| { | |
| "best_metric": 0.44671384619362653, | |
| "best_model_checkpoint": "experiments/translation/gpt2/2025-06-24_18-36-35/checkpoint-7400", | |
| "epoch": 11.953995157384988, | |
| "global_step": 7400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.999999999999999e-07, | |
| "loss": 6.1827, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.8e-06, | |
| "loss": 5.8477, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.8e-06, | |
| "loss": 5.5128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.7999999999999996e-06, | |
| "loss": 5.2431, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8e-06, | |
| "loss": 5.0236, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.7999999999999995e-06, | |
| "loss": 4.8863, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.8e-06, | |
| "loss": 4.7653, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.799999999999998e-06, | |
| "loss": 4.6745, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.799999999999999e-06, | |
| "loss": 4.653, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.799999999999998e-06, | |
| "loss": 4.5728, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.0799999999999998e-05, | |
| "loss": 4.5315, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.1799999999999999e-05, | |
| "loss": 4.5322, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.2799999999999998e-05, | |
| "loss": 4.4806, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.3799999999999998e-05, | |
| "loss": 4.4899, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.4799999999999999e-05, | |
| "loss": 4.4605, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5799999999999998e-05, | |
| "loss": 4.3978, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.68e-05, | |
| "loss": 4.4461, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.78e-05, | |
| "loss": 4.4205, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.8799999999999996e-05, | |
| "loss": 4.3826, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.98e-05, | |
| "loss": 4.3894, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_bleu": 0.4978012676278285, | |
| "eval_bleurt": 0.25222029421664777, | |
| "eval_loss": 4.304965496063232, | |
| "eval_runtime": 985.9715, | |
| "eval_samples_per_second": 4.057, | |
| "eval_steps_per_second": 0.064, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.0799999999999997e-05, | |
| "loss": 4.338, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.1799999999999998e-05, | |
| "loss": 4.3711, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.28e-05, | |
| "loss": 4.3446, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.38e-05, | |
| "loss": 4.3136, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.4799999999999996e-05, | |
| "loss": 4.3436, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.5799999999999997e-05, | |
| "loss": 4.3273, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.6799999999999998e-05, | |
| "loss": 4.3118, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7799999999999995e-05, | |
| "loss": 4.3052, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.88e-05, | |
| "loss": 4.2786, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.9799999999999996e-05, | |
| "loss": 4.26, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3.0799999999999996e-05, | |
| "loss": 4.2972, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.1799999999999994e-05, | |
| "loss": 4.2897, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.28e-05, | |
| "loss": 4.2758, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 3.3799999999999995e-05, | |
| "loss": 4.2753, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.48e-05, | |
| "loss": 4.2768, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.5799999999999996e-05, | |
| "loss": 4.2505, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.679999999999999e-05, | |
| "loss": 4.2614, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.78e-05, | |
| "loss": 4.2568, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.8799999999999994e-05, | |
| "loss": 4.2386, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.979999999999999e-05, | |
| "loss": 4.2741, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_bleu": 0.41623180688588896, | |
| "eval_bleurt": 0.2724794183280319, | |
| "eval_loss": 4.168415546417236, | |
| "eval_runtime": 976.9806, | |
| "eval_samples_per_second": 4.094, | |
| "eval_steps_per_second": 0.064, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.08e-05, | |
| "loss": 4.2711, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.18e-05, | |
| "loss": 4.2302, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.28e-05, | |
| "loss": 4.2196, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.3799999999999994e-05, | |
| "loss": 4.2314, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.48e-05, | |
| "loss": 4.2069, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.5799999999999995e-05, | |
| "loss": 4.2079, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.68e-05, | |
| "loss": 4.189, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.7799999999999996e-05, | |
| "loss": 4.2196, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.8799999999999994e-05, | |
| "loss": 4.2139, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.98e-05, | |
| "loss": 4.2134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.0799999999999995e-05, | |
| "loss": 4.1555, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 5.179999999999999e-05, | |
| "loss": 4.2139, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 5.279999999999999e-05, | |
| "loss": 4.1577, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.38e-05, | |
| "loss": 4.1864, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.48e-05, | |
| "loss": 4.1894, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.5799999999999994e-05, | |
| "loss": 4.1648, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 5.679999999999999e-05, | |
| "loss": 4.1884, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.78e-05, | |
| "loss": 4.1524, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.88e-05, | |
| "loss": 4.173, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.98e-05, | |
| "loss": 4.1383, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_bleu": 0.2691580561538693, | |
| "eval_bleurt": 0.3023578838519752, | |
| "eval_loss": 4.099766731262207, | |
| "eval_runtime": 980.3466, | |
| "eval_samples_per_second": 4.08, | |
| "eval_steps_per_second": 0.064, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.0799999999999994e-05, | |
| "loss": 4.1821, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.18e-05, | |
| "loss": 4.3941, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 6.28e-05, | |
| "loss": 4.1189, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.379999999999999e-05, | |
| "loss": 4.1068, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 6.479999999999999e-05, | |
| "loss": 4.1002, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 6.579999999999999e-05, | |
| "loss": 4.0847, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 6.68e-05, | |
| "loss": 4.0823, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 6.78e-05, | |
| "loss": 4.094, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 6.879999999999999e-05, | |
| "loss": 4.0738, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.979999999999999e-05, | |
| "loss": 4.0843, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.079999999999999e-05, | |
| "loss": 4.0835, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.18e-05, | |
| "loss": 4.0978, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 7.28e-05, | |
| "loss": 4.0779, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.379999999999999e-05, | |
| "loss": 4.048, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.479999999999999e-05, | |
| "loss": 4.0945, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.579999999999999e-05, | |
| "loss": 4.0498, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 7.68e-05, | |
| "loss": 4.081, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 7.780000000000001e-05, | |
| "loss": 4.0902, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.879999999999999e-05, | |
| "loss": 4.0846, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 7.98e-05, | |
| "loss": 4.0628, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_bleu": 0.3705309283554325, | |
| "eval_bleurt": 0.31487692370265724, | |
| "eval_loss": 4.0382981300354, | |
| "eval_runtime": 975.0846, | |
| "eval_samples_per_second": 4.102, | |
| "eval_steps_per_second": 0.065, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.079999999999999e-05, | |
| "loss": 4.0582, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.18e-05, | |
| "loss": 4.0702, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.28e-05, | |
| "loss": 4.0612, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.379999999999999e-05, | |
| "loss": 4.0377, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.48e-05, | |
| "loss": 4.0136, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.579999999999998e-05, | |
| "loss": 4.0391, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.68e-05, | |
| "loss": 4.0161, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.779999999999999e-05, | |
| "loss": 4.0438, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.879999999999999e-05, | |
| "loss": 4.0749, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.98e-05, | |
| "loss": 4.0301, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.079999999999998e-05, | |
| "loss": 4.0454, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.18e-05, | |
| "loss": 4.0165, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.279999999999999e-05, | |
| "loss": 3.9955, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.379999999999999e-05, | |
| "loss": 4.0553, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.479999999999999e-05, | |
| "loss": 4.0186, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.58e-05, | |
| "loss": 4.0187, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.68e-05, | |
| "loss": 4.0468, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.779999999999999e-05, | |
| "loss": 3.9958, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.879999999999999e-05, | |
| "loss": 4.0063, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.979999999999999e-05, | |
| "loss": 3.9868, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_bleu": 0.45829142374176884, | |
| "eval_bleurt": 0.315635218815878, | |
| "eval_loss": 3.9850990772247314, | |
| "eval_runtime": 985.8564, | |
| "eval_samples_per_second": 4.057, | |
| "eval_steps_per_second": 0.064, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0001008, | |
| "loss": 3.9981, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00010179999999999998, | |
| "loss": 4.0142, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00010279999999999999, | |
| "loss": 4.0149, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00010379999999999999, | |
| "loss": 3.9596, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00010479999999999999, | |
| "loss": 3.9942, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001058, | |
| "loss": 3.9804, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00010679999999999998, | |
| "loss": 4.0112, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00010779999999999999, | |
| "loss": 3.9548, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001088, | |
| "loss": 3.9624, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00010979999999999999, | |
| "loss": 3.9833, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001108, | |
| "loss": 3.9872, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011179999999999998, | |
| "loss": 3.9713, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011279999999999999, | |
| "loss": 3.9536, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0001138, | |
| "loss": 3.9762, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011479999999999999, | |
| "loss": 3.9524, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0001158, | |
| "loss": 3.9227, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011679999999999998, | |
| "loss": 3.9524, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00011779999999999999, | |
| "loss": 3.9181, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001188, | |
| "loss": 3.931, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00011979999999999998, | |
| "loss": 3.9334, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_bleu": 0.7031077115785501, | |
| "eval_bleurt": 0.3057404997814447, | |
| "eval_loss": 3.913109302520752, | |
| "eval_runtime": 975.8613, | |
| "eval_samples_per_second": 4.099, | |
| "eval_steps_per_second": 0.065, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001208, | |
| "loss": 3.9211, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00012179999999999999, | |
| "loss": 3.9324, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00012279999999999998, | |
| "loss": 3.9113, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001238, | |
| "loss": 4.0941, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00012479999999999997, | |
| "loss": 3.8044, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0001258, | |
| "loss": 3.8685, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0001268, | |
| "loss": 3.7951, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001278, | |
| "loss": 3.8221, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0001288, | |
| "loss": 3.7975, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00012979999999999998, | |
| "loss": 3.801, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00013079999999999998, | |
| "loss": 3.7766, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0001318, | |
| "loss": 3.7944, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00013279999999999998, | |
| "loss": 3.831, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0001338, | |
| "loss": 3.7952, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00013479999999999997, | |
| "loss": 3.7929, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0001358, | |
| "loss": 3.7581, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001368, | |
| "loss": 3.7673, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0001378, | |
| "loss": 3.7628, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00013879999999999999, | |
| "loss": 3.7511, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00013979999999999998, | |
| "loss": 3.7965, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_bleu": 1.1117915555050346, | |
| "eval_bleurt": 0.30961248799785973, | |
| "eval_loss": 3.8422813415527344, | |
| "eval_runtime": 973.4187, | |
| "eval_samples_per_second": 4.109, | |
| "eval_steps_per_second": 0.065, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00014079999999999998, | |
| "loss": 3.7991, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0001418, | |
| "loss": 3.8, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00014279999999999997, | |
| "loss": 3.7766, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0001438, | |
| "loss": 3.7685, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0001448, | |
| "loss": 3.774, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0001458, | |
| "loss": 3.9565, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0001468, | |
| "loss": 3.7653, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0001478, | |
| "loss": 3.7319, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00014879999999999998, | |
| "loss": 3.7391, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00014979999999999998, | |
| "loss": 3.7441, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00014999997083773588, | |
| "loss": 3.7438, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00014999985236607678, | |
| "loss": 3.7331, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.000149999642762525, | |
| "loss": 3.7211, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0001499993420273353, | |
| "loss": 3.7327, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00014999895016087306, | |
| "loss": 3.7518, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00014999846716361444, | |
| "loss": 3.7189, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0001499978930361463, | |
| "loss": 3.7295, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0001499972277791663, | |
| "loss": 3.6779, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00014999647139348274, | |
| "loss": 3.6388, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00014999562388001478, | |
| "loss": 3.683, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_bleu": 1.3372050519655347, | |
| "eval_bleurt": 0.3216691560912877, | |
| "eval_loss": 3.7514681816101074, | |
| "eval_runtime": 973.4105, | |
| "eval_samples_per_second": 4.109, | |
| "eval_steps_per_second": 0.065, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00014999468523979213, | |
| "loss": 3.7066, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.00014999365547395543, | |
| "loss": 3.6872, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00014999253458375584, | |
| "loss": 3.7027, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00014999132257055543, | |
| "loss": 3.6529, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00014999001943582685, | |
| "loss": 3.662, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00014998862518115358, | |
| "loss": 3.6612, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00014998713980822974, | |
| "loss": 3.6537, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00014998556331886022, | |
| "loss": 3.6965, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00014998389571496058, | |
| "loss": 3.6506, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0001499821369985571, | |
| "loss": 3.6662, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00014998028717178686, | |
| "loss": 3.6689, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00014997834623689752, | |
| "loss": 3.6542, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.00014997631419624749, | |
| "loss": 3.6219, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0001499741910523059, | |
| "loss": 3.6036, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0001499719768076526, | |
| "loss": 3.6413, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00014996967146497806, | |
| "loss": 3.6195, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00014996727502708353, | |
| "loss": 3.6221, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0001499647874968809, | |
| "loss": 3.6038, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00014996220887739272, | |
| "loss": 3.5995, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00014995953917175227, | |
| "loss": 3.5672, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_bleu": 1.7016998676800545, | |
| "eval_bleurt": 0.33596263419650496, | |
| "eval_loss": 3.639861822128296, | |
| "eval_runtime": 973.5052, | |
| "eval_samples_per_second": 4.109, | |
| "eval_steps_per_second": 0.065, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0001499567783832035, | |
| "loss": 3.5941, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00014995392651510108, | |
| "loss": 3.5989, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00014995098357091022, | |
| "loss": 3.5707, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0001499479495542069, | |
| "loss": 3.5822, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00014994482446867774, | |
| "loss": 3.588, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00014994160831812003, | |
| "loss": 3.6809, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0001499383011064417, | |
| "loss": 3.3547, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00014993490283766127, | |
| "loss": 3.3765, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00014993141351590802, | |
| "loss": 3.3772, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00014992783314542174, | |
| "loss": 3.3585, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00014992416173055298, | |
| "loss": 3.3382, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00014992039927576284, | |
| "loss": 3.3746, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00014991654578562304, | |
| "loss": 3.3587, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00014991260126481591, | |
| "loss": 3.3368, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.00014990856571813448, | |
| "loss": 3.3704, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00014990443915048228, | |
| "loss": 3.3363, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00014990022156687348, | |
| "loss": 3.3463, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.00014989591297243286, | |
| "loss": 3.3616, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00014989151337239576, | |
| "loss": 3.34, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0001498870227721081, | |
| "loss": 3.3528, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_bleu": 2.324004828313231, | |
| "eval_bleurt": 0.3465996809080243, | |
| "eval_loss": 3.570871591567993, | |
| "eval_runtime": 975.2211, | |
| "eval_samples_per_second": 4.102, | |
| "eval_steps_per_second": 0.065, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00014988244117702636, | |
| "loss": 3.3445, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00014987776859271766, | |
| "loss": 3.2984, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0001498730050248596, | |
| "loss": 3.3172, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.00014986815047924036, | |
| "loss": 3.3333, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0001498632049617587, | |
| "loss": 3.3316, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00014985816847842387, | |
| "loss": 3.3145, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00014985304103535567, | |
| "loss": 3.314, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00014984782263878445, | |
| "loss": 3.3156, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.00014984251329505101, | |
| "loss": 3.33, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00014983711301060673, | |
| "loss": 3.3131, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.0001498316217920135, | |
| "loss": 3.3288, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00014982603964594358, | |
| "loss": 3.2838, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00014982036657917988, | |
| "loss": 3.3158, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.00014981460259861569, | |
| "loss": 3.271, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.00014980874771125478, | |
| "loss": 3.3109, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0001498028019242114, | |
| "loss": 3.3174, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.00014979676524471024, | |
| "loss": 3.2812, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.00014979063768008643, | |
| "loss": 3.2889, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00014978441923778555, | |
| "loss": 3.3029, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.00014977810992536359, | |
| "loss": 3.2995, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_bleu": 2.843719979357009, | |
| "eval_bleurt": 0.35801208051294087, | |
| "eval_loss": 3.4631431102752686, | |
| "eval_runtime": 974.5479, | |
| "eval_samples_per_second": 4.104, | |
| "eval_steps_per_second": 0.065, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00014977170975048694, | |
| "loss": 3.2609, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 0.00014976521872093242, | |
| "loss": 3.2713, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00014975863684458726, | |
| "loss": 3.2561, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.00014975196412944907, | |
| "loss": 3.2654, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.00014974520058362584, | |
| "loss": 3.2732, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.00014973834621533584, | |
| "loss": 3.2687, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00014973140103290784, | |
| "loss": 3.2866, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00014972436504478087, | |
| "loss": 3.2492, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.00014971723825950433, | |
| "loss": 3.2633, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.00014971002068573793, | |
| "loss": 3.2531, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 0.00014970271233225168, | |
| "loss": 3.248, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.000149695313207926, | |
| "loss": 3.2396, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0001496878233217514, | |
| "loss": 3.229, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.0001496802426828289, | |
| "loss": 3.2151, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.00014967257130036961, | |
| "loss": 3.2081, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00014966480918369507, | |
| "loss": 3.2511, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00014965695634223692, | |
| "loss": 3.2105, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00014964901278553716, | |
| "loss": 3.2414, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.00014964097852324787, | |
| "loss": 3.2115, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.00014963285356513152, | |
| "loss": 3.2494, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_bleu": 3.629290156339251, | |
| "eval_bleurt": 0.35963968054391443, | |
| "eval_loss": 3.3864657878875732, | |
| "eval_runtime": 972.8839, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.065, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00014962463792106065, | |
| "loss": 3.2026, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.0001496163316010181, | |
| "loss": 3.2222, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.00014960793461509675, | |
| "loss": 3.2009, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 0.0001495994469734998, | |
| "loss": 3.2133, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.0001495908686865405, | |
| "loss": 3.1797, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.0001495821997646423, | |
| "loss": 3.1938, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00014957344021833874, | |
| "loss": 3.1787, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.00014956459005827346, | |
| "loss": 3.2641, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00014955564929520034, | |
| "loss": 2.9646, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.00014954661793998317, | |
| "loss": 2.9512, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00014953749600359588, | |
| "loss": 2.9664, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00014952828349712254, | |
| "loss": 2.9758, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0001495189804317572, | |
| "loss": 2.9683, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00014950958681880395, | |
| "loss": 2.9445, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0001495001026696769, | |
| "loss": 2.9855, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00014949052799590024, | |
| "loss": 2.952, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.00014948086280910808, | |
| "loss": 2.9404, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.0001494711071210445, | |
| "loss": 2.925, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 0.0001494612609435636, | |
| "loss": 2.9594, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.00014945132428862936, | |
| "loss": 2.9511, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_bleu": 3.8696422984480376, | |
| "eval_bleurt": 0.3656712284106761, | |
| "eval_loss": 3.357984781265259, | |
| "eval_runtime": 974.0738, | |
| "eval_samples_per_second": 4.106, | |
| "eval_steps_per_second": 0.065, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00014944129716831588, | |
| "loss": 2.9487, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00014943117959480696, | |
| "loss": 2.9551, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00014942097158039645, | |
| "loss": 2.9885, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.000149410673137488, | |
| "loss": 2.9543, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.00014940028427859524, | |
| "loss": 2.9694, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00014938980501634158, | |
| "loss": 2.9729, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.00014937923536346032, | |
| "loss": 2.9461, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.00014936857533279463, | |
| "loss": 2.9617, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00014935782493729737, | |
| "loss": 2.9618, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00014934698419003133, | |
| "loss": 2.955, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00014933605310416906, | |
| "loss": 2.9598, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00014932503169299283, | |
| "loss": 2.953, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00014931391996989468, | |
| "loss": 2.9242, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.00014930271794837642, | |
| "loss": 2.9458, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.0001492914256420496, | |
| "loss": 2.9466, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.00014928004306463536, | |
| "loss": 2.9532, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.00014926857022996468, | |
| "loss": 2.9421, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.0001492570071519781, | |
| "loss": 2.9545, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.00014924535384472582, | |
| "loss": 2.9113, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.00014923361032236776, | |
| "loss": 2.9841, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_bleu": 4.516098361522591, | |
| "eval_bleurt": 0.37371724391914907, | |
| "eval_loss": 3.3018534183502197, | |
| "eval_runtime": 979.3156, | |
| "eval_samples_per_second": 4.084, | |
| "eval_steps_per_second": 0.064, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0001492217765991734, | |
| "loss": 2.9434, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.0001492098526895218, | |
| "loss": 2.9052, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00014919783860790166, | |
| "loss": 2.9328, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.0001491857343689112, | |
| "loss": 2.947, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.00014917353998725823, | |
| "loss": 2.9522, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00014916125547776007, | |
| "loss": 2.9088, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 0.00014914888085534354, | |
| "loss": 2.927, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.000149136416135045, | |
| "loss": 2.916, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.00014912386133201025, | |
| "loss": 2.9224, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00014911121646149456, | |
| "loss": 2.8846, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00014909848153886262, | |
| "loss": 2.9291, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.00014908565657958858, | |
| "loss": 2.9645, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.000149072741599256, | |
| "loss": 2.9107, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.00014905973661355777, | |
| "loss": 2.9181, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00014904664163829616, | |
| "loss": 2.9413, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0001490334566893828, | |
| "loss": 2.9004, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.0001490201817828387, | |
| "loss": 2.8892, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0001490068169347941, | |
| "loss": 2.9178, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.0001489933621614885, | |
| "loss": 2.8924, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.00014897981747927076, | |
| "loss": 2.9527, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_bleu": 4.595275746272008, | |
| "eval_bleurt": 0.38483347702398896, | |
| "eval_loss": 3.2277393341064453, | |
| "eval_runtime": 973.0066, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.065, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00014896618290459896, | |
| "loss": 2.9305, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.00014895245845404038, | |
| "loss": 2.8754, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.00014893864414427152, | |
| "loss": 2.9048, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.00014892473999207802, | |
| "loss": 2.8932, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.00014891074601435482, | |
| "loss": 2.8929, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.00014889666222810588, | |
| "loss": 2.9149, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.00014888248865044433, | |
| "loss": 2.8701, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.00014886822529859242, | |
| "loss": 2.9022, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001488538721898814, | |
| "loss": 2.8979, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.00014883942934175177, | |
| "loss": 2.946, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00014882489677175287, | |
| "loss": 2.6491, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.00014881027449754314, | |
| "loss": 2.6475, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.00014879556253689005, | |
| "loss": 2.6836, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00014878076090767, | |
| "loss": 2.6515, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.0001487658696278684, | |
| "loss": 2.643, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.00014875088871557952, | |
| "loss": 2.6363, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00014873581818900658, | |
| "loss": 2.673, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00014872065806646173, | |
| "loss": 2.6567, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.00014870540836636593, | |
| "loss": 2.63, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.000148690069107249, | |
| "loss": 2.6687, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_bleu": 5.0632623182222956, | |
| "eval_bleurt": 0.3909575751256198, | |
| "eval_loss": 3.23783540725708, | |
| "eval_runtime": 979.0539, | |
| "eval_samples_per_second": 4.086, | |
| "eval_steps_per_second": 0.064, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 0.00014867464030774954, | |
| "loss": 2.6821, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.0001486591219866151, | |
| "loss": 2.6898, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00014864351416270181, | |
| "loss": 2.645, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 0.0001486278168549747, | |
| "loss": 2.6523, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 0.00014861203008250745, | |
| "loss": 2.6635, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00014859615386448251, | |
| "loss": 2.6478, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00014858018822019094, | |
| "loss": 2.6449, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.0001485641331690325, | |
| "loss": 2.6811, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.00014854798873051566, | |
| "loss": 2.6612, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.0001485317549242574, | |
| "loss": 2.6623, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.00014851543176998326, | |
| "loss": 2.6681, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 0.00014849901928752748, | |
| "loss": 2.6443, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00014848251749683279, | |
| "loss": 2.6783, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.00014846592641795038, | |
| "loss": 2.6868, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.00014844924607104, | |
| "loss": 2.6652, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00014843247647636983, | |
| "loss": 2.6485, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 0.0001484156176543165, | |
| "loss": 2.6946, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 0.00014839866962536508, | |
| "loss": 2.6529, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.000148381632410109, | |
| "loss": 2.6616, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.00014836450602925014, | |
| "loss": 2.6495, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_bleu": 4.892552740289103, | |
| "eval_bleurt": 0.3955645103491843, | |
| "eval_loss": 3.1738545894622803, | |
| "eval_runtime": 997.9581, | |
| "eval_samples_per_second": 4.008, | |
| "eval_steps_per_second": 0.063, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.00014834729050359862, | |
| "loss": 2.6531, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 0.00014832998585407293, | |
| "loss": 2.6569, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0001483125921016999, | |
| "loss": 2.664, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0001482951092676145, | |
| "loss": 2.6509, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.00014827753737306008, | |
| "loss": 2.6672, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0001482598764393881, | |
| "loss": 2.6799, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.00014824212648805834, | |
| "loss": 2.673, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.0001482242875406386, | |
| "loss": 2.6853, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 0.0001482063596188049, | |
| "loss": 2.6681, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00014818834274434134, | |
| "loss": 2.6331, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00014817023693914014, | |
| "loss": 2.6973, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.00014815204222520158, | |
| "loss": 2.6435, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0001481337586246339, | |
| "loss": 2.6473, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 0.00014811538615965342, | |
| "loss": 2.6543, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.00014809692485258445, | |
| "loss": 2.6697, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0001480783747258592, | |
| "loss": 2.6473, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.0001480597358020178, | |
| "loss": 2.6654, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.0001480410081037083, | |
| "loss": 2.6614, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.00014802219165368667, | |
| "loss": 2.6079, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00014800328647481662, | |
| "loss": 2.6533, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_bleu": 6.190685639130476, | |
| "eval_bleurt": 0.40516115503571926, | |
| "eval_loss": 3.1166458129882812, | |
| "eval_runtime": 994.5986, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.063, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 0.00014798429259006978, | |
| "loss": 2.6406, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.00014796521002252542, | |
| "loss": 2.6293, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00014794603879537076, | |
| "loss": 2.6464, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.00014792677893190058, | |
| "loss": 2.6529, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.00014790743045551744, | |
| "loss": 2.6477, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.0001478879933897316, | |
| "loss": 2.6709, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.00014786846775816087, | |
| "loss": 2.6516, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 0.00014784885358453081, | |
| "loss": 2.6554, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.0001478291508926744, | |
| "loss": 2.6739, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 0.00014780935970653235, | |
| "loss": 2.6432, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.00014778948005015276, | |
| "loss": 2.6281, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.0001477695119476913, | |
| "loss": 2.6511, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00014774945542341114, | |
| "loss": 2.3883, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.0001477293105016828, | |
| "loss": 2.4194, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.00014770907720698426, | |
| "loss": 2.4187, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00014768875556390093, | |
| "loss": 2.4215, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 0.00014766834559712546, | |
| "loss": 2.4223, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.00014764784733145792, | |
| "loss": 2.3996, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00014762726079180563, | |
| "loss": 2.4129, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00014760658600318318, | |
| "loss": 2.4071, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_bleu": 5.876536541986637, | |
| "eval_bleurt": 0.4050812121555209, | |
| "eval_loss": 3.162557601928711, | |
| "eval_runtime": 982.2873, | |
| "eval_samples_per_second": 4.072, | |
| "eval_steps_per_second": 0.064, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00014758582299071235, | |
| "loss": 2.4225, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.00014756497177962222, | |
| "loss": 2.4042, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00014754403239524897, | |
| "loss": 2.4277, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.00014752300486303585, | |
| "loss": 2.4478, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00014750188920853338, | |
| "loss": 2.4531, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.00014748068545739903, | |
| "loss": 2.4184, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00014745939363539737, | |
| "loss": 2.4173, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 0.0001474380137684, | |
| "loss": 2.4386, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.0001474165458823854, | |
| "loss": 2.4393, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.00014739499000343914, | |
| "loss": 2.4412, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 0.00014737334615775362, | |
| "loss": 2.4136, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00014735161437162816, | |
| "loss": 2.4358, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00014732979467146893, | |
| "loss": 2.4191, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.0001473078870837889, | |
| "loss": 2.4262, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.0001472858916352079, | |
| "loss": 2.44, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00014726380835245243, | |
| "loss": 2.462, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00014724163726235578, | |
| "loss": 2.4067, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 0.00014721937839185791, | |
| "loss": 2.4648, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00014719703176800547, | |
| "loss": 2.4547, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.0001471745974179517, | |
| "loss": 2.4387, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "eval_bleu": 6.622754630611525, | |
| "eval_bleurt": 0.40961993131786584, | |
| "eval_loss": 3.1284425258636475, | |
| "eval_runtime": 973.8224, | |
| "eval_samples_per_second": 4.108, | |
| "eval_steps_per_second": 0.065, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 0.0001471520753689564, | |
| "loss": 2.4268, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 0.0001471294656483861, | |
| "loss": 2.4568, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00014710676828371362, | |
| "loss": 2.4506, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00014708398330251848, | |
| "loss": 2.4675, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.00014706111073248656, | |
| "loss": 2.4454, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.00014703815060141014, | |
| "loss": 2.4341, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00014701510293718803, | |
| "loss": 2.4394, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00014699196776782523, | |
| "loss": 2.4492, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.00014696874512143323, | |
| "loss": 2.446, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.0001469454350262297, | |
| "loss": 2.4559, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.00014692203751053855, | |
| "loss": 2.4478, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 0.00014689855260279007, | |
| "loss": 2.4557, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00014687498033152054, | |
| "loss": 2.4556, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.0001468513207253726, | |
| "loss": 2.4359, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.0001468275738130948, | |
| "loss": 2.427, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00014680373962354195, | |
| "loss": 2.4291, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.00014677981818567477, | |
| "loss": 2.4386, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 0.0001467558095285601, | |
| "loss": 2.4408, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.00014673171368137074, | |
| "loss": 2.453, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.0001467075306733854, | |
| "loss": 2.431, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "eval_bleu": 6.619837351945097, | |
| "eval_bleurt": 0.41852131807245313, | |
| "eval_loss": 3.067232370376587, | |
| "eval_runtime": 988.698, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.064, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 0.00014668326053398872, | |
| "loss": 2.4524, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.00014665890329267122, | |
| "loss": 2.4271, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00014663445897902916, | |
| "loss": 2.4284, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 0.0001466099276227648, | |
| "loss": 2.4613, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 0.000146585309253686, | |
| "loss": 2.4438, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.0001465606039017064, | |
| "loss": 2.4523, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 0.00014653581159684533, | |
| "loss": 2.4341, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.0001465109323692278, | |
| "loss": 2.4255, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.00014648596624908437, | |
| "loss": 2.4456, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00014646091326675126, | |
| "loss": 2.4471, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.00014643577345267025, | |
| "loss": 2.4464, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00014641054683738852, | |
| "loss": 2.4339, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0001463852334515588, | |
| "loss": 2.4211, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.00014635983332593924, | |
| "loss": 2.4022, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 0.00014633434649139344, | |
| "loss": 2.2079, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.0001463087729788902, | |
| "loss": 2.2292, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 0.00014628311281950386, | |
| "loss": 2.1971, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00014625736604441386, | |
| "loss": 2.188, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 0.000146231532684905, | |
| "loss": 2.223, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00014620561277236722, | |
| "loss": 2.2341, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_bleu": 6.801109458210314, | |
| "eval_bleurt": 0.42029437783174217, | |
| "eval_loss": 3.0993056297302246, | |
| "eval_runtime": 975.3529, | |
| "eval_samples_per_second": 4.101, | |
| "eval_steps_per_second": 0.065, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 0.00014617960633829568, | |
| "loss": 2.2328, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00014615351341429065, | |
| "loss": 2.2123, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.00014612733403205749, | |
| "loss": 2.2153, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 0.00014610106822340657, | |
| "loss": 2.2195, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.0001460747160202534, | |
| "loss": 2.2335, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00014604827745461836, | |
| "loss": 2.222, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.00014602175255862677, | |
| "loss": 2.2133, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 0.00014599514136450894, | |
| "loss": 2.2203, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 0.00014596844390459994, | |
| "loss": 2.243, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 0.0001459416602113397, | |
| "loss": 2.2617, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 0.00014591479031727294, | |
| "loss": 2.2613, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.0001458878342550491, | |
| "loss": 2.2351, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.0001458607920574224, | |
| "loss": 2.2523, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00014583366375725158, | |
| "loss": 2.2117, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00014580644938750012, | |
| "loss": 2.2542, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00014577914898123605, | |
| "loss": 2.2678, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 0.00014575176257163193, | |
| "loss": 2.2625, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 0.00014572429019196482, | |
| "loss": 2.2156, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.00014569673187561627, | |
| "loss": 2.2596, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 0.00014566908765607222, | |
| "loss": 2.2364, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "eval_bleu": 7.542120151202923, | |
| "eval_bleurt": 0.421341299476102, | |
| "eval_loss": 3.086074113845825, | |
| "eval_runtime": 986.6994, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.064, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.00014564135756692302, | |
| "loss": 2.2605, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 0.0001456135416418633, | |
| "loss": 2.2352, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.00014558563991469211, | |
| "loss": 2.2393, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.0001455576524193126, | |
| "loss": 2.2243, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.00014552957918973226, | |
| "loss": 2.2561, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0001455014202600627, | |
| "loss": 2.2831, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.00014547317566451968, | |
| "loss": 2.2467, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.00014544484543742303, | |
| "loss": 2.2425, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00014541642961319665, | |
| "loss": 2.2652, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 0.00014538792822636849, | |
| "loss": 2.2718, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 0.00014535934131157036, | |
| "loss": 2.2343, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 0.00014533066890353805, | |
| "loss": 2.2848, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.00014530191103711133, | |
| "loss": 2.2551, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 0.00014527306774723365, | |
| "loss": 2.2559, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.00014524413906895234, | |
| "loss": 2.2463, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00014521512503741846, | |
| "loss": 2.2319, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 0.0001451860256878868, | |
| "loss": 2.2562, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 0.00014515684105571584, | |
| "loss": 2.2652, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.00014512757117636762, | |
| "loss": 2.2638, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 0.00014509821608540784, | |
| "loss": 2.2732, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "eval_bleu": 7.531221731904556, | |
| "eval_bleurt": 0.42558850402757525, | |
| "eval_loss": 3.055649757385254, | |
| "eval_runtime": 979.7402, | |
| "eval_samples_per_second": 4.083, | |
| "eval_steps_per_second": 0.064, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 0.00014506877581850567, | |
| "loss": 2.2475, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.00014503925041143382, | |
| "loss": 2.2729, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0001450096399000685, | |
| "loss": 2.2805, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 0.00014497994432038916, | |
| "loss": 2.2483, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 0.00014495016370847882, | |
| "loss": 2.2538, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.00014492029810052372, | |
| "loss": 2.2674, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 0.00014489034753281335, | |
| "loss": 2.2641, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.0001448603120417405, | |
| "loss": 2.2616, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.00014483019166380116, | |
| "loss": 2.2772, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 0.00014479998643559435, | |
| "loss": 2.2605, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.00014476969639382232, | |
| "loss": 2.2729, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.00014473932157529033, | |
| "loss": 2.2705, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.00014470886201690662, | |
| "loss": 2.2604, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.00014467831775568247, | |
| "loss": 2.2691, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00014464768882873198, | |
| "loss": 2.2545, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.00014461697527327222, | |
| "loss": 2.1906, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.0001445861771266231, | |
| "loss": 2.0166, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.00014455529442620717, | |
| "loss": 2.0251, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.00014452432720954986, | |
| "loss": 2.0404, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.00014449327551427935, | |
| "loss": 2.0369, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_bleu": 7.48166748140297, | |
| "eval_bleurt": 0.4288165750000626, | |
| "eval_loss": 3.1147143840789795, | |
| "eval_runtime": 986.7228, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.064, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 0.00014446213937812624, | |
| "loss": 2.0265, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 0.00014443091883892394, | |
| "loss": 2.0392, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 0.00014439961393460836, | |
| "loss": 2.0623, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 0.0001443682247032179, | |
| "loss": 2.0593, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 0.0001443367511828934, | |
| "loss": 2.0782, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.00014430519341187818, | |
| "loss": 2.0431, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00014427355142851797, | |
| "loss": 2.0692, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 0.00014424182527126065, | |
| "loss": 2.0822, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 0.00014421001497865658, | |
| "loss": 2.0459, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 0.0001441781205893582, | |
| "loss": 2.0637, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 0.00014414614214212026, | |
| "loss": 2.0726, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 0.00014411407967579955, | |
| "loss": 2.0598, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 0.00014408193322935502, | |
| "loss": 2.0743, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 0.0001440497028418476, | |
| "loss": 2.0621, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 0.00014401738855244028, | |
| "loss": 2.0569, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 0.00014398499040039792, | |
| "loss": 2.0823, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 0.0001439525084250874, | |
| "loss": 2.0959, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 0.00014391994266597732, | |
| "loss": 2.0705, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.0001438872931626382, | |
| "loss": 2.0725, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.00014385455995474222, | |
| "loss": 2.0743, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_bleu": 8.061471983214835, | |
| "eval_bleurt": 0.4274405341036618, | |
| "eval_loss": 3.1063921451568604, | |
| "eval_runtime": 976.3437, | |
| "eval_samples_per_second": 4.097, | |
| "eval_steps_per_second": 0.065, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 0.00014382174308206333, | |
| "loss": 2.0572, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 0.00014378884258447715, | |
| "loss": 2.0725, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00014375585850196087, | |
| "loss": 2.0842, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 0.00014372279087459324, | |
| "loss": 2.0655, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 0.00014368963974255454, | |
| "loss": 2.1023, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.00014365640514612656, | |
| "loss": 2.0718, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 0.00014362308712569246, | |
| "loss": 2.104, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00014358968572173678, | |
| "loss": 2.0984, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.00014355620097484533, | |
| "loss": 2.087, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 0.0001435226329257053, | |
| "loss": 2.1192, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.000143488981615105, | |
| "loss": 2.087, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 0.00014345524708393392, | |
| "loss": 2.105, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 0.00014342142937318276, | |
| "loss": 2.1026, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 0.00014338752852394317, | |
| "loss": 2.0855, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 0.00014335354457740792, | |
| "loss": 2.0913, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00014331947757487067, | |
| "loss": 2.1072, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 0.00014328532755772608, | |
| "loss": 2.0985, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 0.0001432510945674696, | |
| "loss": 2.1019, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.00014321677864569755, | |
| "loss": 2.1216, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 0.00014318237983410706, | |
| "loss": 2.0877, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "eval_bleu": 8.141808712728512, | |
| "eval_bleurt": 0.43287834226712585, | |
| "eval_loss": 3.0626797676086426, | |
| "eval_runtime": 987.842, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.064, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 0.00014314789817449587, | |
| "loss": 2.1074, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.0001431133337087625, | |
| "loss": 2.0994, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.00014307868647890596, | |
| "loss": 2.1078, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 0.000143043956527026, | |
| "loss": 2.0952, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 0.0001430091438953227, | |
| "loss": 2.1066, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.00014297424862609674, | |
| "loss": 2.1042, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 0.00014293927076174912, | |
| "loss": 2.1565, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 0.0001429042103447813, | |
| "loss": 2.1239, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.00014286906741779493, | |
| "loss": 2.1004, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.00014283384202349203, | |
| "loss": 2.1134, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 0.00014279853420467477, | |
| "loss": 2.119, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.00014276314400424545, | |
| "loss": 2.1223, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 0.00014272767146520653, | |
| "loss": 2.0873, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.00014269211663066046, | |
| "loss": 2.1068, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 0.00014265647954380976, | |
| "loss": 2.113, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0001426207602479568, | |
| "loss": 2.1283, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.00014258495878650393, | |
| "loss": 2.1295, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 0.0001425490752029533, | |
| "loss": 2.0191, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.00014251310954090682, | |
| "loss": 1.859, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.00014247706184406618, | |
| "loss": 1.8832, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_bleu": 7.942274913486059, | |
| "eval_bleurt": 0.4308631960172206, | |
| "eval_loss": 3.127479076385498, | |
| "eval_runtime": 986.9497, | |
| "eval_samples_per_second": 4.053, | |
| "eval_steps_per_second": 0.064, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 0.00014244093215623273, | |
| "loss": 1.8994, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 0.00014240472052130744, | |
| "loss": 1.8574, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 0.00014236842698329088, | |
| "loss": 1.8903, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 0.0001423320515862831, | |
| "loss": 1.8873, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 0.00014229559437448362, | |
| "loss": 1.8739, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00014225905539219148, | |
| "loss": 1.9151, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 0.00014222243468380488, | |
| "loss": 1.896, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 0.00014218573229382147, | |
| "loss": 1.898, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.00014214894826683813, | |
| "loss": 1.9136, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 0.00014211208264755092, | |
| "loss": 1.9077, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 0.00014207513548075503, | |
| "loss": 1.9253, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 0.00014203810681134477, | |
| "loss": 1.9166, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 0.00014200099668431346, | |
| "loss": 1.9178, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 0.00014196380514475335, | |
| "loss": 1.9303, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 0.00014192653223785577, | |
| "loss": 1.908, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 0.00014188917800891075, | |
| "loss": 1.9301, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 0.0001418517425033072, | |
| "loss": 1.9336, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 0.0001418142257665328, | |
| "loss": 1.9464, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.00014177662784417393, | |
| "loss": 1.9173, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 0.0001417389487819156, | |
| "loss": 1.921, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "eval_bleu": 8.330701000988771, | |
| "eval_bleurt": 0.4317358660828322, | |
| "eval_loss": 3.13454532623291, | |
| "eval_runtime": 989.9641, | |
| "eval_samples_per_second": 4.041, | |
| "eval_steps_per_second": 0.064, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.00014170118862554142, | |
| "loss": 1.905, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 0.0001416633474209336, | |
| "loss": 1.9382, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 0.00014162542521407265, | |
| "loss": 1.9291, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 0.00014158742205103774, | |
| "loss": 1.9546, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 0.00014154933797800621, | |
| "loss": 1.9228, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.0001415111730412539, | |
| "loss": 1.949, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 0.0001414729272871547, | |
| "loss": 1.9353, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 0.0001414346007621809, | |
| "loss": 1.9409, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 0.0001413961935129028, | |
| "loss": 1.956, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 0.0001413577055859888, | |
| "loss": 1.9523, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 0.00014131913702820543, | |
| "loss": 1.9488, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 0.00014128048788641706, | |
| "loss": 1.9422, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.00014124175820758603, | |
| "loss": 1.944, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.00014120294803877264, | |
| "loss": 1.9506, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 0.00014116405742713484, | |
| "loss": 1.9525, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 0.0001411250864199284, | |
| "loss": 1.9864, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 0.00014108603506450678, | |
| "loss": 1.9675, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 0.00014104690340832103, | |
| "loss": 1.9609, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.00014100769149891985, | |
| "loss": 1.9349, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 0.00014096839938394936, | |
| "loss": 1.9755, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "eval_bleu": 8.408521807709198, | |
| "eval_bleurt": 0.43550609762594106, | |
| "eval_loss": 3.0962271690368652, | |
| "eval_runtime": 984.0192, | |
| "eval_samples_per_second": 4.065, | |
| "eval_steps_per_second": 0.064, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.0001409290271111532, | |
| "loss": 1.9637, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 0.00014088957472837242, | |
| "loss": 1.926, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.00014085004228354535, | |
| "loss": 1.9779, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 0.00014081042982470765, | |
| "loss": 1.9595, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 0.00014077073739999222, | |
| "loss": 1.9535, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 0.00014073096505762904, | |
| "loss": 1.9545, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 0.00014069111284594531, | |
| "loss": 1.9681, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 0.0001406511808133652, | |
| "loss": 1.9818, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0001406111690084099, | |
| "loss": 1.9555, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 0.0001405710774796975, | |
| "loss": 1.9684, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 0.00014053090627594306, | |
| "loss": 1.9535, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.00014049065544595828, | |
| "loss": 1.9522, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0001404503250386518, | |
| "loss": 1.9827, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 0.00014040991510302887, | |
| "loss": 1.9505, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 0.0001403694256881913, | |
| "loss": 1.9608, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00014032885684333758, | |
| "loss": 1.9806, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 0.00014028820861776268, | |
| "loss": 1.9842, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 0.00014024748106085806, | |
| "loss": 1.96, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0001402066742221115, | |
| "loss": 1.9758, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 0.00014016578815110716, | |
| "loss": 1.8312, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_bleu": 8.251234394669309, | |
| "eval_bleurt": 0.43491230607777837, | |
| "eval_loss": 3.1952168941497803, | |
| "eval_runtime": 986.8, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.064, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 0.0001401248228975255, | |
| "loss": 1.7423, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 0.00014008377851114316, | |
| "loss": 1.7402, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 0.0001400426550418329, | |
| "loss": 1.7295, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 0.0001400014525395637, | |
| "loss": 1.7593, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 0.00013996017105440036, | |
| "loss": 1.7326, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.00013991881063650388, | |
| "loss": 1.7572, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 0.00013987737133613104, | |
| "loss": 1.7561, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 0.00013983585320363444, | |
| "loss": 1.757, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 0.00013979425628946263, | |
| "loss": 1.7702, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 0.00013975258064415972, | |
| "loss": 1.764, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 0.00013971082631836554, | |
| "loss": 1.7526, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 0.00013966899336281558, | |
| "loss": 1.7735, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 0.00013962708182834076, | |
| "loss": 1.7674, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 0.0001395850917658676, | |
| "loss": 1.7763, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 0.00013954302322641797, | |
| "loss": 1.7732, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.0001395008762611091, | |
| "loss": 1.7991, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 0.00013945865092115356, | |
| "loss": 1.7882, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 0.00013941634725785909, | |
| "loss": 1.8007, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.00013937396532262862, | |
| "loss": 1.7857, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 0.00013933150516696024, | |
| "loss": 1.7881, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "eval_bleu": 8.229771935594089, | |
| "eval_bleurt": 0.4351532816365361, | |
| "eval_loss": 3.1696953773498535, | |
| "eval_runtime": 979.5105, | |
| "eval_samples_per_second": 4.084, | |
| "eval_steps_per_second": 0.064, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 0.000139288966842447, | |
| "loss": 1.7869, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 0.00013924635040077699, | |
| "loss": 1.7874, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 0.0001392036558937332, | |
| "loss": 1.7883, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 0.0001391608833731935, | |
| "loss": 1.808, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 0.00013911803289113055, | |
| "loss": 1.8156, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 0.00013907510449961166, | |
| "loss": 1.8051, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 0.00013903209825079894, | |
| "loss": 1.8041, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 0.00013898901419694902, | |
| "loss": 1.817, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.00013894585239041305, | |
| "loss": 1.8294, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 0.00013890261288363676, | |
| "loss": 1.8183, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 0.00013885929572916017, | |
| "loss": 1.8049, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 0.00013881590097961774, | |
| "loss": 1.8097, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 0.00013877242868773817, | |
| "loss": 1.8073, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 0.0001387288789063444, | |
| "loss": 1.8318, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 0.00013868525168835353, | |
| "loss": 1.8178, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.0001386415470867767, | |
| "loss": 1.8056, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 0.00013859776515471917, | |
| "loss": 1.8196, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 0.00013855390594538013, | |
| "loss": 1.7906, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.00013850996951205257, | |
| "loss": 1.8242, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 0.0001384659559081235, | |
| "loss": 1.834, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "eval_bleu": 8.799660989311153, | |
| "eval_bleurt": 0.4393302373867482, | |
| "eval_loss": 3.140110969543457, | |
| "eval_runtime": 995.4934, | |
| "eval_samples_per_second": 4.018, | |
| "eval_steps_per_second": 0.063, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 0.00013842186518707355, | |
| "loss": 1.8405, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 0.0001383776974024771, | |
| "loss": 1.8082, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.00013833345260800213, | |
| "loss": 1.806, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 0.00013828913085741035, | |
| "loss": 1.8329, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 0.0001382447322045568, | |
| "loss": 1.8265, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.00013820025670339, | |
| "loss": 1.8053, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.0001381557044079519, | |
| "loss": 1.8374, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 0.00013811107537237778, | |
| "loss": 1.8492, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.0001380663696508961, | |
| "loss": 1.8172, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 0.0001380215872978285, | |
| "loss": 1.8224, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 0.00013797672836758982, | |
| "loss": 1.8404, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.00013793179291468784, | |
| "loss": 1.829, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 0.0001378867809937234, | |
| "loss": 1.8358, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 0.00013784169265939017, | |
| "loss": 1.815, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 0.0001377965279664748, | |
| "loss": 1.8337, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 0.00013775128696985665, | |
| "loss": 1.8566, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 0.00013770596972450776, | |
| "loss": 1.8403, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.00013766057628549283, | |
| "loss": 1.8548, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.00013761510670796926, | |
| "loss": 1.8728, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 0.0001375695610471868, | |
| "loss": 1.8577, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_bleu": 8.780151376587522, | |
| "eval_bleurt": 0.44215448238514365, | |
| "eval_loss": 3.1167867183685303, | |
| "eval_runtime": 990.1239, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.064, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.00013752393935848774, | |
| "loss": 1.9387, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 0.00013747824169730671, | |
| "loss": 1.6384, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.00013743246811917075, | |
| "loss": 1.5928, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 0.00013738661867969903, | |
| "loss": 1.6039, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 0.00013734069343460293, | |
| "loss": 1.645, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.00013729469243968593, | |
| "loss": 1.6316, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 0.00013724861575084365, | |
| "loss": 1.6386, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 0.00013720246342406356, | |
| "loss": 1.6215, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.0001371562355154251, | |
| "loss": 1.6222, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 0.0001371099320810995, | |
| "loss": 1.6516, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 0.00013706355317734989, | |
| "loss": 1.6461, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 0.00013701709886053097, | |
| "loss": 1.6383, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 0.00013697056918708905, | |
| "loss": 1.6492, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 0.00013692396421356216, | |
| "loss": 1.6421, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 0.0001368772839965797, | |
| "loss": 1.6485, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00013683052859286252, | |
| "loss": 1.6571, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 0.0001367836980592229, | |
| "loss": 1.652, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 0.00013673679245256425, | |
| "loss": 1.6652, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.00013668981182988143, | |
| "loss": 1.6684, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 0.00013664275624826025, | |
| "loss": 1.6391, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "eval_bleu": 8.588833236157425, | |
| "eval_bleurt": 0.43970556886307893, | |
| "eval_loss": 3.242238759994507, | |
| "eval_runtime": 974.225, | |
| "eval_samples_per_second": 4.106, | |
| "eval_steps_per_second": 0.065, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 0.00013659562576487768, | |
| "loss": 1.6534, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.00013654842043700174, | |
| "loss": 1.6841, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 0.0001365011403219913, | |
| "loss": 1.667, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 0.00013645378547729625, | |
| "loss": 1.6701, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 0.00013640635596045707, | |
| "loss": 1.677, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 0.0001363588518291052, | |
| "loss": 1.6668, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 0.00013631127314096256, | |
| "loss": 1.6812, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 0.0001362636199538418, | |
| "loss": 1.6696, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.00013621589232564601, | |
| "loss": 1.6856, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 0.00013616809031436876, | |
| "loss": 1.675, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 0.00013612021397809402, | |
| "loss": 1.6898, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 0.00013607226337499601, | |
| "loss": 1.6912, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 0.00013602423856333927, | |
| "loss": 1.6782, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 0.0001359761396014785, | |
| "loss": 1.6773, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.0001359279665478584, | |
| "loss": 1.6892, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.00013587971946101381, | |
| "loss": 1.7114, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 0.00013583139839956951, | |
| "loss": 1.6724, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 0.00013578300342224014, | |
| "loss": 1.711, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 0.00013573453458783012, | |
| "loss": 1.6977, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 0.0001356859919552337, | |
| "loss": 1.6849, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "eval_bleu": 8.72266913623635, | |
| "eval_bleurt": 0.43958353469148276, | |
| "eval_loss": 3.183589220046997, | |
| "eval_runtime": 976.6079, | |
| "eval_samples_per_second": 4.096, | |
| "eval_steps_per_second": 0.065, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 0.00013563737558343474, | |
| "loss": 1.6983, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 0.00013558868553150671, | |
| "loss": 1.703, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 0.00013553992185861262, | |
| "loss": 1.7026, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 0.00013549108462400494, | |
| "loss": 1.699, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 0.0001354421738870255, | |
| "loss": 1.7119, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 0.00013539318970710545, | |
| "loss": 1.7168, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 0.0001353441321437652, | |
| "loss": 1.7182, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.00013529500125661432, | |
| "loss": 1.6878, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 0.00013524579710535146, | |
| "loss": 1.7105, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 0.00013519651974976433, | |
| "loss": 1.7379, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 0.00013514716924972953, | |
| "loss": 1.7224, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 0.00013509774566521258, | |
| "loss": 1.7288, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 0.0001350482490562678, | |
| "loss": 1.7178, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 0.00013499867948303827, | |
| "loss": 1.7234, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 0.00013494903700575562, | |
| "loss": 1.7292, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.0001348993216847402, | |
| "loss": 1.7394, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 0.0001348495335804008, | |
| "loss": 1.7191, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 0.00013479967275323464, | |
| "loss": 1.7393, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00013474973926382735, | |
| "loss": 1.7052, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 0.00013469973317285284, | |
| "loss": 1.7325, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "eval_bleu": 9.169944232709382, | |
| "eval_bleurt": 0.44671384619362653, | |
| "eval_loss": 3.176605463027954, | |
| "eval_runtime": 986.2782, | |
| "eval_samples_per_second": 4.056, | |
| "eval_steps_per_second": 0.064, | |
| "step": 7400 | |
| } | |
| ], | |
| "max_steps": 30000, | |
| "num_train_epochs": 49, | |
| "total_flos": 9.215999699933127e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |