| { | |
| "best_metric": 2.039487600326538, | |
| "best_model_checkpoint": "t5-base-cnndaily/checkpoint-3680", | |
| "epoch": 19.99728997289973, | |
| "global_step": 3680, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9660326086956525e-05, | |
| "loss": 4.2518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.932065217391305e-05, | |
| "loss": 3.2161, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.898097826086957e-05, | |
| "loss": 2.9499, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.8641304347826086e-05, | |
| "loss": 2.8424, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.8301630434782615e-05, | |
| "loss": 2.7775, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.796195652173913e-05, | |
| "loss": 2.7339, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.7622282608695654e-05, | |
| "loss": 2.7173, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 68.36778372289496, | |
| "eval_loss": 2.237959384918213, | |
| "eval_rouge1": 26.4764, | |
| "eval_rouge2": 9.4302, | |
| "eval_rougeL": 19.7562, | |
| "eval_rougeLsum": 24.4771, | |
| "eval_runtime": 180.353, | |
| "eval_samples_per_second": 19.689, | |
| "eval_steps_per_second": 0.615, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.7282608695652177e-05, | |
| "loss": 2.7233, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.69429347826087e-05, | |
| "loss": 2.6398, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.660326086956522e-05, | |
| "loss": 2.6332, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.6263586956521744e-05, | |
| "loss": 2.6027, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.592391304347826e-05, | |
| "loss": 2.5922, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.558423913043478e-05, | |
| "loss": 2.581, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.5244565217391305e-05, | |
| "loss": 2.5683, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 70.79273444100254, | |
| "eval_loss": 2.177700996398926, | |
| "eval_rouge1": 26.9803, | |
| "eval_rouge2": 9.711, | |
| "eval_rougeL": 20.1842, | |
| "eval_rougeLsum": 25.0146, | |
| "eval_runtime": 180.5228, | |
| "eval_samples_per_second": 19.671, | |
| "eval_steps_per_second": 0.615, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.490489130434783e-05, | |
| "loss": 2.5997, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.456521739130435e-05, | |
| "loss": 2.5445, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.422554347826087e-05, | |
| "loss": 2.5334, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.388586956521739e-05, | |
| "loss": 2.504, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.354619565217392e-05, | |
| "loss": 2.521, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.3206521739130434e-05, | |
| "loss": 2.515, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 4.286684782608696e-05, | |
| "loss": 2.499, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.252717391304348e-05, | |
| "loss": 2.4764, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 70.5550549141087, | |
| "eval_loss": 2.149622917175293, | |
| "eval_rouge1": 27.4931, | |
| "eval_rouge2": 9.9982, | |
| "eval_rougeL": 20.4503, | |
| "eval_rougeLsum": 25.5179, | |
| "eval_runtime": 181.4064, | |
| "eval_samples_per_second": 19.575, | |
| "eval_steps_per_second": 0.612, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 4.21875e-05, | |
| "loss": 2.5205, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 4.1847826086956525e-05, | |
| "loss": 2.4676, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.150815217391305e-05, | |
| "loss": 2.4766, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 4.116847826086957e-05, | |
| "loss": 2.4496, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 4.0828804347826086e-05, | |
| "loss": 2.4475, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.0489130434782615e-05, | |
| "loss": 2.4433, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 4.014945652173913e-05, | |
| "loss": 2.4365, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 70.99042523232892, | |
| "eval_loss": 2.124873161315918, | |
| "eval_rouge1": 27.8843, | |
| "eval_rouge2": 10.2961, | |
| "eval_rougeL": 20.7113, | |
| "eval_rougeLsum": 25.8998, | |
| "eval_runtime": 179.7697, | |
| "eval_samples_per_second": 19.753, | |
| "eval_steps_per_second": 0.617, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 3.9809782608695654e-05, | |
| "loss": 2.4847, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 3.9470108695652176e-05, | |
| "loss": 2.4137, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.91304347826087e-05, | |
| "loss": 2.4275, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.8790760869565215e-05, | |
| "loss": 2.4068, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.8451086956521744e-05, | |
| "loss": 2.4144, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 3.811141304347826e-05, | |
| "loss": 2.4101, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.777173913043478e-05, | |
| "loss": 2.3932, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 70.42692199380456, | |
| "eval_loss": 2.1084039211273193, | |
| "eval_rouge1": 28.2543, | |
| "eval_rouge2": 10.433, | |
| "eval_rougeL": 20.9026, | |
| "eval_rougeLsum": 26.2599, | |
| "eval_runtime": 178.1314, | |
| "eval_samples_per_second": 19.935, | |
| "eval_steps_per_second": 0.623, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.7432065217391305e-05, | |
| "loss": 2.4457, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 3.709239130434783e-05, | |
| "loss": 2.3702, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 3.675271739130435e-05, | |
| "loss": 2.3941, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 3.641304347826087e-05, | |
| "loss": 2.3999, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 3.607336956521739e-05, | |
| "loss": 2.3703, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 3.573369565217392e-05, | |
| "loss": 2.3707, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 3.5394021739130434e-05, | |
| "loss": 2.3716, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 3.505434782608696e-05, | |
| "loss": 2.3815, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 70.43227259926782, | |
| "eval_loss": 2.096766948699951, | |
| "eval_rouge1": 28.4855, | |
| "eval_rouge2": 10.5771, | |
| "eval_rougeL": 21.0169, | |
| "eval_rougeLsum": 26.4552, | |
| "eval_runtime": 179.9467, | |
| "eval_samples_per_second": 19.734, | |
| "eval_steps_per_second": 0.617, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 3.471467391304348e-05, | |
| "loss": 2.391, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 2.3547, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 3.4035326086956525e-05, | |
| "loss": 2.3611, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.369565217391305e-05, | |
| "loss": 2.3495, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 3.335597826086957e-05, | |
| "loss": 2.357, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 3.3016304347826086e-05, | |
| "loss": 2.3457, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.2676630434782615e-05, | |
| "loss": 2.35, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 69.14080540692763, | |
| "eval_loss": 2.0887129306793213, | |
| "eval_rouge1": 28.7887, | |
| "eval_rouge2": 10.6794, | |
| "eval_rougeL": 21.2061, | |
| "eval_rougeLsum": 26.7346, | |
| "eval_runtime": 179.9375, | |
| "eval_samples_per_second": 19.735, | |
| "eval_steps_per_second": 0.617, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 3.233695652173913e-05, | |
| "loss": 2.3907, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 3.1997282608695654e-05, | |
| "loss": 2.329, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 3.1657608695652176e-05, | |
| "loss": 2.3296, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 3.13179347826087e-05, | |
| "loss": 2.3408, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 3.0978260869565215e-05, | |
| "loss": 2.3199, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 3.0638586956521744e-05, | |
| "loss": 2.3183, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 3.029891304347826e-05, | |
| "loss": 2.3331, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_gen_len": 69.29850746268657, | |
| "eval_loss": 2.0796895027160645, | |
| "eval_rouge1": 28.8309, | |
| "eval_rouge2": 10.7142, | |
| "eval_rougeL": 21.2091, | |
| "eval_rougeLsum": 26.791, | |
| "eval_runtime": 178.7689, | |
| "eval_samples_per_second": 19.864, | |
| "eval_steps_per_second": 0.621, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 2.9959239130434786e-05, | |
| "loss": 2.3675, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 2.9619565217391305e-05, | |
| "loss": 2.3262, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 2.9279891304347828e-05, | |
| "loss": 2.3138, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 2.8940217391304347e-05, | |
| "loss": 2.3079, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 2.8600543478260873e-05, | |
| "loss": 2.3094, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 2.3081, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 2.7921195652173915e-05, | |
| "loss": 2.2917, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 2.7581521739130434e-05, | |
| "loss": 2.3139, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_gen_len": 69.51900872993522, | |
| "eval_loss": 2.071018934249878, | |
| "eval_rouge1": 29.1251, | |
| "eval_rouge2": 10.8789, | |
| "eval_rougeL": 21.4693, | |
| "eval_rougeLsum": 27.0652, | |
| "eval_runtime": 178.038, | |
| "eval_samples_per_second": 19.945, | |
| "eval_steps_per_second": 0.623, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 2.7241847826086957e-05, | |
| "loss": 2.3485, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 2.6902173913043476e-05, | |
| "loss": 2.302, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 2.6562500000000002e-05, | |
| "loss": 2.3095, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 2.6222826086956525e-05, | |
| "loss": 2.2841, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 2.5883152173913044e-05, | |
| "loss": 2.3034, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.554347826086957e-05, | |
| "loss": 2.2753, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 2.520380434782609e-05, | |
| "loss": 2.2977, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_gen_len": 69.72007885102788, | |
| "eval_loss": 2.0674257278442383, | |
| "eval_rouge1": 29.0481, | |
| "eval_rouge2": 10.7896, | |
| "eval_rougeL": 21.2985, | |
| "eval_rougeLsum": 26.9968, | |
| "eval_runtime": 179.3171, | |
| "eval_samples_per_second": 19.803, | |
| "eval_steps_per_second": 0.619, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 2.4864130434782608e-05, | |
| "loss": 2.3133, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 2.452445652173913e-05, | |
| "loss": 2.2748, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 2.4184782608695653e-05, | |
| "loss": 2.2849, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.46, | |
| "learning_rate": 2.3845108695652173e-05, | |
| "loss": 2.2777, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 2.3505434782608695e-05, | |
| "loss": 2.2862, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 2.3165760869565218e-05, | |
| "loss": 2.2779, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 2.282608695652174e-05, | |
| "loss": 2.2732, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_gen_len": 69.99014362151506, | |
| "eval_loss": 2.0569896697998047, | |
| "eval_rouge1": 29.4623, | |
| "eval_rouge2": 11.0479, | |
| "eval_rougeL": 21.5714, | |
| "eval_rougeLsum": 27.425, | |
| "eval_runtime": 179.0446, | |
| "eval_samples_per_second": 19.833, | |
| "eval_steps_per_second": 0.62, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.2486413043478263e-05, | |
| "loss": 2.3298, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 2.2146739130434786e-05, | |
| "loss": 2.2779, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.1807065217391305e-05, | |
| "loss": 2.2701, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 2.1467391304347828e-05, | |
| "loss": 2.2635, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 2.112771739130435e-05, | |
| "loss": 2.2716, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 2.0788043478260873e-05, | |
| "loss": 2.2601, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 2.0448369565217392e-05, | |
| "loss": 2.2663, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 2.0108695652173915e-05, | |
| "loss": 2.2483, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_gen_len": 70.79442410588567, | |
| "eval_loss": 2.0552728176116943, | |
| "eval_rouge1": 29.2723, | |
| "eval_rouge2": 10.8919, | |
| "eval_rougeL": 21.3793, | |
| "eval_rougeLsum": 27.2419, | |
| "eval_runtime": 179.2858, | |
| "eval_samples_per_second": 19.806, | |
| "eval_steps_per_second": 0.619, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 1.9769021739130437e-05, | |
| "loss": 2.3121, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 1.9429347826086957e-05, | |
| "loss": 2.2507, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 1.908967391304348e-05, | |
| "loss": 2.2494, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.2538, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 1.841032608695652e-05, | |
| "loss": 2.2607, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 1.8070652173913044e-05, | |
| "loss": 2.264, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 1.7730978260869566e-05, | |
| "loss": 2.2468, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_gen_len": 70.16896648831315, | |
| "eval_loss": 2.048848867416382, | |
| "eval_rouge1": 29.5015, | |
| "eval_rouge2": 11.0234, | |
| "eval_rougeL": 21.5698, | |
| "eval_rougeLsum": 27.4697, | |
| "eval_runtime": 178.4371, | |
| "eval_samples_per_second": 19.901, | |
| "eval_steps_per_second": 0.622, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.739130434782609e-05, | |
| "loss": 2.2379, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 1.7051630434782608e-05, | |
| "loss": 2.2511, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 1.671195652173913e-05, | |
| "loss": 2.2455, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 1.6372282608695653e-05, | |
| "loss": 2.2544, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 1.6032608695652173e-05, | |
| "loss": 2.2362, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 1.5692934782608695e-05, | |
| "loss": 2.2418, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 1.5353260869565218e-05, | |
| "loss": 2.2375, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 1.5013586956521739e-05, | |
| "loss": 2.2549, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_gen_len": 70.30582934384681, | |
| "eval_loss": 2.0479626655578613, | |
| "eval_rouge1": 29.5076, | |
| "eval_rouge2": 11.0717, | |
| "eval_rougeL": 21.6358, | |
| "eval_rougeLsum": 27.5399, | |
| "eval_runtime": 177.5749, | |
| "eval_samples_per_second": 19.997, | |
| "eval_steps_per_second": 0.625, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 14.13, | |
| "learning_rate": 1.4673913043478263e-05, | |
| "loss": 2.293, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 1.4334239130434784e-05, | |
| "loss": 2.2487, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 1.3994565217391307e-05, | |
| "loss": 2.2404, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 14.54, | |
| "learning_rate": 1.3654891304347827e-05, | |
| "loss": 2.2404, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 1.331521739130435e-05, | |
| "loss": 2.234, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 1.2975543478260871e-05, | |
| "loss": 2.244, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "learning_rate": 1.2635869565217392e-05, | |
| "loss": 2.2225, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_gen_len": 70.256829062236, | |
| "eval_loss": 2.044435977935791, | |
| "eval_rouge1": 29.5289, | |
| "eval_rouge2": 11.0401, | |
| "eval_rougeL": 21.609, | |
| "eval_rougeLsum": 27.5116, | |
| "eval_runtime": 181.0716, | |
| "eval_samples_per_second": 19.611, | |
| "eval_steps_per_second": 0.613, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 1.2296195652173915e-05, | |
| "loss": 2.282, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 1.1956521739130435e-05, | |
| "loss": 2.2318, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.1616847826086958e-05, | |
| "loss": 2.239, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 1.1277173913043479e-05, | |
| "loss": 2.2285, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 2.2364, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 1.0597826086956523e-05, | |
| "loss": 2.2213, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 1.0258152173913043e-05, | |
| "loss": 2.2351, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_gen_len": 70.1554491692481, | |
| "eval_loss": 2.042268991470337, | |
| "eval_rouge1": 29.6463, | |
| "eval_rouge2": 11.1162, | |
| "eval_rougeL": 21.6627, | |
| "eval_rougeLsum": 27.6332, | |
| "eval_runtime": 180.5795, | |
| "eval_samples_per_second": 19.664, | |
| "eval_steps_per_second": 0.615, | |
| "step": 2944 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.918478260869566e-06, | |
| "loss": 2.2698, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 9.578804347826087e-06, | |
| "loss": 2.2243, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 9.239130434782608e-06, | |
| "loss": 2.2397, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 8.899456521739132e-06, | |
| "loss": 2.2241, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 8.559782608695653e-06, | |
| "loss": 2.2186, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 8.220108695652174e-06, | |
| "loss": 2.2331, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "learning_rate": 7.880434782608697e-06, | |
| "loss": 2.2231, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 7.540760869565218e-06, | |
| "loss": 2.2218, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_gen_len": 69.79414249507181, | |
| "eval_loss": 2.040226936340332, | |
| "eval_rouge1": 29.7229, | |
| "eval_rouge2": 11.1601, | |
| "eval_rougeL": 21.7195, | |
| "eval_rougeLsum": 27.6978, | |
| "eval_runtime": 180.1107, | |
| "eval_samples_per_second": 19.716, | |
| "eval_steps_per_second": 0.616, | |
| "step": 3128 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 7.201086956521739e-06, | |
| "loss": 2.2616, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 6.861413043478261e-06, | |
| "loss": 2.2188, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 2.2304, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 6.182065217391305e-06, | |
| "loss": 2.2245, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 5.842391304347826e-06, | |
| "loss": 2.2187, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 5.502717391304348e-06, | |
| "loss": 2.2147, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 5.16304347826087e-06, | |
| "loss": 2.2264, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_gen_len": 70.03801745987046, | |
| "eval_loss": 2.0398149490356445, | |
| "eval_rouge1": 29.6695, | |
| "eval_rouge2": 11.1279, | |
| "eval_rougeL": 21.6656, | |
| "eval_rougeLsum": 27.6246, | |
| "eval_runtime": 179.5984, | |
| "eval_samples_per_second": 19.772, | |
| "eval_steps_per_second": 0.618, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 4.823369565217392e-06, | |
| "loss": 2.2775, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 4.483695652173913e-06, | |
| "loss": 2.2251, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 4.144021739130434e-06, | |
| "loss": 2.2135, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 3.804347826086957e-06, | |
| "loss": 2.2338, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 3.4646739130434784e-06, | |
| "loss": 2.2216, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 3.125e-06, | |
| "loss": 2.2235, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.785326086956522e-06, | |
| "loss": 2.2104, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_gen_len": 70.22416220782878, | |
| "eval_loss": 2.0398826599121094, | |
| "eval_rouge1": 29.7001, | |
| "eval_rouge2": 11.1385, | |
| "eval_rougeL": 21.6634, | |
| "eval_rougeLsum": 27.635, | |
| "eval_runtime": 179.3733, | |
| "eval_samples_per_second": 19.797, | |
| "eval_steps_per_second": 0.619, | |
| "step": 3496 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 2.4456521739130437e-06, | |
| "loss": 2.2583, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 2.1059782608695655e-06, | |
| "loss": 2.2194, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 1.7663043478260868e-06, | |
| "loss": 2.2273, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 1.4266304347826088e-06, | |
| "loss": 2.2196, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 1.0869565217391306e-06, | |
| "loss": 2.2192, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 7.472826086956522e-07, | |
| "loss": 2.2073, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 4.0760869565217393e-07, | |
| "loss": 2.2106, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 19.97, | |
| "learning_rate": 6.793478260869566e-08, | |
| "loss": 2.2235, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_gen_len": 70.12644325542101, | |
| "eval_loss": 2.039487600326538, | |
| "eval_rouge1": 29.6901, | |
| "eval_rouge2": 11.127, | |
| "eval_rougeL": 21.6809, | |
| "eval_rougeLsum": 27.6332, | |
| "eval_runtime": 179.8041, | |
| "eval_samples_per_second": 19.749, | |
| "eval_steps_per_second": 0.617, | |
| "step": 3680 | |
| } | |
| ], | |
| "max_steps": 3680, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.1311399656530903e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |