| { | |
| "best_metric": 2.0570528507232666, | |
| "best_model_checkpoint": "t5-base-snl/checkpoint-2890", | |
| "epoch": 19.0, | |
| "global_step": 3230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9632352941176476e-05, | |
| "loss": 4.9792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.9264705882352944e-05, | |
| "loss": 3.7166, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.889705882352941e-05, | |
| "loss": 3.2528, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.8529411764705885e-05, | |
| "loss": 3.0823, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.816176470588236e-05, | |
| "loss": 3.0381, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.7794117647058826e-05, | |
| "loss": 2.9943, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 18.976800976800977, | |
| "eval_loss": 2.2042253017425537, | |
| "eval_rouge1": 28.1135, | |
| "eval_rouge2": 13.7477, | |
| "eval_rougeL": 25.4842, | |
| "eval_rougeLsum": 26.6467, | |
| "eval_runtime": 22.885, | |
| "eval_samples_per_second": 35.788, | |
| "eval_steps_per_second": 2.272, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.742647058823529e-05, | |
| "loss": 2.9188, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 2.8824, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.669117647058824e-05, | |
| "loss": 2.8751, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.632352941176471e-05, | |
| "loss": 2.8037, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.5955882352941176e-05, | |
| "loss": 2.7824, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.558823529411765e-05, | |
| "loss": 2.7789, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.522058823529412e-05, | |
| "loss": 2.7955, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 18.985347985347985, | |
| "eval_loss": 2.1561412811279297, | |
| "eval_rouge1": 28.5159, | |
| "eval_rouge2": 14.3492, | |
| "eval_rougeL": 26.0596, | |
| "eval_rougeLsum": 27.2431, | |
| "eval_runtime": 23.1378, | |
| "eval_samples_per_second": 35.397, | |
| "eval_steps_per_second": 2.247, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.485294117647059e-05, | |
| "loss": 2.7598, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 4.448529411764706e-05, | |
| "loss": 2.7091, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 2.7055, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.375e-05, | |
| "loss": 2.7163, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.3382352941176474e-05, | |
| "loss": 2.6844, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.301470588235295e-05, | |
| "loss": 2.686, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.2647058823529415e-05, | |
| "loss": 2.6378, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 18.99145299145299, | |
| "eval_loss": 2.130974531173706, | |
| "eval_rouge1": 28.9554, | |
| "eval_rouge2": 14.6901, | |
| "eval_rougeL": 26.4208, | |
| "eval_rougeLsum": 27.5523, | |
| "eval_runtime": 23.1305, | |
| "eval_samples_per_second": 35.408, | |
| "eval_steps_per_second": 2.248, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 4.227941176470588e-05, | |
| "loss": 2.6666, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.1911764705882356e-05, | |
| "loss": 2.6372, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.154411764705883e-05, | |
| "loss": 2.6506, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 2.6104, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.0808823529411765e-05, | |
| "loss": 2.5946, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.044117647058824e-05, | |
| "loss": 2.6182, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.007352941176471e-05, | |
| "loss": 2.5962, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 18.99145299145299, | |
| "eval_loss": 2.1109659671783447, | |
| "eval_rouge1": 29.381, | |
| "eval_rouge2": 15.1503, | |
| "eval_rougeL": 26.8406, | |
| "eval_rougeLsum": 27.9653, | |
| "eval_runtime": 23.0996, | |
| "eval_samples_per_second": 35.455, | |
| "eval_steps_per_second": 2.251, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.970588235294117e-05, | |
| "loss": 2.5478, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.933823529411765e-05, | |
| "loss": 2.5601, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.897058823529412e-05, | |
| "loss": 2.5793, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 3.8602941176470595e-05, | |
| "loss": 2.5655, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 3.8235294117647055e-05, | |
| "loss": 2.5686, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.786764705882353e-05, | |
| "loss": 2.5704, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.5369, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.1019859313964844, | |
| "eval_rouge1": 29.5767, | |
| "eval_rouge2": 15.2692, | |
| "eval_rougeL": 27.0113, | |
| "eval_rougeLsum": 28.1849, | |
| "eval_runtime": 22.9206, | |
| "eval_samples_per_second": 35.732, | |
| "eval_steps_per_second": 2.269, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 3.713235294117647e-05, | |
| "loss": 2.5257, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 3.6764705882352945e-05, | |
| "loss": 2.5294, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 3.639705882352941e-05, | |
| "loss": 2.5188, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 3.6029411764705886e-05, | |
| "loss": 2.5164, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 3.566176470588235e-05, | |
| "loss": 2.4973, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 2.5103, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.090707302093506, | |
| "eval_rouge1": 29.6354, | |
| "eval_rouge2": 15.434, | |
| "eval_rougeL": 27.0893, | |
| "eval_rougeLsum": 28.2703, | |
| "eval_runtime": 22.9931, | |
| "eval_samples_per_second": 35.619, | |
| "eval_steps_per_second": 2.262, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.4926470588235294e-05, | |
| "loss": 2.4817, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 3.455882352941177e-05, | |
| "loss": 2.4662, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 3.4191176470588236e-05, | |
| "loss": 2.4879, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 3.382352941176471e-05, | |
| "loss": 2.4666, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 3.345588235294118e-05, | |
| "loss": 2.4908, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 3.308823529411765e-05, | |
| "loss": 2.4887, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 3.272058823529412e-05, | |
| "loss": 2.4524, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.0839579105377197, | |
| "eval_rouge1": 29.7812, | |
| "eval_rouge2": 15.4963, | |
| "eval_rougeL": 27.2779, | |
| "eval_rougeLsum": 28.385, | |
| "eval_runtime": 23.0064, | |
| "eval_samples_per_second": 35.599, | |
| "eval_steps_per_second": 2.26, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 3.235294117647059e-05, | |
| "loss": 2.4526, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 3.198529411764706e-05, | |
| "loss": 2.4316, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 3.161764705882353e-05, | |
| "loss": 2.4511, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.4642, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 3.0882352941176475e-05, | |
| "loss": 2.4387, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 3.0514705882352945e-05, | |
| "loss": 2.477, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 3.0147058823529413e-05, | |
| "loss": 2.4472, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.0799622535705566, | |
| "eval_rouge1": 29.6011, | |
| "eval_rouge2": 15.5138, | |
| "eval_rougeL": 27.1381, | |
| "eval_rougeLsum": 28.2799, | |
| "eval_runtime": 22.9827, | |
| "eval_samples_per_second": 35.636, | |
| "eval_steps_per_second": 2.263, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 2.9779411764705883e-05, | |
| "loss": 2.4296, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 2.4109, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 2.9044117647058828e-05, | |
| "loss": 2.4181, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 2.8676470588235295e-05, | |
| "loss": 2.4089, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 2.8308823529411766e-05, | |
| "loss": 2.4518, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 2.7941176470588236e-05, | |
| "loss": 2.4271, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 2.757352941176471e-05, | |
| "loss": 2.4089, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.075223207473755, | |
| "eval_rouge1": 29.7647, | |
| "eval_rouge2": 15.6183, | |
| "eval_rougeL": 27.318, | |
| "eval_rougeLsum": 28.4747, | |
| "eval_runtime": 22.8902, | |
| "eval_samples_per_second": 35.779, | |
| "eval_steps_per_second": 2.272, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 2.7205882352941174e-05, | |
| "loss": 2.4048, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 2.6838235294117648e-05, | |
| "loss": 2.4132, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 2.3885, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.6102941176470593e-05, | |
| "loss": 2.4007, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 2.5735294117647057e-05, | |
| "loss": 2.4089, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 2.536764705882353e-05, | |
| "loss": 2.3912, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.4011, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.071033239364624, | |
| "eval_rouge1": 29.6533, | |
| "eval_rouge2": 15.5536, | |
| "eval_rougeL": 27.2687, | |
| "eval_rougeLsum": 28.4457, | |
| "eval_runtime": 23.0214, | |
| "eval_samples_per_second": 35.576, | |
| "eval_steps_per_second": 2.259, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 2.4632352941176472e-05, | |
| "loss": 2.4049, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 2.4264705882352942e-05, | |
| "loss": 2.3802, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 2.3897058823529413e-05, | |
| "loss": 2.3688, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 2.3897, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 2.3161764705882354e-05, | |
| "loss": 2.3464, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 2.2794117647058825e-05, | |
| "loss": 2.3792, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0655674934387207, | |
| "eval_rouge1": 29.8668, | |
| "eval_rouge2": 15.6931, | |
| "eval_rougeL": 27.4208, | |
| "eval_rougeLsum": 28.5477, | |
| "eval_runtime": 21.951, | |
| "eval_samples_per_second": 37.31, | |
| "eval_steps_per_second": 2.369, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.2426470588235296e-05, | |
| "loss": 2.3783, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 2.3446, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 2.1691176470588237e-05, | |
| "loss": 2.3929, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 2.1323529411764707e-05, | |
| "loss": 2.374, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 2.0955882352941178e-05, | |
| "loss": 2.3544, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 2.357, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 2.022058823529412e-05, | |
| "loss": 2.3588, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.0634803771972656, | |
| "eval_rouge1": 29.8378, | |
| "eval_rouge2": 15.682, | |
| "eval_rougeL": 27.4635, | |
| "eval_rougeLsum": 28.5803, | |
| "eval_runtime": 22.98, | |
| "eval_samples_per_second": 35.64, | |
| "eval_steps_per_second": 2.263, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 1.9852941176470586e-05, | |
| "loss": 2.3503, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 1.948529411764706e-05, | |
| "loss": 2.3402, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 1.9117647058823528e-05, | |
| "loss": 2.3716, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.3161, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 1.8382352941176472e-05, | |
| "loss": 2.3354, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 1.8014705882352943e-05, | |
| "loss": 2.3476, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 2.3397, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0630440711975098, | |
| "eval_rouge1": 29.9043, | |
| "eval_rouge2": 15.7535, | |
| "eval_rougeL": 27.5065, | |
| "eval_rougeLsum": 28.6539, | |
| "eval_runtime": 22.9094, | |
| "eval_samples_per_second": 35.75, | |
| "eval_steps_per_second": 2.27, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.7279411764705884e-05, | |
| "loss": 2.3399, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 1.6911764705882355e-05, | |
| "loss": 2.3207, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 1.6544117647058825e-05, | |
| "loss": 2.3339, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.6176470588235296e-05, | |
| "loss": 2.3347, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 1.5808823529411763e-05, | |
| "loss": 2.3318, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 1.5441176470588237e-05, | |
| "loss": 2.3275, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 1.5073529411764706e-05, | |
| "loss": 2.3201, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_gen_len": 18.996336996336996, | |
| "eval_loss": 2.0599966049194336, | |
| "eval_rouge1": 29.7926, | |
| "eval_rouge2": 15.7077, | |
| "eval_rougeL": 27.4066, | |
| "eval_rougeLsum": 28.5302, | |
| "eval_runtime": 23.1182, | |
| "eval_samples_per_second": 35.427, | |
| "eval_steps_per_second": 2.249, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 2.3204, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 1.4338235294117647e-05, | |
| "loss": 2.3592, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 1.3970588235294118e-05, | |
| "loss": 2.3275, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 1.3602941176470587e-05, | |
| "loss": 2.2936, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 2.3013, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 1.2867647058823528e-05, | |
| "loss": 2.3007, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.3241, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0615200996398926, | |
| "eval_rouge1": 29.8536, | |
| "eval_rouge2": 15.7929, | |
| "eval_rougeL": 27.4572, | |
| "eval_rougeLsum": 28.5704, | |
| "eval_runtime": 22.9087, | |
| "eval_samples_per_second": 35.751, | |
| "eval_steps_per_second": 2.27, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 1.2132352941176471e-05, | |
| "loss": 2.326, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.3004, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 1.1397058823529412e-05, | |
| "loss": 2.311, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 1.1029411764705883e-05, | |
| "loss": 2.3427, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 1.0661764705882354e-05, | |
| "loss": 2.2741, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 1.0294117647058824e-05, | |
| "loss": 2.3183, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0573582649230957, | |
| "eval_rouge1": 29.7529, | |
| "eval_rouge2": 15.6729, | |
| "eval_rougeL": 27.3388, | |
| "eval_rougeLsum": 28.4678, | |
| "eval_runtime": 23.1299, | |
| "eval_samples_per_second": 35.409, | |
| "eval_steps_per_second": 2.248, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.926470588235293e-06, | |
| "loss": 2.2934, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 9.558823529411764e-06, | |
| "loss": 2.2633, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 9.191176470588236e-06, | |
| "loss": 2.2957, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 2.3083, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 8.455882352941177e-06, | |
| "loss": 2.3246, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 8.088235294117648e-06, | |
| "loss": 2.2989, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 7.720588235294119e-06, | |
| "loss": 2.3346, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0570528507232666, | |
| "eval_rouge1": 29.7443, | |
| "eval_rouge2": 15.6459, | |
| "eval_rougeL": 27.3245, | |
| "eval_rougeLsum": 28.4549, | |
| "eval_runtime": 22.9331, | |
| "eval_samples_per_second": 35.713, | |
| "eval_steps_per_second": 2.267, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 7.3529411764705884e-06, | |
| "loss": 2.2887, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 6.985294117647059e-06, | |
| "loss": 2.2881, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 6.61764705882353e-06, | |
| "loss": 2.3062, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 6.25e-06, | |
| "loss": 2.2867, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 2.3056, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 5.5147058823529415e-06, | |
| "loss": 2.3098, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "learning_rate": 5.147058823529412e-06, | |
| "loss": 2.2932, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0577263832092285, | |
| "eval_rouge1": 29.7467, | |
| "eval_rouge2": 15.6717, | |
| "eval_rougeL": 27.3391, | |
| "eval_rougeLsum": 28.4541, | |
| "eval_runtime": 23.0624, | |
| "eval_samples_per_second": 35.512, | |
| "eval_steps_per_second": 2.255, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 4.779411764705882e-06, | |
| "loss": 2.2832, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 2.289, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 4.044117647058824e-06, | |
| "loss": 2.2932, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 3.6764705882352942e-06, | |
| "loss": 2.3085, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "learning_rate": 3.308823529411765e-06, | |
| "loss": 2.2884, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 2.2877, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 2.573529411764706e-06, | |
| "loss": 2.2755, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 2.0573978424072266, | |
| "eval_rouge1": 29.7694, | |
| "eval_rouge2": 15.6776, | |
| "eval_rougeL": 27.3556, | |
| "eval_rougeLsum": 28.4819, | |
| "eval_runtime": 22.951, | |
| "eval_samples_per_second": 35.685, | |
| "eval_steps_per_second": 2.266, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "step": 3230, | |
| "total_flos": 2.285170027491492e+17, | |
| "train_loss": 2.4905450729393737, | |
| "train_runtime": 8327.4677, | |
| "train_samples_per_second": 26.116, | |
| "train_steps_per_second": 0.408 | |
| } | |
| ], | |
| "max_steps": 3400, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.285170027491492e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |