05, | |
| "loss": 1.5209, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.1413, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8939195275306702, | |
| "eval_runtime": 35.4148, | |
| "eval_samples_per_second": 22.166, | |
| "eval_steps_per_second": 1.412, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.8727735368956744e-05, | |
| "loss": 1.0258, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.1641, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8333808779716492, | |
| "eval_runtime": 35.2354, | |
| "eval_samples_per_second": 22.279, | |
| "eval_steps_per_second": 1.419, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.809160305343512e-05, | |
| "loss": 0.9177, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.1729, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7867220044136047, | |
| "eval_runtime": 35.207, | |
| "eval_samples_per_second": 22.297, | |
| "eval_steps_per_second": 1.42, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.1742, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7542837858200073, | |
| "eval_runtime": 35.3809, | |
| "eval_samples_per_second": 22.187, | |
| "eval_steps_per_second": 1.413, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.7455470737913485e-05, | |
| "loss": 0.8482, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.1692, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7316721677780151, | |
| "eval_runtime": 35.4956, | |
| "eval_samples_per_second": 22.115, | |
| "eval_steps_per_second": 1.409, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 4.681933842239186e-05, | |
| "loss": 0.7957, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.1742, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7106090188026428, | |
| "eval_runtime": 35.1034, | |
| "eval_samples_per_second": 22.362, | |
| "eval_steps_per_second": 1.424, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 4.618320610687023e-05, | |
| "loss": 0.7557, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.216, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6849327087402344, | |
| "eval_runtime": 35.4066, | |
| "eval_samples_per_second": 22.171, | |
| "eval_steps_per_second": 1.412, | |
| "step": 3144 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.5547073791348604e-05, | |
| "loss": 0.7204, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.189, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6731250882148743, | |
| "eval_runtime": 35.3153, | |
| "eval_samples_per_second": 22.228, | |
| "eval_steps_per_second": 1.416, | |
| "step": 3537 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.2063, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6562144160270691, | |
| "eval_runtime": 35.358, | |
| "eval_samples_per_second": 22.201, | |
| "eval_steps_per_second": 1.414, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 4.4910941475826975e-05, | |
| "loss": 0.6901, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 0.2025, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6510306596755981, | |
| "eval_runtime": 35.1746, | |
| "eval_samples_per_second": 22.317, | |
| "eval_steps_per_second": 1.421, | |
| "step": 4323 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 4.4274809160305345e-05, | |
| "loss": 0.6635, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 0.2266, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6423279047012329, | |
| "eval_runtime": 34.9781, | |
| "eval_samples_per_second": 22.443, | |
| "eval_steps_per_second": 1.429, | |
| "step": 4716 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 4.3638676844783716e-05, | |
| "loss": 0.6346, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 0.2229, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6330356597900391, | |
| "eval_runtime": 35.0795, | |
| "eval_samples_per_second": 22.378, | |
| "eval_steps_per_second": 1.425, | |
| "step": 5109 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 4.300254452926209e-05, | |
| "loss": 0.6132, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 0.2195, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6257367134094238, | |
| "eval_runtime": 34.9799, | |
| "eval_samples_per_second": 22.441, | |
| "eval_steps_per_second": 1.429, | |
| "step": 5502 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 0.2344, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6191786527633667, | |
| "eval_runtime": 35.2808, | |
| "eval_samples_per_second": 22.25, | |
| "eval_steps_per_second": 1.417, | |
| "step": 5895 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 4.236641221374046e-05, | |
| "loss": 0.5885, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 0.2424, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6103959083557129, | |
| "eval_runtime": 35.1057, | |
| "eval_samples_per_second": 22.361, | |
| "eval_steps_per_second": 1.424, | |
| "step": 6288 | |
| }, | |
| { | |
| "epoch": 16.54, | |
| "learning_rate": 4.1730279898218835e-05, | |
| "loss": 0.5682, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 0.2536, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6047710180282593, | |
| "eval_runtime": 35.079, | |
| "eval_samples_per_second": 22.378, | |
| "eval_steps_per_second": 1.425, | |
| "step": 6681 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 4.10941475826972e-05, | |
| "loss": 0.5452, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 0.2541, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6057348847389221, | |
| "eval_runtime": 35.3873, | |
| "eval_samples_per_second": 22.183, | |
| "eval_steps_per_second": 1.413, | |
| "step": 7074 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 0.2526, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6047215461730957, | |
| "eval_runtime": 35.004, | |
| "eval_samples_per_second": 22.426, | |
| "eval_steps_per_second": 1.428, | |
| "step": 7467 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 4.0458015267175576e-05, | |
| "loss": 0.5294, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 0.2644, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6065888404846191, | |
| "eval_runtime": 35.2375, | |
| "eval_samples_per_second": 22.277, | |
| "eval_steps_per_second": 1.419, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 3.982188295165395e-05, | |
| "loss": 0.5072, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 0.2666, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6080436706542969, | |
| "eval_runtime": 35.085, | |
| "eval_samples_per_second": 22.374, | |
| "eval_steps_per_second": 1.425, | |
| "step": 8253 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "learning_rate": 3.918575063613232e-05, | |
| "loss": 0.4921, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 0.2499, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6091626882553101, | |
| "eval_runtime": 35.0913, | |
| "eval_samples_per_second": 22.37, | |
| "eval_steps_per_second": 1.425, | |
| "step": 8646 | |
| }, | |
| { | |
| "epoch": 22.9, | |
| "learning_rate": 3.854961832061069e-05, | |
| "loss": 0.4753, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 0.2719, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6132063269615173, | |
| "eval_runtime": 35.0981, | |
| "eval_samples_per_second": 22.366, | |
| "eval_steps_per_second": 1.425, | |
| "step": 9039 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 0.2724, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6088494658470154, | |
| "eval_runtime": 35.1025, | |
| "eval_samples_per_second": 22.363, | |
| "eval_steps_per_second": 1.424, | |
| "step": 9432 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 3.791348600508906e-05, | |
| "loss": 0.4597, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 0.2683, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6127578020095825, | |
| "eval_runtime": 35.0847, | |
| "eval_samples_per_second": 22.374, | |
| "eval_steps_per_second": 1.425, | |
| "step": 9825 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 3.727735368956743e-05, | |
| "loss": 0.4443, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 0.2856, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6183450818061829, | |
| "eval_runtime": 35.0496, | |
| "eval_samples_per_second": 22.397, | |
| "eval_steps_per_second": 1.427, | |
| "step": 10218 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 3.66412213740458e-05, | |
| "loss": 0.4301, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 0.3006, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6246443390846252, | |
| "eval_runtime": 35.1774, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.421, | |
| "step": 10611 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 3.600508905852418e-05, | |
| "loss": 0.418, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 0.2788, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6312348246574402, | |
| "eval_runtime": 35.3395, | |
| "eval_samples_per_second": 22.213, | |
| "eval_steps_per_second": 1.415, | |
| "step": 11004 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 0.2843, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6295350790023804, | |
| "eval_runtime": 35.2861, | |
| "eval_samples_per_second": 22.247, | |
| "eval_steps_per_second": 1.417, | |
| "step": 11397 | |
| }, | |
| { | |
| "epoch": 29.26, | |
| "learning_rate": 3.536895674300255e-05, | |
| "loss": 0.4002, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 0.2982, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6349673271179199, | |
| "eval_runtime": 35.0212, | |
| "eval_samples_per_second": 22.415, | |
| "eval_steps_per_second": 1.428, | |
| "step": 11790 | |
| }, | |
| { | |
| "epoch": 30.53, | |
| "learning_rate": 3.473282442748092e-05, | |
| "loss": 0.3913, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 0.2822, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6441249847412109, | |
| "eval_runtime": 35.0154, | |
| "eval_samples_per_second": 22.419, | |
| "eval_steps_per_second": 1.428, | |
| "step": 12183 | |
| }, | |
| { | |
| "epoch": 31.81, | |
| "learning_rate": 3.409669211195929e-05, | |
| "loss": 0.3755, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 0.3215, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6430069804191589, | |
| "eval_runtime": 35.1225, | |
| "eval_samples_per_second": 22.35, | |
| "eval_steps_per_second": 1.424, | |
| "step": 12576 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 0.3024, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6485504508018494, | |
| "eval_runtime": 35.0519, | |
| "eval_samples_per_second": 22.395, | |
| "eval_steps_per_second": 1.426, | |
| "step": 12969 | |
| }, | |
| { | |
| "epoch": 33.08, | |
| "learning_rate": 3.346055979643766e-05, | |
| "loss": 0.3673, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 0.2985, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6527048945426941, | |
| "eval_runtime": 34.9946, | |
| "eval_samples_per_second": 22.432, | |
| "eval_steps_per_second": 1.429, | |
| "step": 13362 | |
| }, | |
| { | |
| "epoch": 34.35, | |
| "learning_rate": 3.282442748091603e-05, | |
| "loss": 0.352, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 0.31, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6660041213035583, | |
| "eval_runtime": 34.9679, | |
| "eval_samples_per_second": 22.449, | |
| "eval_steps_per_second": 1.43, | |
| "step": 13755 | |
| }, | |
| { | |
| "epoch": 35.62, | |
| "learning_rate": 3.21882951653944e-05, | |
| "loss": 0.3408, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 0.288, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6737257838249207, | |
| "eval_runtime": 35.0785, | |
| "eval_samples_per_second": 22.378, | |
| "eval_steps_per_second": 1.425, | |
| "step": 14148 | |
| }, | |
| { | |
| "epoch": 36.9, | |
| "learning_rate": 3.155216284987277e-05, | |
| "loss": 0.3307, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 0.2995, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6772977113723755, | |
| "eval_runtime": 35.0227, | |
| "eval_samples_per_second": 22.414, | |
| "eval_steps_per_second": 1.428, | |
| "step": 14541 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 0.29, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6903324723243713, | |
| "eval_runtime": 35.1225, | |
| "eval_samples_per_second": 22.35, | |
| "eval_steps_per_second": 1.424, | |
| "step": 14934 | |
| }, | |
| { | |
| "epoch": 38.17, | |
| "learning_rate": 3.091603053435115e-05, | |
| "loss": 0.3182, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 0.2848, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7059388160705566, | |
| "eval_runtime": 34.9533, | |
| "eval_samples_per_second": 22.459, | |
| "eval_steps_per_second": 1.43, | |
| "step": 15327 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 3.0279898218829518e-05, | |
| "loss": 0.3077, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 0.2878, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6985650658607483, | |
| "eval_runtime": 35.0758, | |
| "eval_samples_per_second": 22.38, | |
| "eval_steps_per_second": 1.425, | |
| "step": 15720 | |
| }, | |
| { | |
| "epoch": 40.71, | |
| "learning_rate": 2.9643765903307892e-05, | |
| "loss": 0.298, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_bleu": 0.2859, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7053300142288208, | |
| "eval_runtime": 35.1562, | |
| "eval_samples_per_second": 22.329, | |
| "eval_steps_per_second": 1.422, | |
| "step": 16113 | |
| }, | |
| { | |
| "epoch": 41.98, | |
| "learning_rate": 2.900763358778626e-05, | |
| "loss": 0.29, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_bleu": 0.2871, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.719767689704895, | |
| "eval_runtime": 35.1382, | |
| "eval_samples_per_second": 22.34, | |
| "eval_steps_per_second": 1.423, | |
| "step": 16506 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_bleu": 0.2813, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7274527549743652, | |
| "eval_runtime": 35.0854, | |
| "eval_samples_per_second": 22.374, | |
| "eval_steps_per_second": 1.425, | |
| "step": 16899 | |
| }, | |
| { | |
| "epoch": 43.26, | |
| "learning_rate": 2.8371501272264633e-05, | |
| "loss": 0.2787, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_bleu": 0.2972, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7369562983512878, | |
| "eval_runtime": 35.1464, | |
| "eval_samples_per_second": 22.335, | |
| "eval_steps_per_second": 1.423, | |
| "step": 17292 | |
| }, | |
| { | |
| "epoch": 44.53, | |
| "learning_rate": 2.7735368956743e-05, | |
| "loss": 0.268, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_bleu": 0.26, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7426473498344421, | |
| "eval_runtime": 35.1116, | |
| "eval_samples_per_second": 22.357, | |
| "eval_steps_per_second": 1.424, | |
| "step": 17685 | |
| }, | |
| { | |
| "epoch": 45.8, | |
| "learning_rate": 2.7099236641221375e-05, | |
| "loss": 0.2638, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_bleu": 0.2846, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7529018521308899, | |
| "eval_runtime": 35.1433, | |
| "eval_samples_per_second": 22.337, | |
| "eval_steps_per_second": 1.423, | |
| "step": 18078 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_bleu": 0.2898, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7602871060371399, | |
| "eval_runtime": 35.1079, | |
| "eval_samples_per_second": 22.36, | |
| "eval_steps_per_second": 1.424, | |
| "step": 18471 | |
| }, | |
| { | |
| "epoch": 47.07, | |
| "learning_rate": 2.6463104325699745e-05, | |
| "loss": 0.253, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_bleu": 0.277, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7711123824119568, | |
| "eval_runtime": 35.1881, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 1.421, | |
| "step": 18864 | |
| }, | |
| { | |
| "epoch": 48.35, | |
| "learning_rate": 2.582697201017812e-05, | |
| "loss": 0.244, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_bleu": 0.3005, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7778590321540833, | |
| "eval_runtime": 35.1873, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 1.421, | |
| "step": 19257 | |
| }, | |
| { | |
| "epoch": 49.62, | |
| "learning_rate": 2.5190839694656487e-05, | |
| "loss": 0.2368, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_bleu": 0.2931, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7815132737159729, | |
| "eval_runtime": 35.108, | |
| "eval_samples_per_second": 22.36, | |
| "eval_steps_per_second": 1.424, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 50.89, | |
| "learning_rate": 2.455470737913486e-05, | |
| "loss": 0.2301, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_bleu": 0.2998, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8020169734954834, | |
| "eval_runtime": 35.1735, | |
| "eval_samples_per_second": 22.318, | |
| "eval_steps_per_second": 1.422, | |
| "step": 20043 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_bleu": 0.2806, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8051058053970337, | |
| "eval_runtime": 35.0481, | |
| "eval_samples_per_second": 22.398, | |
| "eval_steps_per_second": 1.427, | |
| "step": 20436 | |
| }, | |
| { | |
| "epoch": 52.16, | |
| "learning_rate": 2.391857506361323e-05, | |
| "loss": 0.2217, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_bleu": 0.294, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.811935544013977, | |
| "eval_runtime": 35.104, | |
| "eval_samples_per_second": 22.362, | |
| "eval_steps_per_second": 1.424, | |
| "step": 20829 | |
| }, | |
| { | |
| "epoch": 53.44, | |
| "learning_rate": 2.3282442748091605e-05, | |
| "loss": 0.2158, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_bleu": 0.2921, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8288211226463318, | |
| "eval_runtime": 35.1084, | |
| "eval_samples_per_second": 22.359, | |
| "eval_steps_per_second": 1.424, | |
| "step": 21222 | |
| }, | |
| { | |
| "epoch": 54.71, | |
| "learning_rate": 2.2646310432569976e-05, | |
| "loss": 0.2079, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_bleu": 0.2954, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8340888619422913, | |
| "eval_runtime": 35.1775, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.421, | |
| "step": 21615 | |
| }, | |
| { | |
| "epoch": 55.98, | |
| "learning_rate": 2.2010178117048347e-05, | |
| "loss": 0.2027, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_bleu": 0.2884, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8364927768707275, | |
| "eval_runtime": 35.072, | |
| "eval_samples_per_second": 22.383, | |
| "eval_steps_per_second": 1.426, | |
| "step": 22008 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_bleu": 0.2995, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8441442251205444, | |
| "eval_runtime": 35.1154, | |
| "eval_samples_per_second": 22.355, | |
| "eval_steps_per_second": 1.424, | |
| "step": 22401 | |
| }, | |
| { | |
| "epoch": 57.25, | |
| "learning_rate": 2.1374045801526718e-05, | |
| "loss": 0.1954, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_bleu": 0.3115, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8488335609436035, | |
| "eval_runtime": 34.9312, | |
| "eval_samples_per_second": 22.473, | |
| "eval_steps_per_second": 1.431, | |
| "step": 22794 | |
| }, | |
| { | |
| "epoch": 58.52, | |
| "learning_rate": 2.0737913486005088e-05, | |
| "loss": 0.1918, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_bleu": 0.3085, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8709967732429504, | |
| "eval_runtime": 35.0738, | |
| "eval_samples_per_second": 22.381, | |
| "eval_steps_per_second": 1.426, | |
| "step": 23187 | |
| }, | |
| { | |
| "epoch": 59.8, | |
| "learning_rate": 2.0101781170483462e-05, | |
| "loss": 0.1857, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_bleu": 0.2932, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8718471527099609, | |
| "eval_runtime": 35.1809, | |
| "eval_samples_per_second": 22.313, | |
| "eval_steps_per_second": 1.421, | |
| "step": 23580 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_bleu": 0.2923, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8777070045471191, | |
| "eval_runtime": 35.0923, | |
| "eval_samples_per_second": 22.37, | |
| "eval_steps_per_second": 1.425, | |
| "step": 23973 | |
| }, | |
| { | |
| "epoch": 61.07, | |
| "learning_rate": 1.9465648854961833e-05, | |
| "loss": 0.1796, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_bleu": 0.3038, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8831952214241028, | |
| "eval_runtime": 35.1476, | |
| "eval_samples_per_second": 22.334, | |
| "eval_steps_per_second": 1.423, | |
| "step": 24366 | |
| }, | |
| { | |
| "epoch": 62.34, | |
| "learning_rate": 1.8829516539440204e-05, | |
| "loss": 0.1753, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_bleu": 0.3063, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8996883630752563, | |
| "eval_runtime": 35.1466, | |
| "eval_samples_per_second": 22.335, | |
| "eval_steps_per_second": 1.423, | |
| "step": 24759 | |
| }, | |
| { | |
| "epoch": 63.61, | |
| "learning_rate": 1.8193384223918574e-05, | |
| "loss": 0.1703, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_bleu": 0.3047, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9198061227798462, | |
| "eval_runtime": 35.8655, | |
| "eval_samples_per_second": 21.887, | |
| "eval_steps_per_second": 1.394, | |
| "step": 25152 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "learning_rate": 1.7557251908396945e-05, | |
| "loss": 0.1661, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_bleu": 0.3159, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9193503856658936, | |
| "eval_runtime": 35.1603, | |
| "eval_samples_per_second": 22.326, | |
| "eval_steps_per_second": 1.422, | |
| "step": 25545 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_bleu": 0.2962, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9242938756942749, | |
| "eval_runtime": 35.073, | |
| "eval_samples_per_second": 22.382, | |
| "eval_steps_per_second": 1.426, | |
| "step": 25938 | |
| }, | |
| { | |
| "epoch": 66.16, | |
| "learning_rate": 1.692111959287532e-05, | |
| "loss": 0.1606, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_bleu": 0.3065, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9375536441802979, | |
| "eval_runtime": 34.9169, | |
| "eval_samples_per_second": 22.482, | |
| "eval_steps_per_second": 1.432, | |
| "step": 26331 | |
| }, | |
| { | |
| "epoch": 67.43, | |
| "learning_rate": 1.628498727735369e-05, | |
| "loss": 0.1582, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_bleu": 0.3002, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9338624477386475, | |
| "eval_runtime": 35.1084, | |
| "eval_samples_per_second": 22.359, | |
| "eval_steps_per_second": 1.424, | |
| "step": 26724 | |
| }, | |
| { | |
| "epoch": 68.7, | |
| "learning_rate": 1.5648854961832064e-05, | |
| "loss": 0.1533, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_bleu": 0.3096, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9420493841171265, | |
| "eval_runtime": 35.122, | |
| "eval_samples_per_second": 22.351, | |
| "eval_steps_per_second": 1.424, | |
| "step": 27117 | |
| }, | |
| { | |
| "epoch": 69.97, | |
| "learning_rate": 1.5012722646310435e-05, | |
| "loss": 0.1503, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_bleu": 0.2919, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9522092342376709, | |
| "eval_runtime": 35.4031, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 1.412, | |
| "step": 27510 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_bleu": 0.3085, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9620120525360107, | |
| "eval_runtime": 35.926, | |
| "eval_samples_per_second": 21.85, | |
| "eval_steps_per_second": 1.392, | |
| "step": 27903 | |
| }, | |
| { | |
| "epoch": 71.25, | |
| "learning_rate": 1.4376590330788805e-05, | |
| "loss": 0.1469, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_bleu": 0.2946, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9673256874084473, | |
| "eval_runtime": 35.209, | |
| "eval_samples_per_second": 22.295, | |
| "eval_steps_per_second": 1.42, | |
| "step": 28296 | |
| }, | |
| { | |
| "epoch": 72.52, | |
| "learning_rate": 1.3740458015267178e-05, | |
| "loss": 0.1416, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_bleu": 0.3019, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9706256985664368, | |
| "eval_runtime": 35.1594, | |
| "eval_samples_per_second": 22.327, | |
| "eval_steps_per_second": 1.422, | |
| "step": 28689 | |
| }, | |
| { | |
| "epoch": 73.79, | |
| "learning_rate": 1.3104325699745548e-05, | |
| "loss": 0.1401, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_bleu": 0.3103, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9876586198806763, | |
| "eval_runtime": 35.0824, | |
| "eval_samples_per_second": 22.376, | |
| "eval_steps_per_second": 1.425, | |
| "step": 29082 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_bleu": 0.2903, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9860377311706543, | |
| "eval_runtime": 35.2841, | |
| "eval_samples_per_second": 22.248, | |
| "eval_steps_per_second": 1.417, | |
| "step": 29475 | |
| }, | |
| { | |
| "epoch": 75.06, | |
| "learning_rate": 1.2468193384223919e-05, | |
| "loss": 0.1376, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_bleu": 0.2855, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0073317289352417, | |
| "eval_runtime": 35.1549, | |
| "eval_samples_per_second": 22.33, | |
| "eval_steps_per_second": 1.422, | |
| "step": 29868 | |
| }, | |
| { | |
| "epoch": 76.34, | |
| "learning_rate": 1.1832061068702292e-05, | |
| "loss": 0.1341, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_bleu": 0.2927, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0067394971847534, | |
| "eval_runtime": 35.7641, | |
| "eval_samples_per_second": 21.949, | |
| "eval_steps_per_second": 1.398, | |
| "step": 30261 | |
| }, | |
| { | |
| "epoch": 77.61, | |
| "learning_rate": 1.1195928753180662e-05, | |
| "loss": 0.1307, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_bleu": 0.3, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.006367564201355, | |
| "eval_runtime": 35.3184, | |
| "eval_samples_per_second": 22.226, | |
| "eval_steps_per_second": 1.416, | |
| "step": 30654 | |
| }, | |
| { | |
| "epoch": 78.88, | |
| "learning_rate": 1.0559796437659033e-05, | |
| "loss": 0.1296, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_bleu": 0.2886, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.022121787071228, | |
| "eval_runtime": 35.3415, | |
| "eval_samples_per_second": 22.212, | |
| "eval_steps_per_second": 1.415, | |
| "step": 31047 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_bleu": 0.297, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.021680235862732, | |
| "eval_runtime": 35.3179, | |
| "eval_samples_per_second": 22.227, | |
| "eval_steps_per_second": 1.416, | |
| "step": 31440 | |
| }, | |
| { | |
| "epoch": 80.15, | |
| "learning_rate": 9.923664122137405e-06, | |
| "loss": 0.126, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_bleu": 0.2919, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.027828335762024, | |
| "eval_runtime": 35.4035, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 1.412, | |
| "step": 31833 | |
| }, | |
| { | |
| "epoch": 81.42, | |
| "learning_rate": 9.287531806615776e-06, | |
| "loss": 0.1238, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_bleu": 0.2951, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.03290855884552, | |
| "eval_runtime": 35.2364, | |
| "eval_samples_per_second": 22.278, | |
| "eval_steps_per_second": 1.419, | |
| "step": 32226 | |
| }, | |
| { | |
| "epoch": 82.7, | |
| "learning_rate": 8.651399491094148e-06, | |
| "loss": 0.1214, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_bleu": 0.3043, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0350806713104248, | |
| "eval_runtime": 35.1544, | |
| "eval_samples_per_second": 22.33, | |
| "eval_steps_per_second": 1.422, | |
| "step": 32619 | |
| }, | |
| { | |
| "epoch": 83.97, | |
| "learning_rate": 8.015267175572519e-06, | |
| "loss": 0.1206, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_bleu": 0.2964, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.04984450340271, | |
| "eval_runtime": 35.3457, | |
| "eval_samples_per_second": 22.209, | |
| "eval_steps_per_second": 1.415, | |
| "step": 33012 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_bleu": 0.2971, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0432653427124023, | |
| "eval_runtime": 35.2727, | |
| "eval_samples_per_second": 22.255, | |
| "eval_steps_per_second": 1.418, | |
| "step": 33405 | |
| }, | |
| { | |
| "epoch": 85.24, | |
| "learning_rate": 7.379134860050891e-06, | |
| "loss": 0.1186, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_bleu": 0.2964, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.05250883102417, | |
| "eval_runtime": 35.1615, | |
| "eval_samples_per_second": 22.326, | |
| "eval_steps_per_second": 1.422, | |
| "step": 33798 | |
| }, | |
| { | |
| "epoch": 86.51, | |
| "learning_rate": 6.743002544529263e-06, | |
| "loss": 0.116, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_bleu": 0.2943, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0547308921813965, | |
| "eval_runtime": 35.1782, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.421, | |
| "step": 34191 | |
| }, | |
| { | |
| "epoch": 87.79, | |
| "learning_rate": 6.106870229007634e-06, | |
| "loss": 0.116, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_bleu": 0.2876, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0584968328475952, | |
| "eval_runtime": 35.1038, | |
| "eval_samples_per_second": 22.362, | |
| "eval_steps_per_second": 1.424, | |
| "step": 34584 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_bleu": 0.2904, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0630890130996704, | |
| "eval_runtime": 35.1555, | |
| "eval_samples_per_second": 22.329, | |
| "eval_steps_per_second": 1.422, | |
| "step": 34977 | |
| }, | |
| { | |
| "epoch": 89.06, | |
| "learning_rate": 5.470737913486006e-06, | |
| "loss": 0.1131, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_bleu": 0.2859, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0678483247756958, | |
| "eval_runtime": 35.1133, | |
| "eval_samples_per_second": 22.356, | |
| "eval_steps_per_second": 1.424, | |
| "step": 35370 | |
| }, | |
| { | |
| "epoch": 90.33, | |
| "learning_rate": 4.834605597964377e-06, | |
| "loss": 0.1124, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_bleu": 0.3027, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0763660669326782, | |
| "eval_runtime": 35.192, | |
| "eval_samples_per_second": 22.306, | |
| "eval_steps_per_second": 1.421, | |
| "step": 35763 | |
| }, | |
| { | |
| "epoch": 91.6, | |
| "learning_rate": 4.198473282442748e-06, | |
| "loss": 0.1109, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_bleu": 0.3037, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0759409666061401, | |
| "eval_runtime": 35.1267, | |
| "eval_samples_per_second": 22.348, | |
| "eval_steps_per_second": 1.423, | |
| "step": 36156 | |
| }, | |
| { | |
| "epoch": 92.88, | |
| "learning_rate": 3.56234096692112e-06, | |
| "loss": 0.1097, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_bleu": 0.2962, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.073776364326477, | |
| "eval_runtime": 35.2856, | |
| "eval_samples_per_second": 22.247, | |
| "eval_steps_per_second": 1.417, | |
| "step": 36549 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_bleu": 0.2966, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0854607820510864, | |
| "eval_runtime": 35.1676, | |
| "eval_samples_per_second": 22.322, | |
| "eval_steps_per_second": 1.422, | |
| "step": 36942 | |
| }, | |
| { | |
| "epoch": 94.15, | |
| "learning_rate": 2.9262086513994914e-06, | |
| "loss": 0.1093, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_bleu": 0.2968, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.090211033821106, | |
| "eval_runtime": 35.1673, | |
| "eval_samples_per_second": 22.322, | |
| "eval_steps_per_second": 1.422, | |
| "step": 37335 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 2.2900763358778625e-06, | |
| "loss": 0.1082, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_bleu": 0.2958, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0858522653579712, | |
| "eval_runtime": 35.1286, | |
| "eval_samples_per_second": 22.346, | |
| "eval_steps_per_second": 1.423, | |
| "step": 37728 | |
| }, | |
| { | |
| "epoch": 96.69, | |
| "learning_rate": 1.653944020356234e-06, | |
| "loss": 0.1073, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_bleu": 0.3023, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0867019891738892, | |
| "eval_runtime": 35.1622, | |
| "eval_samples_per_second": 22.325, | |
| "eval_steps_per_second": 1.422, | |
| "step": 38121 | |
| }, | |
| { | |
| "epoch": 97.96, | |
| "learning_rate": 1.0178117048346056e-06, | |
| "loss": 0.1063, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_bleu": 0.3004, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.090205430984497, | |
| "eval_runtime": 35.3454, | |
| "eval_samples_per_second": 22.209, | |
| "eval_steps_per_second": 1.415, | |
| "step": 38514 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_bleu": 0.3018, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0909733772277832, | |
| "eval_runtime": 35.2503, | |
| "eval_samples_per_second": 22.269, | |
| "eval_steps_per_second": 1.418, | |
| "step": 38907 | |
| }, | |
| { | |
| "epoch": 99.24, | |
| "learning_rate": 3.816793893129771e-07, | |
| "loss": 0.1065, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_bleu": 0.3021, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0916588306427002, | |
| "eval_runtime": 35.2577, | |
| "eval_samples_per_second": 22.265, | |
| "eval_steps_per_second": 1.418, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 39300, | |
| "total_flos": 2.232877359218688e+17, | |
| "train_loss": 0.3279189860123108, | |
| "train_runtime": 20714.0027, | |
| "train_samples_per_second": 30.313, | |
| "train_steps_per_second": 1.897 | |
| } | |
| ], | |
| "max_steps": 39300, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.232877359218688e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |