| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 500.0, | |
| "global_step": 31000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 40.06241989135742, | |
| "eval_runtime": 1.547, | |
| "eval_samples_per_second": 79.509, | |
| "eval_steps_per_second": 10.343, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 39.472923278808594, | |
| "eval_runtime": 1.5508, | |
| "eval_samples_per_second": 79.312, | |
| "eval_steps_per_second": 10.317, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 39.0081672668457, | |
| "eval_runtime": 1.546, | |
| "eval_samples_per_second": 79.558, | |
| "eval_steps_per_second": 10.349, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 38.20319366455078, | |
| "eval_runtime": 1.5507, | |
| "eval_samples_per_second": 79.317, | |
| "eval_steps_per_second": 10.318, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 37.33580017089844, | |
| "eval_runtime": 1.5485, | |
| "eval_samples_per_second": 79.431, | |
| "eval_steps_per_second": 10.332, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 36.15742111206055, | |
| "eval_runtime": 1.5522, | |
| "eval_samples_per_second": 79.244, | |
| "eval_steps_per_second": 10.308, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 35.14997863769531, | |
| "eval_runtime": 1.5454, | |
| "eval_samples_per_second": 79.589, | |
| "eval_steps_per_second": 10.353, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 33.69432067871094, | |
| "eval_runtime": 1.5477, | |
| "eval_samples_per_second": 79.472, | |
| "eval_steps_per_second": 10.338, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 6.887096774193549e-08, | |
| "loss": 39.2118, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 32.3968391418457, | |
| "eval_runtime": 1.5552, | |
| "eval_samples_per_second": 79.09, | |
| "eval_steps_per_second": 10.288, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 30.730754852294922, | |
| "eval_runtime": 1.5637, | |
| "eval_samples_per_second": 78.658, | |
| "eval_steps_per_second": 10.232, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 29.227901458740234, | |
| "eval_runtime": 1.553, | |
| "eval_samples_per_second": 79.199, | |
| "eval_steps_per_second": 10.302, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 27.82735824584961, | |
| "eval_runtime": 1.5637, | |
| "eval_samples_per_second": 78.659, | |
| "eval_steps_per_second": 10.232, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 26.49405288696289, | |
| "eval_runtime": 1.5536, | |
| "eval_samples_per_second": 79.17, | |
| "eval_steps_per_second": 10.298, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 24.659284591674805, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 79.576, | |
| "eval_steps_per_second": 10.351, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 23.44048309326172, | |
| "eval_runtime": 1.5478, | |
| "eval_samples_per_second": 79.467, | |
| "eval_steps_per_second": 10.337, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 21.999380111694336, | |
| "eval_runtime": 1.5447, | |
| "eval_samples_per_second": 79.626, | |
| "eval_steps_per_second": 10.358, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 6.774193548387097e-08, | |
| "loss": 27.5423, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 21.027385711669922, | |
| "eval_runtime": 1.5545, | |
| "eval_samples_per_second": 79.127, | |
| "eval_steps_per_second": 10.293, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 19.89065170288086, | |
| "eval_runtime": 1.565, | |
| "eval_samples_per_second": 78.592, | |
| "eval_steps_per_second": 10.223, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 19.33472442626953, | |
| "eval_runtime": 1.5542, | |
| "eval_samples_per_second": 79.141, | |
| "eval_steps_per_second": 10.295, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 18.324054718017578, | |
| "eval_runtime": 1.5611, | |
| "eval_samples_per_second": 78.793, | |
| "eval_steps_per_second": 10.249, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 17.521472930908203, | |
| "eval_runtime": 1.5648, | |
| "eval_samples_per_second": 78.603, | |
| "eval_steps_per_second": 10.225, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 16.96886444091797, | |
| "eval_runtime": 1.5541, | |
| "eval_samples_per_second": 79.144, | |
| "eval_steps_per_second": 10.295, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 16.298294067382812, | |
| "eval_runtime": 1.5454, | |
| "eval_samples_per_second": 79.59, | |
| "eval_steps_per_second": 10.353, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 15.870747566223145, | |
| "eval_runtime": 1.5451, | |
| "eval_samples_per_second": 79.609, | |
| "eval_steps_per_second": 10.356, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 6.661290322580646e-08, | |
| "loss": 18.4542, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 15.465510368347168, | |
| "eval_runtime": 1.5532, | |
| "eval_samples_per_second": 79.191, | |
| "eval_steps_per_second": 10.301, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 15.184890747070312, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.271, | |
| "eval_steps_per_second": 10.312, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 14.780122756958008, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 10.297, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 14.557552337646484, | |
| "eval_runtime": 1.5541, | |
| "eval_samples_per_second": 79.147, | |
| "eval_steps_per_second": 10.296, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 14.421510696411133, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.275, | |
| "eval_steps_per_second": 10.312, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 13.931785583496094, | |
| "eval_runtime": 1.5492, | |
| "eval_samples_per_second": 79.395, | |
| "eval_steps_per_second": 10.328, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 13.980083465576172, | |
| "eval_runtime": 1.5454, | |
| "eval_samples_per_second": 79.593, | |
| "eval_steps_per_second": 10.354, | |
| "step": 1922 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 13.709578514099121, | |
| "eval_runtime": 1.5464, | |
| "eval_samples_per_second": 79.537, | |
| "eval_steps_per_second": 10.346, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 32.26, | |
| "learning_rate": 6.548387096774194e-08, | |
| "loss": 13.9556, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 13.463862419128418, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.233, | |
| "eval_steps_per_second": 10.307, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 13.298738479614258, | |
| "eval_runtime": 1.5554, | |
| "eval_samples_per_second": 79.08, | |
| "eval_steps_per_second": 10.287, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 13.23029613494873, | |
| "eval_runtime": 1.5584, | |
| "eval_samples_per_second": 78.926, | |
| "eval_steps_per_second": 10.267, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 13.24497127532959, | |
| "eval_runtime": 1.5624, | |
| "eval_samples_per_second": 78.724, | |
| "eval_steps_per_second": 10.24, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 13.057371139526367, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.261, | |
| "eval_steps_per_second": 10.31, | |
| "step": 2294 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 12.902210235595703, | |
| "eval_runtime": 1.5456, | |
| "eval_samples_per_second": 79.583, | |
| "eval_steps_per_second": 10.352, | |
| "step": 2356 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 12.819963455200195, | |
| "eval_runtime": 1.5458, | |
| "eval_samples_per_second": 79.571, | |
| "eval_steps_per_second": 10.351, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 12.729530334472656, | |
| "eval_runtime": 1.5456, | |
| "eval_samples_per_second": 79.582, | |
| "eval_steps_per_second": 10.352, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "learning_rate": 6.435483870967743e-08, | |
| "loss": 12.111, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 12.840241432189941, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.277, | |
| "eval_steps_per_second": 10.312, | |
| "step": 2542 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 12.690611839294434, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.163, | |
| "eval_steps_per_second": 10.298, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 12.54220199584961, | |
| "eval_runtime": 1.554, | |
| "eval_samples_per_second": 79.15, | |
| "eval_steps_per_second": 10.296, | |
| "step": 2666 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 12.503222465515137, | |
| "eval_runtime": 1.5553, | |
| "eval_samples_per_second": 79.086, | |
| "eval_steps_per_second": 10.288, | |
| "step": 2728 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 12.296753883361816, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.275, | |
| "eval_steps_per_second": 10.312, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 12.332414627075195, | |
| "eval_runtime": 1.5484, | |
| "eval_samples_per_second": 79.436, | |
| "eval_steps_per_second": 10.333, | |
| "step": 2852 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 12.254257202148438, | |
| "eval_runtime": 1.551, | |
| "eval_samples_per_second": 79.301, | |
| "eval_steps_per_second": 10.316, | |
| "step": 2914 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 12.24339485168457, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.26, | |
| "eval_steps_per_second": 10.31, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 48.39, | |
| "learning_rate": 6.322580645161291e-08, | |
| "loss": 11.3304, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 12.251891136169434, | |
| "eval_runtime": 1.5529, | |
| "eval_samples_per_second": 79.207, | |
| "eval_steps_per_second": 10.303, | |
| "step": 3038 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 12.112042427062988, | |
| "eval_runtime": 1.56, | |
| "eval_samples_per_second": 78.845, | |
| "eval_steps_per_second": 10.256, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 12.196945190429688, | |
| "eval_runtime": 1.5565, | |
| "eval_samples_per_second": 79.023, | |
| "eval_steps_per_second": 10.279, | |
| "step": 3162 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 11.9977388381958, | |
| "eval_runtime": 1.5836, | |
| "eval_samples_per_second": 77.673, | |
| "eval_steps_per_second": 10.104, | |
| "step": 3224 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 12.175936698913574, | |
| "eval_runtime": 1.5513, | |
| "eval_samples_per_second": 79.287, | |
| "eval_steps_per_second": 10.314, | |
| "step": 3286 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 11.980809211730957, | |
| "eval_runtime": 1.546, | |
| "eval_samples_per_second": 79.559, | |
| "eval_steps_per_second": 10.349, | |
| "step": 3348 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 12.149847030639648, | |
| "eval_runtime": 1.5462, | |
| "eval_samples_per_second": 79.548, | |
| "eval_steps_per_second": 10.348, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 11.985103607177734, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 79.577, | |
| "eval_steps_per_second": 10.351, | |
| "step": 3472 | |
| }, | |
| { | |
| "epoch": 56.45, | |
| "learning_rate": 6.20967741935484e-08, | |
| "loss": 10.9471, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 12.080038070678711, | |
| "eval_runtime": 1.5551, | |
| "eval_samples_per_second": 79.095, | |
| "eval_steps_per_second": 10.289, | |
| "step": 3534 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 11.881911277770996, | |
| "eval_runtime": 1.5543, | |
| "eval_samples_per_second": 79.133, | |
| "eval_steps_per_second": 10.294, | |
| "step": 3596 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 12.009904861450195, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 79.328, | |
| "eval_steps_per_second": 10.319, | |
| "step": 3658 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 11.861567497253418, | |
| "eval_runtime": 1.5654, | |
| "eval_samples_per_second": 78.574, | |
| "eval_steps_per_second": 10.221, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 11.89500617980957, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.279, | |
| "eval_steps_per_second": 10.313, | |
| "step": 3782 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 11.830110549926758, | |
| "eval_runtime": 1.5521, | |
| "eval_samples_per_second": 79.249, | |
| "eval_steps_per_second": 10.309, | |
| "step": 3844 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 12.096732139587402, | |
| "eval_runtime": 1.5464, | |
| "eval_samples_per_second": 79.542, | |
| "eval_steps_per_second": 10.347, | |
| "step": 3906 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 11.837874412536621, | |
| "eval_runtime": 1.5533, | |
| "eval_samples_per_second": 79.184, | |
| "eval_steps_per_second": 10.3, | |
| "step": 3968 | |
| }, | |
| { | |
| "epoch": 64.52, | |
| "learning_rate": 6.096774193548388e-08, | |
| "loss": 10.6841, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 11.909323692321777, | |
| "eval_runtime": 1.5534, | |
| "eval_samples_per_second": 79.181, | |
| "eval_steps_per_second": 10.3, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 11.91748332977295, | |
| "eval_runtime": 1.5598, | |
| "eval_samples_per_second": 78.854, | |
| "eval_steps_per_second": 10.257, | |
| "step": 4092 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 11.73180103302002, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.365, | |
| "eval_steps_per_second": 10.324, | |
| "step": 4154 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 11.830022811889648, | |
| "eval_runtime": 1.5461, | |
| "eval_samples_per_second": 79.557, | |
| "eval_steps_per_second": 10.349, | |
| "step": 4216 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 11.599220275878906, | |
| "eval_runtime": 1.5555, | |
| "eval_samples_per_second": 79.074, | |
| "eval_steps_per_second": 10.286, | |
| "step": 4278 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 11.604393005371094, | |
| "eval_runtime": 1.5547, | |
| "eval_samples_per_second": 79.114, | |
| "eval_steps_per_second": 10.291, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 11.693653106689453, | |
| "eval_runtime": 1.5528, | |
| "eval_samples_per_second": 79.212, | |
| "eval_steps_per_second": 10.304, | |
| "step": 4402 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 11.596038818359375, | |
| "eval_runtime": 1.5565, | |
| "eval_samples_per_second": 79.023, | |
| "eval_steps_per_second": 10.279, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 72.58, | |
| "learning_rate": 5.983870967741936e-08, | |
| "loss": 10.542, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 11.545083045959473, | |
| "eval_runtime": 1.5539, | |
| "eval_samples_per_second": 79.157, | |
| "eval_steps_per_second": 10.297, | |
| "step": 4526 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 11.403264999389648, | |
| "eval_runtime": 1.5513, | |
| "eval_samples_per_second": 79.291, | |
| "eval_steps_per_second": 10.314, | |
| "step": 4588 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 11.480517387390137, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.28, | |
| "eval_steps_per_second": 10.313, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 11.539589881896973, | |
| "eval_runtime": 1.552, | |
| "eval_samples_per_second": 79.252, | |
| "eval_steps_per_second": 10.309, | |
| "step": 4712 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 11.492401123046875, | |
| "eval_runtime": 1.5522, | |
| "eval_samples_per_second": 79.245, | |
| "eval_steps_per_second": 10.308, | |
| "step": 4774 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 11.428875923156738, | |
| "eval_runtime": 1.5583, | |
| "eval_samples_per_second": 78.931, | |
| "eval_steps_per_second": 10.268, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 11.364572525024414, | |
| "eval_runtime": 1.5553, | |
| "eval_samples_per_second": 79.085, | |
| "eval_steps_per_second": 10.287, | |
| "step": 4898 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 11.362411499023438, | |
| "eval_runtime": 1.5451, | |
| "eval_samples_per_second": 79.605, | |
| "eval_steps_per_second": 10.355, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 80.65, | |
| "learning_rate": 5.870967741935484e-08, | |
| "loss": 10.4457, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 11.462297439575195, | |
| "eval_runtime": 1.5542, | |
| "eval_samples_per_second": 79.139, | |
| "eval_steps_per_second": 10.294, | |
| "step": 5022 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 11.522425651550293, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 10.297, | |
| "step": 5084 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 11.419597625732422, | |
| "eval_runtime": 1.5519, | |
| "eval_samples_per_second": 79.26, | |
| "eval_steps_per_second": 10.31, | |
| "step": 5146 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 11.435912132263184, | |
| "eval_runtime": 1.572, | |
| "eval_samples_per_second": 78.243, | |
| "eval_steps_per_second": 10.178, | |
| "step": 5208 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 11.434619903564453, | |
| "eval_runtime": 1.5634, | |
| "eval_samples_per_second": 78.674, | |
| "eval_steps_per_second": 10.234, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 11.463889122009277, | |
| "eval_runtime": 1.5521, | |
| "eval_samples_per_second": 79.248, | |
| "eval_steps_per_second": 10.309, | |
| "step": 5332 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 11.230652809143066, | |
| "eval_runtime": 1.5468, | |
| "eval_samples_per_second": 79.521, | |
| "eval_steps_per_second": 10.344, | |
| "step": 5394 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 11.526171684265137, | |
| "eval_runtime": 1.5455, | |
| "eval_samples_per_second": 79.584, | |
| "eval_steps_per_second": 10.352, | |
| "step": 5456 | |
| }, | |
| { | |
| "epoch": 88.71, | |
| "learning_rate": 5.758064516129033e-08, | |
| "loss": 10.3854, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 11.665349006652832, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 79.329, | |
| "eval_steps_per_second": 10.319, | |
| "step": 5518 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 11.3471040725708, | |
| "eval_runtime": 1.5506, | |
| "eval_samples_per_second": 79.325, | |
| "eval_steps_per_second": 10.319, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 11.304780960083008, | |
| "eval_runtime": 1.5529, | |
| "eval_samples_per_second": 79.209, | |
| "eval_steps_per_second": 10.304, | |
| "step": 5642 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 11.36330509185791, | |
| "eval_runtime": 1.5593, | |
| "eval_samples_per_second": 78.88, | |
| "eval_steps_per_second": 10.261, | |
| "step": 5704 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 11.343398094177246, | |
| "eval_runtime": 1.5672, | |
| "eval_samples_per_second": 78.483, | |
| "eval_steps_per_second": 10.209, | |
| "step": 5766 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 11.257966041564941, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.263, | |
| "eval_steps_per_second": 10.311, | |
| "step": 5828 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 11.270854949951172, | |
| "eval_runtime": 1.5445, | |
| "eval_samples_per_second": 79.635, | |
| "eval_steps_per_second": 10.359, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 11.198323249816895, | |
| "eval_runtime": 1.5471, | |
| "eval_samples_per_second": 79.503, | |
| "eval_steps_per_second": 10.342, | |
| "step": 5952 | |
| }, | |
| { | |
| "epoch": 96.77, | |
| "learning_rate": 5.6451612903225805e-08, | |
| "loss": 10.324, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 11.22177791595459, | |
| "eval_runtime": 1.5536, | |
| "eval_samples_per_second": 79.171, | |
| "eval_steps_per_second": 10.299, | |
| "step": 6014 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 11.330657005310059, | |
| "eval_runtime": 1.5691, | |
| "eval_samples_per_second": 78.388, | |
| "eval_steps_per_second": 10.197, | |
| "step": 6076 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 11.203608512878418, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.972, | |
| "eval_steps_per_second": 10.273, | |
| "step": 6138 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 11.372391700744629, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.216, | |
| "eval_steps_per_second": 10.305, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_loss": 11.344269752502441, | |
| "eval_runtime": 1.5528, | |
| "eval_samples_per_second": 79.21, | |
| "eval_steps_per_second": 10.304, | |
| "step": 6262 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_loss": 11.264634132385254, | |
| "eval_runtime": 1.5533, | |
| "eval_samples_per_second": 79.188, | |
| "eval_steps_per_second": 10.301, | |
| "step": 6324 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_loss": 11.27165699005127, | |
| "eval_runtime": 1.549, | |
| "eval_samples_per_second": 79.408, | |
| "eval_steps_per_second": 10.33, | |
| "step": 6386 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_loss": 11.310558319091797, | |
| "eval_runtime": 1.5464, | |
| "eval_samples_per_second": 79.542, | |
| "eval_steps_per_second": 10.347, | |
| "step": 6448 | |
| }, | |
| { | |
| "epoch": 104.84, | |
| "learning_rate": 5.532258064516129e-08, | |
| "loss": 10.2981, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_loss": 11.243507385253906, | |
| "eval_runtime": 1.5536, | |
| "eval_samples_per_second": 79.17, | |
| "eval_steps_per_second": 10.298, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_loss": 11.249150276184082, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.261, | |
| "eval_steps_per_second": 10.31, | |
| "step": 6572 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_loss": 11.111257553100586, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.218, | |
| "eval_steps_per_second": 10.305, | |
| "step": 6634 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_loss": 11.210649490356445, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 78.999, | |
| "eval_steps_per_second": 10.276, | |
| "step": 6696 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_loss": 11.214300155639648, | |
| "eval_runtime": 1.5747, | |
| "eval_samples_per_second": 78.112, | |
| "eval_steps_per_second": 10.161, | |
| "step": 6758 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_loss": 11.015155792236328, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.274, | |
| "eval_steps_per_second": 10.312, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_loss": 11.08711051940918, | |
| "eval_runtime": 1.5448, | |
| "eval_samples_per_second": 79.621, | |
| "eval_steps_per_second": 10.357, | |
| "step": 6882 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_loss": 11.098098754882812, | |
| "eval_runtime": 1.5449, | |
| "eval_samples_per_second": 79.617, | |
| "eval_steps_per_second": 10.357, | |
| "step": 6944 | |
| }, | |
| { | |
| "epoch": 112.9, | |
| "learning_rate": 5.4193548387096774e-08, | |
| "loss": 10.2536, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_loss": 11.243887901306152, | |
| "eval_runtime": 1.5475, | |
| "eval_samples_per_second": 79.483, | |
| "eval_steps_per_second": 10.339, | |
| "step": 7006 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_loss": 11.156224250793457, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 79.327, | |
| "eval_steps_per_second": 10.319, | |
| "step": 7068 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_loss": 11.118559837341309, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.363, | |
| "eval_steps_per_second": 10.324, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_loss": 11.2282133102417, | |
| "eval_runtime": 1.562, | |
| "eval_samples_per_second": 78.744, | |
| "eval_steps_per_second": 10.243, | |
| "step": 7192 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_loss": 11.289180755615234, | |
| "eval_runtime": 1.5484, | |
| "eval_samples_per_second": 79.437, | |
| "eval_steps_per_second": 10.333, | |
| "step": 7254 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_loss": 11.165923118591309, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.263, | |
| "eval_steps_per_second": 10.311, | |
| "step": 7316 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_loss": 11.34392261505127, | |
| "eval_runtime": 1.545, | |
| "eval_samples_per_second": 79.613, | |
| "eval_steps_per_second": 10.356, | |
| "step": 7378 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_loss": 11.199868202209473, | |
| "eval_runtime": 1.5455, | |
| "eval_samples_per_second": 79.586, | |
| "eval_steps_per_second": 10.353, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 120.97, | |
| "learning_rate": 5.306451612903226e-08, | |
| "loss": 10.2336, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_loss": 11.250391960144043, | |
| "eval_runtime": 1.5504, | |
| "eval_samples_per_second": 79.337, | |
| "eval_steps_per_second": 10.32, | |
| "step": 7502 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_loss": 11.289613723754883, | |
| "eval_runtime": 1.5534, | |
| "eval_samples_per_second": 79.18, | |
| "eval_steps_per_second": 10.3, | |
| "step": 7564 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_loss": 11.068822860717773, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.158, | |
| "eval_steps_per_second": 10.297, | |
| "step": 7626 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_loss": 11.16740894317627, | |
| "eval_runtime": 1.5519, | |
| "eval_samples_per_second": 79.258, | |
| "eval_steps_per_second": 10.31, | |
| "step": 7688 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_loss": 11.207221984863281, | |
| "eval_runtime": 1.5529, | |
| "eval_samples_per_second": 79.204, | |
| "eval_steps_per_second": 10.303, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_loss": 11.035326957702637, | |
| "eval_runtime": 1.552, | |
| "eval_samples_per_second": 79.253, | |
| "eval_steps_per_second": 10.309, | |
| "step": 7812 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_loss": 11.048843383789062, | |
| "eval_runtime": 1.548, | |
| "eval_samples_per_second": 79.46, | |
| "eval_steps_per_second": 10.336, | |
| "step": 7874 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_loss": 11.093210220336914, | |
| "eval_runtime": 1.5454, | |
| "eval_samples_per_second": 79.59, | |
| "eval_steps_per_second": 10.353, | |
| "step": 7936 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_loss": 11.070518493652344, | |
| "eval_runtime": 1.5446, | |
| "eval_samples_per_second": 79.63, | |
| "eval_steps_per_second": 10.358, | |
| "step": 7998 | |
| }, | |
| { | |
| "epoch": 129.03, | |
| "learning_rate": 5.193548387096775e-08, | |
| "loss": 10.2101, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_loss": 11.219257354736328, | |
| "eval_runtime": 1.5539, | |
| "eval_samples_per_second": 79.157, | |
| "eval_steps_per_second": 10.297, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_loss": 11.227781295776367, | |
| "eval_runtime": 1.5509, | |
| "eval_samples_per_second": 79.307, | |
| "eval_steps_per_second": 10.316, | |
| "step": 8122 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_loss": 11.136541366577148, | |
| "eval_runtime": 1.5783, | |
| "eval_samples_per_second": 77.932, | |
| "eval_steps_per_second": 10.137, | |
| "step": 8184 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_loss": 11.035323143005371, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 10.297, | |
| "step": 8246 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_loss": 11.014593124389648, | |
| "eval_runtime": 1.5521, | |
| "eval_samples_per_second": 79.246, | |
| "eval_steps_per_second": 10.308, | |
| "step": 8308 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_loss": 11.237153053283691, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 79.575, | |
| "eval_steps_per_second": 10.351, | |
| "step": 8370 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_loss": 11.104418754577637, | |
| "eval_runtime": 1.5452, | |
| "eval_samples_per_second": 79.6, | |
| "eval_steps_per_second": 10.355, | |
| "step": 8432 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_loss": 11.134021759033203, | |
| "eval_runtime": 1.5476, | |
| "eval_samples_per_second": 79.478, | |
| "eval_steps_per_second": 10.339, | |
| "step": 8494 | |
| }, | |
| { | |
| "epoch": 137.1, | |
| "learning_rate": 5.0806451612903234e-08, | |
| "loss": 10.1991, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_loss": 11.075273513793945, | |
| "eval_runtime": 1.5484, | |
| "eval_samples_per_second": 79.436, | |
| "eval_steps_per_second": 10.333, | |
| "step": 8556 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_loss": 11.021109580993652, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.391, | |
| "eval_steps_per_second": 10.327, | |
| "step": 8618 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_loss": 10.930947303771973, | |
| "eval_runtime": 1.5551, | |
| "eval_samples_per_second": 79.096, | |
| "eval_steps_per_second": 10.289, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_loss": 10.977023124694824, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.263, | |
| "eval_steps_per_second": 10.311, | |
| "step": 8742 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_loss": 11.079144477844238, | |
| "eval_runtime": 1.5523, | |
| "eval_samples_per_second": 79.238, | |
| "eval_steps_per_second": 10.307, | |
| "step": 8804 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_loss": 11.116453170776367, | |
| "eval_runtime": 1.5541, | |
| "eval_samples_per_second": 79.147, | |
| "eval_steps_per_second": 10.296, | |
| "step": 8866 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_loss": 10.936894416809082, | |
| "eval_runtime": 1.5532, | |
| "eval_samples_per_second": 79.19, | |
| "eval_steps_per_second": 10.301, | |
| "step": 8928 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_loss": 11.121102333068848, | |
| "eval_runtime": 1.5444, | |
| "eval_samples_per_second": 79.641, | |
| "eval_steps_per_second": 10.36, | |
| "step": 8990 | |
| }, | |
| { | |
| "epoch": 145.16, | |
| "learning_rate": 4.967741935483872e-08, | |
| "loss": 10.1925, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_loss": 11.074503898620605, | |
| "eval_runtime": 1.5533, | |
| "eval_samples_per_second": 79.185, | |
| "eval_steps_per_second": 10.301, | |
| "step": 9052 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_loss": 11.104596138000488, | |
| "eval_runtime": 1.553, | |
| "eval_samples_per_second": 79.201, | |
| "eval_steps_per_second": 10.303, | |
| "step": 9114 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_loss": 11.025848388671875, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.234, | |
| "eval_steps_per_second": 10.307, | |
| "step": 9176 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_loss": 11.02661418914795, | |
| "eval_runtime": 1.5531, | |
| "eval_samples_per_second": 79.198, | |
| "eval_steps_per_second": 10.302, | |
| "step": 9238 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_loss": 11.253996849060059, | |
| "eval_runtime": 1.5526, | |
| "eval_samples_per_second": 79.224, | |
| "eval_steps_per_second": 10.306, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_loss": 10.970392227172852, | |
| "eval_runtime": 1.5474, | |
| "eval_samples_per_second": 79.487, | |
| "eval_steps_per_second": 10.34, | |
| "step": 9362 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_loss": 11.034109115600586, | |
| "eval_runtime": 1.5453, | |
| "eval_samples_per_second": 79.599, | |
| "eval_steps_per_second": 10.354, | |
| "step": 9424 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_loss": 11.111385345458984, | |
| "eval_runtime": 1.5448, | |
| "eval_samples_per_second": 79.622, | |
| "eval_steps_per_second": 10.357, | |
| "step": 9486 | |
| }, | |
| { | |
| "epoch": 153.23, | |
| "learning_rate": 4.85483870967742e-08, | |
| "loss": 10.1538, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_loss": 11.022419929504395, | |
| "eval_runtime": 1.5528, | |
| "eval_samples_per_second": 79.213, | |
| "eval_steps_per_second": 10.304, | |
| "step": 9548 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_loss": 10.915043830871582, | |
| "eval_runtime": 1.6252, | |
| "eval_samples_per_second": 75.682, | |
| "eval_steps_per_second": 9.845, | |
| "step": 9610 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_loss": 10.930474281311035, | |
| "eval_runtime": 1.5606, | |
| "eval_samples_per_second": 78.816, | |
| "eval_steps_per_second": 10.252, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_loss": 11.069900512695312, | |
| "eval_runtime": 1.5514, | |
| "eval_samples_per_second": 79.281, | |
| "eval_steps_per_second": 10.313, | |
| "step": 9734 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_loss": 10.990084648132324, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.23, | |
| "eval_steps_per_second": 10.306, | |
| "step": 9796 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_loss": 11.068836212158203, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.392, | |
| "eval_steps_per_second": 10.327, | |
| "step": 9858 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_loss": 10.933384895324707, | |
| "eval_runtime": 1.5461, | |
| "eval_samples_per_second": 79.553, | |
| "eval_steps_per_second": 10.348, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_loss": 10.985239028930664, | |
| "eval_runtime": 1.5514, | |
| "eval_samples_per_second": 79.283, | |
| "eval_steps_per_second": 10.313, | |
| "step": 9982 | |
| }, | |
| { | |
| "epoch": 161.29, | |
| "learning_rate": 4.741935483870968e-08, | |
| "loss": 10.1494, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_loss": 10.903247833251953, | |
| "eval_runtime": 1.5599, | |
| "eval_samples_per_second": 78.85, | |
| "eval_steps_per_second": 10.257, | |
| "step": 10044 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_loss": 10.96179485321045, | |
| "eval_runtime": 1.5509, | |
| "eval_samples_per_second": 79.309, | |
| "eval_steps_per_second": 10.317, | |
| "step": 10106 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_loss": 10.947345733642578, | |
| "eval_runtime": 1.5514, | |
| "eval_samples_per_second": 79.286, | |
| "eval_steps_per_second": 10.314, | |
| "step": 10168 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_loss": 11.153131484985352, | |
| "eval_runtime": 1.5559, | |
| "eval_samples_per_second": 79.053, | |
| "eval_steps_per_second": 10.283, | |
| "step": 10230 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_loss": 10.846189498901367, | |
| "eval_runtime": 1.5522, | |
| "eval_samples_per_second": 79.244, | |
| "eval_steps_per_second": 10.308, | |
| "step": 10292 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_loss": 10.957653045654297, | |
| "eval_runtime": 1.5541, | |
| "eval_samples_per_second": 79.147, | |
| "eval_steps_per_second": 10.296, | |
| "step": 10354 | |
| }, | |
| { | |
| "epoch": 168.0, | |
| "eval_loss": 10.935074806213379, | |
| "eval_runtime": 1.5492, | |
| "eval_samples_per_second": 79.394, | |
| "eval_steps_per_second": 10.328, | |
| "step": 10416 | |
| }, | |
| { | |
| "epoch": 169.0, | |
| "eval_loss": 11.212529182434082, | |
| "eval_runtime": 1.545, | |
| "eval_samples_per_second": 79.61, | |
| "eval_steps_per_second": 10.356, | |
| "step": 10478 | |
| }, | |
| { | |
| "epoch": 169.35, | |
| "learning_rate": 4.6290322580645165e-08, | |
| "loss": 10.1424, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 170.0, | |
| "eval_loss": 11.054618835449219, | |
| "eval_runtime": 1.5612, | |
| "eval_samples_per_second": 78.784, | |
| "eval_steps_per_second": 10.248, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 171.0, | |
| "eval_loss": 10.993365287780762, | |
| "eval_runtime": 1.5547, | |
| "eval_samples_per_second": 79.116, | |
| "eval_steps_per_second": 10.292, | |
| "step": 10602 | |
| }, | |
| { | |
| "epoch": 172.0, | |
| "eval_loss": 10.891836166381836, | |
| "eval_runtime": 1.5523, | |
| "eval_samples_per_second": 79.24, | |
| "eval_steps_per_second": 10.308, | |
| "step": 10664 | |
| }, | |
| { | |
| "epoch": 173.0, | |
| "eval_loss": 10.886784553527832, | |
| "eval_runtime": 1.5513, | |
| "eval_samples_per_second": 79.29, | |
| "eval_steps_per_second": 10.314, | |
| "step": 10726 | |
| }, | |
| { | |
| "epoch": 174.0, | |
| "eval_loss": 11.039985656738281, | |
| "eval_runtime": 1.6601, | |
| "eval_samples_per_second": 74.092, | |
| "eval_steps_per_second": 9.638, | |
| "step": 10788 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "eval_loss": 11.119784355163574, | |
| "eval_runtime": 1.5449, | |
| "eval_samples_per_second": 79.617, | |
| "eval_steps_per_second": 10.357, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 176.0, | |
| "eval_loss": 11.159457206726074, | |
| "eval_runtime": 1.5467, | |
| "eval_samples_per_second": 79.525, | |
| "eval_steps_per_second": 10.345, | |
| "step": 10912 | |
| }, | |
| { | |
| "epoch": 177.0, | |
| "eval_loss": 11.113701820373535, | |
| "eval_runtime": 1.5449, | |
| "eval_samples_per_second": 79.616, | |
| "eval_steps_per_second": 10.357, | |
| "step": 10974 | |
| }, | |
| { | |
| "epoch": 177.42, | |
| "learning_rate": 4.516129032258065e-08, | |
| "loss": 10.1181, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 178.0, | |
| "eval_loss": 11.199760437011719, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 10.297, | |
| "step": 11036 | |
| }, | |
| { | |
| "epoch": 179.0, | |
| "eval_loss": 11.049378395080566, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.215, | |
| "eval_steps_per_second": 10.304, | |
| "step": 11098 | |
| }, | |
| { | |
| "epoch": 180.0, | |
| "eval_loss": 10.948933601379395, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.216, | |
| "eval_steps_per_second": 10.305, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 181.0, | |
| "eval_loss": 11.02480411529541, | |
| "eval_runtime": 1.5509, | |
| "eval_samples_per_second": 79.306, | |
| "eval_steps_per_second": 10.316, | |
| "step": 11222 | |
| }, | |
| { | |
| "epoch": 182.0, | |
| "eval_loss": 10.991153717041016, | |
| "eval_runtime": 1.5561, | |
| "eval_samples_per_second": 79.045, | |
| "eval_steps_per_second": 10.282, | |
| "step": 11284 | |
| }, | |
| { | |
| "epoch": 183.0, | |
| "eval_loss": 10.922146797180176, | |
| "eval_runtime": 1.5488, | |
| "eval_samples_per_second": 79.416, | |
| "eval_steps_per_second": 10.331, | |
| "step": 11346 | |
| }, | |
| { | |
| "epoch": 184.0, | |
| "eval_loss": 11.055255889892578, | |
| "eval_runtime": 1.547, | |
| "eval_samples_per_second": 79.508, | |
| "eval_steps_per_second": 10.343, | |
| "step": 11408 | |
| }, | |
| { | |
| "epoch": 185.0, | |
| "eval_loss": 11.005462646484375, | |
| "eval_runtime": 1.5452, | |
| "eval_samples_per_second": 79.6, | |
| "eval_steps_per_second": 10.354, | |
| "step": 11470 | |
| }, | |
| { | |
| "epoch": 185.48, | |
| "learning_rate": 4.4032258064516134e-08, | |
| "loss": 10.1165, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 186.0, | |
| "eval_loss": 11.112872123718262, | |
| "eval_runtime": 1.5624, | |
| "eval_samples_per_second": 78.724, | |
| "eval_steps_per_second": 10.24, | |
| "step": 11532 | |
| }, | |
| { | |
| "epoch": 187.0, | |
| "eval_loss": 11.082246780395508, | |
| "eval_runtime": 1.5529, | |
| "eval_samples_per_second": 79.209, | |
| "eval_steps_per_second": 10.304, | |
| "step": 11594 | |
| }, | |
| { | |
| "epoch": 188.0, | |
| "eval_loss": 11.050854682922363, | |
| "eval_runtime": 1.5513, | |
| "eval_samples_per_second": 79.287, | |
| "eval_steps_per_second": 10.314, | |
| "step": 11656 | |
| }, | |
| { | |
| "epoch": 189.0, | |
| "eval_loss": 11.088144302368164, | |
| "eval_runtime": 1.5522, | |
| "eval_samples_per_second": 79.24, | |
| "eval_steps_per_second": 10.308, | |
| "step": 11718 | |
| }, | |
| { | |
| "epoch": 190.0, | |
| "eval_loss": 10.890948295593262, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.263, | |
| "eval_steps_per_second": 10.311, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 191.0, | |
| "eval_loss": 11.048895835876465, | |
| "eval_runtime": 1.5439, | |
| "eval_samples_per_second": 79.668, | |
| "eval_steps_per_second": 10.363, | |
| "step": 11842 | |
| }, | |
| { | |
| "epoch": 192.0, | |
| "eval_loss": 10.934896469116211, | |
| "eval_runtime": 1.548, | |
| "eval_samples_per_second": 79.46, | |
| "eval_steps_per_second": 10.336, | |
| "step": 11904 | |
| }, | |
| { | |
| "epoch": 193.0, | |
| "eval_loss": 10.882064819335938, | |
| "eval_runtime": 1.5473, | |
| "eval_samples_per_second": 79.492, | |
| "eval_steps_per_second": 10.34, | |
| "step": 11966 | |
| }, | |
| { | |
| "epoch": 193.55, | |
| "learning_rate": 4.290322580645162e-08, | |
| "loss": 10.1021, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 194.0, | |
| "eval_loss": 11.055244445800781, | |
| "eval_runtime": 1.5566, | |
| "eval_samples_per_second": 79.017, | |
| "eval_steps_per_second": 10.279, | |
| "step": 12028 | |
| }, | |
| { | |
| "epoch": 195.0, | |
| "eval_loss": 11.152359962463379, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.217, | |
| "eval_steps_per_second": 10.305, | |
| "step": 12090 | |
| }, | |
| { | |
| "epoch": 196.0, | |
| "eval_loss": 11.008437156677246, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.158, | |
| "eval_steps_per_second": 10.297, | |
| "step": 12152 | |
| }, | |
| { | |
| "epoch": 197.0, | |
| "eval_loss": 11.086997032165527, | |
| "eval_runtime": 1.5634, | |
| "eval_samples_per_second": 78.677, | |
| "eval_steps_per_second": 10.234, | |
| "step": 12214 | |
| }, | |
| { | |
| "epoch": 198.0, | |
| "eval_loss": 10.842860221862793, | |
| "eval_runtime": 1.5635, | |
| "eval_samples_per_second": 78.671, | |
| "eval_steps_per_second": 10.234, | |
| "step": 12276 | |
| }, | |
| { | |
| "epoch": 199.0, | |
| "eval_loss": 11.010416030883789, | |
| "eval_runtime": 1.5454, | |
| "eval_samples_per_second": 79.593, | |
| "eval_steps_per_second": 10.354, | |
| "step": 12338 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_loss": 10.92686939239502, | |
| "eval_runtime": 1.545, | |
| "eval_samples_per_second": 79.613, | |
| "eval_steps_per_second": 10.356, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 201.0, | |
| "eval_loss": 10.987348556518555, | |
| "eval_runtime": 1.548, | |
| "eval_samples_per_second": 79.458, | |
| "eval_steps_per_second": 10.336, | |
| "step": 12462 | |
| }, | |
| { | |
| "epoch": 201.61, | |
| "learning_rate": 4.17741935483871e-08, | |
| "loss": 10.1022, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 202.0, | |
| "eval_loss": 10.98776912689209, | |
| "eval_runtime": 1.57, | |
| "eval_samples_per_second": 78.342, | |
| "eval_steps_per_second": 10.191, | |
| "step": 12524 | |
| }, | |
| { | |
| "epoch": 203.0, | |
| "eval_loss": 10.882826805114746, | |
| "eval_runtime": 1.5543, | |
| "eval_samples_per_second": 79.135, | |
| "eval_steps_per_second": 10.294, | |
| "step": 12586 | |
| }, | |
| { | |
| "epoch": 204.0, | |
| "eval_loss": 11.043395042419434, | |
| "eval_runtime": 1.5636, | |
| "eval_samples_per_second": 78.662, | |
| "eval_steps_per_second": 10.233, | |
| "step": 12648 | |
| }, | |
| { | |
| "epoch": 205.0, | |
| "eval_loss": 10.953902244567871, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.972, | |
| "eval_steps_per_second": 10.273, | |
| "step": 12710 | |
| }, | |
| { | |
| "epoch": 206.0, | |
| "eval_loss": 10.684782028198242, | |
| "eval_runtime": 1.5525, | |
| "eval_samples_per_second": 79.228, | |
| "eval_steps_per_second": 10.306, | |
| "step": 12772 | |
| }, | |
| { | |
| "epoch": 207.0, | |
| "eval_loss": 11.177257537841797, | |
| "eval_runtime": 1.5483, | |
| "eval_samples_per_second": 79.441, | |
| "eval_steps_per_second": 10.334, | |
| "step": 12834 | |
| }, | |
| { | |
| "epoch": 208.0, | |
| "eval_loss": 10.996722221374512, | |
| "eval_runtime": 1.5543, | |
| "eval_samples_per_second": 79.138, | |
| "eval_steps_per_second": 10.294, | |
| "step": 12896 | |
| }, | |
| { | |
| "epoch": 209.0, | |
| "eval_loss": 10.998943328857422, | |
| "eval_runtime": 1.5532, | |
| "eval_samples_per_second": 79.19, | |
| "eval_steps_per_second": 10.301, | |
| "step": 12958 | |
| }, | |
| { | |
| "epoch": 209.68, | |
| "learning_rate": 4.064516129032259e-08, | |
| "loss": 10.0962, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 210.0, | |
| "eval_loss": 11.20012378692627, | |
| "eval_runtime": 1.5557, | |
| "eval_samples_per_second": 79.063, | |
| "eval_steps_per_second": 10.285, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 211.0, | |
| "eval_loss": 10.965839385986328, | |
| "eval_runtime": 1.554, | |
| "eval_samples_per_second": 79.148, | |
| "eval_steps_per_second": 10.296, | |
| "step": 13082 | |
| }, | |
| { | |
| "epoch": 212.0, | |
| "eval_loss": 11.009934425354004, | |
| "eval_runtime": 1.5719, | |
| "eval_samples_per_second": 78.252, | |
| "eval_steps_per_second": 10.179, | |
| "step": 13144 | |
| }, | |
| { | |
| "epoch": 213.0, | |
| "eval_loss": 11.053404808044434, | |
| "eval_runtime": 1.5544, | |
| "eval_samples_per_second": 79.129, | |
| "eval_steps_per_second": 10.293, | |
| "step": 13206 | |
| }, | |
| { | |
| "epoch": 214.0, | |
| "eval_loss": 11.185773849487305, | |
| "eval_runtime": 1.5545, | |
| "eval_samples_per_second": 79.125, | |
| "eval_steps_per_second": 10.293, | |
| "step": 13268 | |
| }, | |
| { | |
| "epoch": 215.0, | |
| "eval_loss": 11.044096946716309, | |
| "eval_runtime": 1.5449, | |
| "eval_samples_per_second": 79.615, | |
| "eval_steps_per_second": 10.356, | |
| "step": 13330 | |
| }, | |
| { | |
| "epoch": 216.0, | |
| "eval_loss": 11.181927680969238, | |
| "eval_runtime": 1.5461, | |
| "eval_samples_per_second": 79.553, | |
| "eval_steps_per_second": 10.348, | |
| "step": 13392 | |
| }, | |
| { | |
| "epoch": 217.0, | |
| "eval_loss": 11.01004695892334, | |
| "eval_runtime": 1.5451, | |
| "eval_samples_per_second": 79.607, | |
| "eval_steps_per_second": 10.355, | |
| "step": 13454 | |
| }, | |
| { | |
| "epoch": 217.74, | |
| "learning_rate": 3.951612903225807e-08, | |
| "loss": 10.0861, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 218.0, | |
| "eval_loss": 11.007074356079102, | |
| "eval_runtime": 1.5582, | |
| "eval_samples_per_second": 78.937, | |
| "eval_steps_per_second": 10.268, | |
| "step": 13516 | |
| }, | |
| { | |
| "epoch": 219.0, | |
| "eval_loss": 11.145269393920898, | |
| "eval_runtime": 1.5533, | |
| "eval_samples_per_second": 79.188, | |
| "eval_steps_per_second": 10.301, | |
| "step": 13578 | |
| }, | |
| { | |
| "epoch": 220.0, | |
| "eval_loss": 10.985397338867188, | |
| "eval_runtime": 1.5653, | |
| "eval_samples_per_second": 78.577, | |
| "eval_steps_per_second": 10.221, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 221.0, | |
| "eval_loss": 11.120607376098633, | |
| "eval_runtime": 1.5535, | |
| "eval_samples_per_second": 79.174, | |
| "eval_steps_per_second": 10.299, | |
| "step": 13702 | |
| }, | |
| { | |
| "epoch": 222.0, | |
| "eval_loss": 11.069469451904297, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 10.297, | |
| "step": 13764 | |
| }, | |
| { | |
| "epoch": 223.0, | |
| "eval_loss": 11.070048332214355, | |
| "eval_runtime": 1.5473, | |
| "eval_samples_per_second": 79.495, | |
| "eval_steps_per_second": 10.341, | |
| "step": 13826 | |
| }, | |
| { | |
| "epoch": 224.0, | |
| "eval_loss": 10.968293190002441, | |
| "eval_runtime": 1.547, | |
| "eval_samples_per_second": 79.509, | |
| "eval_steps_per_second": 10.343, | |
| "step": 13888 | |
| }, | |
| { | |
| "epoch": 225.0, | |
| "eval_loss": 10.9319486618042, | |
| "eval_runtime": 1.5452, | |
| "eval_samples_per_second": 79.599, | |
| "eval_steps_per_second": 10.354, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 225.81, | |
| "learning_rate": 3.838709677419355e-08, | |
| "loss": 10.0808, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 226.0, | |
| "eval_loss": 10.993424415588379, | |
| "eval_runtime": 1.57, | |
| "eval_samples_per_second": 78.345, | |
| "eval_steps_per_second": 10.191, | |
| "step": 14012 | |
| }, | |
| { | |
| "epoch": 227.0, | |
| "eval_loss": 10.878746032714844, | |
| "eval_runtime": 1.5608, | |
| "eval_samples_per_second": 78.805, | |
| "eval_steps_per_second": 10.251, | |
| "step": 14074 | |
| }, | |
| { | |
| "epoch": 228.0, | |
| "eval_loss": 10.905098915100098, | |
| "eval_runtime": 1.5539, | |
| "eval_samples_per_second": 79.155, | |
| "eval_steps_per_second": 10.297, | |
| "step": 14136 | |
| }, | |
| { | |
| "epoch": 229.0, | |
| "eval_loss": 11.037513732910156, | |
| "eval_runtime": 1.5551, | |
| "eval_samples_per_second": 79.093, | |
| "eval_steps_per_second": 10.289, | |
| "step": 14198 | |
| }, | |
| { | |
| "epoch": 230.0, | |
| "eval_loss": 11.025934219360352, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.161, | |
| "eval_steps_per_second": 10.297, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 231.0, | |
| "eval_loss": 11.063486099243164, | |
| "eval_runtime": 1.5562, | |
| "eval_samples_per_second": 79.041, | |
| "eval_steps_per_second": 10.282, | |
| "step": 14322 | |
| }, | |
| { | |
| "epoch": 232.0, | |
| "eval_loss": 10.88222885131836, | |
| "eval_runtime": 1.5487, | |
| "eval_samples_per_second": 79.422, | |
| "eval_steps_per_second": 10.331, | |
| "step": 14384 | |
| }, | |
| { | |
| "epoch": 233.0, | |
| "eval_loss": 10.89100170135498, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 79.576, | |
| "eval_steps_per_second": 10.351, | |
| "step": 14446 | |
| }, | |
| { | |
| "epoch": 233.87, | |
| "learning_rate": 3.7258064516129034e-08, | |
| "loss": 10.0768, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 234.0, | |
| "eval_loss": 10.974419593811035, | |
| "eval_runtime": 1.5538, | |
| "eval_samples_per_second": 79.16, | |
| "eval_steps_per_second": 10.297, | |
| "step": 14508 | |
| }, | |
| { | |
| "epoch": 235.0, | |
| "eval_loss": 11.042181015014648, | |
| "eval_runtime": 1.58, | |
| "eval_samples_per_second": 77.85, | |
| "eval_steps_per_second": 10.127, | |
| "step": 14570 | |
| }, | |
| { | |
| "epoch": 236.0, | |
| "eval_loss": 11.03979778289795, | |
| "eval_runtime": 1.5648, | |
| "eval_samples_per_second": 78.605, | |
| "eval_steps_per_second": 10.225, | |
| "step": 14632 | |
| }, | |
| { | |
| "epoch": 237.0, | |
| "eval_loss": 10.850703239440918, | |
| "eval_runtime": 1.5587, | |
| "eval_samples_per_second": 78.914, | |
| "eval_steps_per_second": 10.265, | |
| "step": 14694 | |
| }, | |
| { | |
| "epoch": 238.0, | |
| "eval_loss": 11.022680282592773, | |
| "eval_runtime": 1.5543, | |
| "eval_samples_per_second": 79.135, | |
| "eval_steps_per_second": 10.294, | |
| "step": 14756 | |
| }, | |
| { | |
| "epoch": 239.0, | |
| "eval_loss": 11.027267456054688, | |
| "eval_runtime": 1.5884, | |
| "eval_samples_per_second": 77.438, | |
| "eval_steps_per_second": 10.073, | |
| "step": 14818 | |
| }, | |
| { | |
| "epoch": 240.0, | |
| "eval_loss": 11.07776165008545, | |
| "eval_runtime": 1.5492, | |
| "eval_samples_per_second": 79.395, | |
| "eval_steps_per_second": 10.328, | |
| "step": 14880 | |
| }, | |
| { | |
| "epoch": 241.0, | |
| "eval_loss": 11.077691078186035, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.393, | |
| "eval_steps_per_second": 10.328, | |
| "step": 14942 | |
| }, | |
| { | |
| "epoch": 241.94, | |
| "learning_rate": 3.612903225806452e-08, | |
| "loss": 10.0792, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 242.0, | |
| "eval_loss": 10.942319869995117, | |
| "eval_runtime": 1.5569, | |
| "eval_samples_per_second": 79.005, | |
| "eval_steps_per_second": 10.277, | |
| "step": 15004 | |
| }, | |
| { | |
| "epoch": 243.0, | |
| "eval_loss": 11.226703643798828, | |
| "eval_runtime": 1.5593, | |
| "eval_samples_per_second": 78.88, | |
| "eval_steps_per_second": 10.261, | |
| "step": 15066 | |
| }, | |
| { | |
| "epoch": 244.0, | |
| "eval_loss": 10.85287094116211, | |
| "eval_runtime": 1.564, | |
| "eval_samples_per_second": 78.644, | |
| "eval_steps_per_second": 10.23, | |
| "step": 15128 | |
| }, | |
| { | |
| "epoch": 245.0, | |
| "eval_loss": 11.056612968444824, | |
| "eval_runtime": 1.5825, | |
| "eval_samples_per_second": 77.725, | |
| "eval_steps_per_second": 10.111, | |
| "step": 15190 | |
| }, | |
| { | |
| "epoch": 246.0, | |
| "eval_loss": 10.887572288513184, | |
| "eval_runtime": 1.5637, | |
| "eval_samples_per_second": 78.661, | |
| "eval_steps_per_second": 10.232, | |
| "step": 15252 | |
| }, | |
| { | |
| "epoch": 247.0, | |
| "eval_loss": 11.144104957580566, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.978, | |
| "eval_steps_per_second": 10.274, | |
| "step": 15314 | |
| }, | |
| { | |
| "epoch": 248.0, | |
| "eval_loss": 10.909028053283691, | |
| "eval_runtime": 1.5501, | |
| "eval_samples_per_second": 79.35, | |
| "eval_steps_per_second": 10.322, | |
| "step": 15376 | |
| }, | |
| { | |
| "epoch": 249.0, | |
| "eval_loss": 10.97555923461914, | |
| "eval_runtime": 1.5502, | |
| "eval_samples_per_second": 79.347, | |
| "eval_steps_per_second": 10.322, | |
| "step": 15438 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 3.5e-08, | |
| "loss": 10.0832, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "eval_loss": 10.953834533691406, | |
| "eval_runtime": 1.5699, | |
| "eval_samples_per_second": 78.347, | |
| "eval_steps_per_second": 10.192, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 251.0, | |
| "eval_loss": 10.842375755310059, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.974, | |
| "eval_steps_per_second": 10.273, | |
| "step": 15562 | |
| }, | |
| { | |
| "epoch": 252.0, | |
| "eval_loss": 10.767086029052734, | |
| "eval_runtime": 1.5579, | |
| "eval_samples_per_second": 78.953, | |
| "eval_steps_per_second": 10.27, | |
| "step": 15624 | |
| }, | |
| { | |
| "epoch": 253.0, | |
| "eval_loss": 10.963540077209473, | |
| "eval_runtime": 1.5571, | |
| "eval_samples_per_second": 78.992, | |
| "eval_steps_per_second": 10.275, | |
| "step": 15686 | |
| }, | |
| { | |
| "epoch": 254.0, | |
| "eval_loss": 10.849014282226562, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.976, | |
| "eval_steps_per_second": 10.273, | |
| "step": 15748 | |
| }, | |
| { | |
| "epoch": 255.0, | |
| "eval_loss": 11.134928703308105, | |
| "eval_runtime": 1.5686, | |
| "eval_samples_per_second": 78.416, | |
| "eval_steps_per_second": 10.2, | |
| "step": 15810 | |
| }, | |
| { | |
| "epoch": 256.0, | |
| "eval_loss": 10.884407043457031, | |
| "eval_runtime": 1.5495, | |
| "eval_samples_per_second": 79.381, | |
| "eval_steps_per_second": 10.326, | |
| "step": 15872 | |
| }, | |
| { | |
| "epoch": 257.0, | |
| "eval_loss": 10.865640640258789, | |
| "eval_runtime": 1.552, | |
| "eval_samples_per_second": 79.251, | |
| "eval_steps_per_second": 10.309, | |
| "step": 15934 | |
| }, | |
| { | |
| "epoch": 258.0, | |
| "eval_loss": 10.823393821716309, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 79.33, | |
| "eval_steps_per_second": 10.319, | |
| "step": 15996 | |
| }, | |
| { | |
| "epoch": 258.06, | |
| "learning_rate": 3.387096774193549e-08, | |
| "loss": 10.0747, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 259.0, | |
| "eval_loss": 10.950251579284668, | |
| "eval_runtime": 1.5601, | |
| "eval_samples_per_second": 78.843, | |
| "eval_steps_per_second": 10.256, | |
| "step": 16058 | |
| }, | |
| { | |
| "epoch": 260.0, | |
| "eval_loss": 10.885615348815918, | |
| "eval_runtime": 1.5592, | |
| "eval_samples_per_second": 78.886, | |
| "eval_steps_per_second": 10.262, | |
| "step": 16120 | |
| }, | |
| { | |
| "epoch": 261.0, | |
| "eval_loss": 11.051911354064941, | |
| "eval_runtime": 1.5755, | |
| "eval_samples_per_second": 78.069, | |
| "eval_steps_per_second": 10.155, | |
| "step": 16182 | |
| }, | |
| { | |
| "epoch": 262.0, | |
| "eval_loss": 10.886160850524902, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 79.0, | |
| "eval_steps_per_second": 10.276, | |
| "step": 16244 | |
| }, | |
| { | |
| "epoch": 263.0, | |
| "eval_loss": 10.897393226623535, | |
| "eval_runtime": 1.5641, | |
| "eval_samples_per_second": 78.64, | |
| "eval_steps_per_second": 10.23, | |
| "step": 16306 | |
| }, | |
| { | |
| "epoch": 264.0, | |
| "eval_loss": 10.84638500213623, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.364, | |
| "eval_steps_per_second": 10.324, | |
| "step": 16368 | |
| }, | |
| { | |
| "epoch": 265.0, | |
| "eval_loss": 10.965924263000488, | |
| "eval_runtime": 1.5489, | |
| "eval_samples_per_second": 79.411, | |
| "eval_steps_per_second": 10.33, | |
| "step": 16430 | |
| }, | |
| { | |
| "epoch": 266.0, | |
| "eval_loss": 10.742626190185547, | |
| "eval_runtime": 1.55, | |
| "eval_samples_per_second": 79.357, | |
| "eval_steps_per_second": 10.323, | |
| "step": 16492 | |
| }, | |
| { | |
| "epoch": 266.13, | |
| "learning_rate": 3.274193548387097e-08, | |
| "loss": 10.0678, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 267.0, | |
| "eval_loss": 10.985177040100098, | |
| "eval_runtime": 1.5698, | |
| "eval_samples_per_second": 78.356, | |
| "eval_steps_per_second": 10.193, | |
| "step": 16554 | |
| }, | |
| { | |
| "epoch": 268.0, | |
| "eval_loss": 11.049816131591797, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 79.0, | |
| "eval_steps_per_second": 10.276, | |
| "step": 16616 | |
| }, | |
| { | |
| "epoch": 269.0, | |
| "eval_loss": 10.7893648147583, | |
| "eval_runtime": 1.5584, | |
| "eval_samples_per_second": 78.929, | |
| "eval_steps_per_second": 10.267, | |
| "step": 16678 | |
| }, | |
| { | |
| "epoch": 270.0, | |
| "eval_loss": 11.10730266571045, | |
| "eval_runtime": 1.5594, | |
| "eval_samples_per_second": 78.878, | |
| "eval_steps_per_second": 10.261, | |
| "step": 16740 | |
| }, | |
| { | |
| "epoch": 271.0, | |
| "eval_loss": 10.826376914978027, | |
| "eval_runtime": 1.5624, | |
| "eval_samples_per_second": 78.727, | |
| "eval_steps_per_second": 10.241, | |
| "step": 16802 | |
| }, | |
| { | |
| "epoch": 272.0, | |
| "eval_loss": 10.931463241577148, | |
| "eval_runtime": 1.5486, | |
| "eval_samples_per_second": 79.427, | |
| "eval_steps_per_second": 10.332, | |
| "step": 16864 | |
| }, | |
| { | |
| "epoch": 273.0, | |
| "eval_loss": 10.775986671447754, | |
| "eval_runtime": 1.5509, | |
| "eval_samples_per_second": 79.307, | |
| "eval_steps_per_second": 10.316, | |
| "step": 16926 | |
| }, | |
| { | |
| "epoch": 274.0, | |
| "eval_loss": 10.972262382507324, | |
| "eval_runtime": 1.566, | |
| "eval_samples_per_second": 78.543, | |
| "eval_steps_per_second": 10.217, | |
| "step": 16988 | |
| }, | |
| { | |
| "epoch": 274.19, | |
| "learning_rate": 3.1612903225806456e-08, | |
| "loss": 10.0631, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 275.0, | |
| "eval_loss": 10.748165130615234, | |
| "eval_runtime": 1.5567, | |
| "eval_samples_per_second": 79.014, | |
| "eval_steps_per_second": 10.278, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 276.0, | |
| "eval_loss": 11.049092292785645, | |
| "eval_runtime": 1.5587, | |
| "eval_samples_per_second": 78.912, | |
| "eval_steps_per_second": 10.265, | |
| "step": 17112 | |
| }, | |
| { | |
| "epoch": 277.0, | |
| "eval_loss": 10.751622200012207, | |
| "eval_runtime": 1.5568, | |
| "eval_samples_per_second": 79.007, | |
| "eval_steps_per_second": 10.277, | |
| "step": 17174 | |
| }, | |
| { | |
| "epoch": 278.0, | |
| "eval_loss": 10.950490951538086, | |
| "eval_runtime": 1.5586, | |
| "eval_samples_per_second": 78.916, | |
| "eval_steps_per_second": 10.266, | |
| "step": 17236 | |
| }, | |
| { | |
| "epoch": 279.0, | |
| "eval_loss": 10.889892578125, | |
| "eval_runtime": 1.5568, | |
| "eval_samples_per_second": 79.01, | |
| "eval_steps_per_second": 10.278, | |
| "step": 17298 | |
| }, | |
| { | |
| "epoch": 280.0, | |
| "eval_loss": 10.786404609680176, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 78.998, | |
| "eval_steps_per_second": 10.276, | |
| "step": 17360 | |
| }, | |
| { | |
| "epoch": 281.0, | |
| "eval_loss": 10.865982055664062, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.377, | |
| "eval_steps_per_second": 10.326, | |
| "step": 17422 | |
| }, | |
| { | |
| "epoch": 282.0, | |
| "eval_loss": 10.97549819946289, | |
| "eval_runtime": 1.5507, | |
| "eval_samples_per_second": 79.318, | |
| "eval_steps_per_second": 10.318, | |
| "step": 17484 | |
| }, | |
| { | |
| "epoch": 282.26, | |
| "learning_rate": 3.048387096774194e-08, | |
| "loss": 10.0464, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 283.0, | |
| "eval_loss": 10.970197677612305, | |
| "eval_runtime": 1.5595, | |
| "eval_samples_per_second": 78.873, | |
| "eval_steps_per_second": 10.26, | |
| "step": 17546 | |
| }, | |
| { | |
| "epoch": 284.0, | |
| "eval_loss": 10.966419219970703, | |
| "eval_runtime": 1.5592, | |
| "eval_samples_per_second": 78.887, | |
| "eval_steps_per_second": 10.262, | |
| "step": 17608 | |
| }, | |
| { | |
| "epoch": 285.0, | |
| "eval_loss": 10.941322326660156, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.971, | |
| "eval_steps_per_second": 10.273, | |
| "step": 17670 | |
| }, | |
| { | |
| "epoch": 286.0, | |
| "eval_loss": 10.966172218322754, | |
| "eval_runtime": 1.5626, | |
| "eval_samples_per_second": 78.714, | |
| "eval_steps_per_second": 10.239, | |
| "step": 17732 | |
| }, | |
| { | |
| "epoch": 287.0, | |
| "eval_loss": 10.951107025146484, | |
| "eval_runtime": 1.5766, | |
| "eval_samples_per_second": 78.017, | |
| "eval_steps_per_second": 10.149, | |
| "step": 17794 | |
| }, | |
| { | |
| "epoch": 288.0, | |
| "eval_loss": 10.864799499511719, | |
| "eval_runtime": 1.5527, | |
| "eval_samples_per_second": 79.216, | |
| "eval_steps_per_second": 10.305, | |
| "step": 17856 | |
| }, | |
| { | |
| "epoch": 289.0, | |
| "eval_loss": 10.88668441772461, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 79.261, | |
| "eval_steps_per_second": 10.31, | |
| "step": 17918 | |
| }, | |
| { | |
| "epoch": 290.0, | |
| "eval_loss": 11.037867546081543, | |
| "eval_runtime": 1.5494, | |
| "eval_samples_per_second": 79.386, | |
| "eval_steps_per_second": 10.327, | |
| "step": 17980 | |
| }, | |
| { | |
| "epoch": 290.32, | |
| "learning_rate": 2.935483870967742e-08, | |
| "loss": 10.059, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 291.0, | |
| "eval_loss": 10.958696365356445, | |
| "eval_runtime": 1.5631, | |
| "eval_samples_per_second": 78.692, | |
| "eval_steps_per_second": 10.236, | |
| "step": 18042 | |
| }, | |
| { | |
| "epoch": 292.0, | |
| "eval_loss": 10.871495246887207, | |
| "eval_runtime": 1.5627, | |
| "eval_samples_per_second": 78.71, | |
| "eval_steps_per_second": 10.239, | |
| "step": 18104 | |
| }, | |
| { | |
| "epoch": 293.0, | |
| "eval_loss": 11.032896041870117, | |
| "eval_runtime": 1.5647, | |
| "eval_samples_per_second": 78.608, | |
| "eval_steps_per_second": 10.225, | |
| "step": 18166 | |
| }, | |
| { | |
| "epoch": 294.0, | |
| "eval_loss": 10.993353843688965, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 78.998, | |
| "eval_steps_per_second": 10.276, | |
| "step": 18228 | |
| }, | |
| { | |
| "epoch": 295.0, | |
| "eval_loss": 11.031813621520996, | |
| "eval_runtime": 1.5556, | |
| "eval_samples_per_second": 79.072, | |
| "eval_steps_per_second": 10.286, | |
| "step": 18290 | |
| }, | |
| { | |
| "epoch": 296.0, | |
| "eval_loss": 10.949562072753906, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.389, | |
| "eval_steps_per_second": 10.327, | |
| "step": 18352 | |
| }, | |
| { | |
| "epoch": 297.0, | |
| "eval_loss": 10.985105514526367, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.373, | |
| "eval_steps_per_second": 10.325, | |
| "step": 18414 | |
| }, | |
| { | |
| "epoch": 298.0, | |
| "eval_loss": 10.904229164123535, | |
| "eval_runtime": 1.5499, | |
| "eval_samples_per_second": 79.359, | |
| "eval_steps_per_second": 10.323, | |
| "step": 18476 | |
| }, | |
| { | |
| "epoch": 298.39, | |
| "learning_rate": 2.8225806451612902e-08, | |
| "loss": 10.0478, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 299.0, | |
| "eval_loss": 10.848288536071777, | |
| "eval_runtime": 1.5652, | |
| "eval_samples_per_second": 78.585, | |
| "eval_steps_per_second": 10.222, | |
| "step": 18538 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "eval_loss": 11.128362655639648, | |
| "eval_runtime": 1.5589, | |
| "eval_samples_per_second": 78.903, | |
| "eval_steps_per_second": 10.264, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 301.0, | |
| "eval_loss": 10.965646743774414, | |
| "eval_runtime": 1.5837, | |
| "eval_samples_per_second": 77.668, | |
| "eval_steps_per_second": 10.103, | |
| "step": 18662 | |
| }, | |
| { | |
| "epoch": 302.0, | |
| "eval_loss": 10.962158203125, | |
| "eval_runtime": 1.5581, | |
| "eval_samples_per_second": 78.944, | |
| "eval_steps_per_second": 10.269, | |
| "step": 18724 | |
| }, | |
| { | |
| "epoch": 303.0, | |
| "eval_loss": 11.022586822509766, | |
| "eval_runtime": 1.5559, | |
| "eval_samples_per_second": 79.056, | |
| "eval_steps_per_second": 10.284, | |
| "step": 18786 | |
| }, | |
| { | |
| "epoch": 304.0, | |
| "eval_loss": 10.998231887817383, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.272, | |
| "eval_steps_per_second": 10.312, | |
| "step": 18848 | |
| }, | |
| { | |
| "epoch": 305.0, | |
| "eval_loss": 10.964576721191406, | |
| "eval_runtime": 1.5886, | |
| "eval_samples_per_second": 77.425, | |
| "eval_steps_per_second": 10.072, | |
| "step": 18910 | |
| }, | |
| { | |
| "epoch": 306.0, | |
| "eval_loss": 11.094855308532715, | |
| "eval_runtime": 1.549, | |
| "eval_samples_per_second": 79.406, | |
| "eval_steps_per_second": 10.329, | |
| "step": 18972 | |
| }, | |
| { | |
| "epoch": 306.45, | |
| "learning_rate": 2.7096774193548387e-08, | |
| "loss": 10.0513, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 307.0, | |
| "eval_loss": 11.073990821838379, | |
| "eval_runtime": 1.5592, | |
| "eval_samples_per_second": 78.885, | |
| "eval_steps_per_second": 10.261, | |
| "step": 19034 | |
| }, | |
| { | |
| "epoch": 308.0, | |
| "eval_loss": 10.888773918151855, | |
| "eval_runtime": 1.5638, | |
| "eval_samples_per_second": 78.652, | |
| "eval_steps_per_second": 10.231, | |
| "step": 19096 | |
| }, | |
| { | |
| "epoch": 309.0, | |
| "eval_loss": 11.247567176818848, | |
| "eval_runtime": 1.5616, | |
| "eval_samples_per_second": 78.763, | |
| "eval_steps_per_second": 10.246, | |
| "step": 19158 | |
| }, | |
| { | |
| "epoch": 310.0, | |
| "eval_loss": 10.999629020690918, | |
| "eval_runtime": 1.5902, | |
| "eval_samples_per_second": 77.348, | |
| "eval_steps_per_second": 10.062, | |
| "step": 19220 | |
| }, | |
| { | |
| "epoch": 311.0, | |
| "eval_loss": 10.804391860961914, | |
| "eval_runtime": 1.5586, | |
| "eval_samples_per_second": 78.919, | |
| "eval_steps_per_second": 10.266, | |
| "step": 19282 | |
| }, | |
| { | |
| "epoch": 312.0, | |
| "eval_loss": 10.949257850646973, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.391, | |
| "eval_steps_per_second": 10.327, | |
| "step": 19344 | |
| }, | |
| { | |
| "epoch": 313.0, | |
| "eval_loss": 10.94599723815918, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.367, | |
| "eval_steps_per_second": 10.324, | |
| "step": 19406 | |
| }, | |
| { | |
| "epoch": 314.0, | |
| "eval_loss": 10.966387748718262, | |
| "eval_runtime": 1.5504, | |
| "eval_samples_per_second": 79.336, | |
| "eval_steps_per_second": 10.32, | |
| "step": 19468 | |
| }, | |
| { | |
| "epoch": 314.52, | |
| "learning_rate": 2.5967741935483875e-08, | |
| "loss": 10.0363, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 315.0, | |
| "eval_loss": 10.91958999633789, | |
| "eval_runtime": 1.5704, | |
| "eval_samples_per_second": 78.324, | |
| "eval_steps_per_second": 10.188, | |
| "step": 19530 | |
| }, | |
| { | |
| "epoch": 316.0, | |
| "eval_loss": 10.921772956848145, | |
| "eval_runtime": 1.5577, | |
| "eval_samples_per_second": 78.964, | |
| "eval_steps_per_second": 10.272, | |
| "step": 19592 | |
| }, | |
| { | |
| "epoch": 317.0, | |
| "eval_loss": 10.800854682922363, | |
| "eval_runtime": 1.5565, | |
| "eval_samples_per_second": 79.024, | |
| "eval_steps_per_second": 10.28, | |
| "step": 19654 | |
| }, | |
| { | |
| "epoch": 318.0, | |
| "eval_loss": 11.121504783630371, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.979, | |
| "eval_steps_per_second": 10.274, | |
| "step": 19716 | |
| }, | |
| { | |
| "epoch": 319.0, | |
| "eval_loss": 10.96510124206543, | |
| "eval_runtime": 1.5619, | |
| "eval_samples_per_second": 78.751, | |
| "eval_steps_per_second": 10.244, | |
| "step": 19778 | |
| }, | |
| { | |
| "epoch": 320.0, | |
| "eval_loss": 10.995678901672363, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 79.33, | |
| "eval_steps_per_second": 10.319, | |
| "step": 19840 | |
| }, | |
| { | |
| "epoch": 321.0, | |
| "eval_loss": 11.144912719726562, | |
| "eval_runtime": 1.5521, | |
| "eval_samples_per_second": 79.247, | |
| "eval_steps_per_second": 10.309, | |
| "step": 19902 | |
| }, | |
| { | |
| "epoch": 322.0, | |
| "eval_loss": 11.01318645477295, | |
| "eval_runtime": 1.555, | |
| "eval_samples_per_second": 79.101, | |
| "eval_steps_per_second": 10.289, | |
| "step": 19964 | |
| }, | |
| { | |
| "epoch": 322.58, | |
| "learning_rate": 2.483870967741936e-08, | |
| "loss": 10.0503, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 323.0, | |
| "eval_loss": 11.119362831115723, | |
| "eval_runtime": 1.5655, | |
| "eval_samples_per_second": 78.571, | |
| "eval_steps_per_second": 10.221, | |
| "step": 20026 | |
| }, | |
| { | |
| "epoch": 324.0, | |
| "eval_loss": 10.964983940124512, | |
| "eval_runtime": 1.5692, | |
| "eval_samples_per_second": 78.382, | |
| "eval_steps_per_second": 10.196, | |
| "step": 20088 | |
| }, | |
| { | |
| "epoch": 325.0, | |
| "eval_loss": 10.841401100158691, | |
| "eval_runtime": 1.5595, | |
| "eval_samples_per_second": 78.871, | |
| "eval_steps_per_second": 10.26, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 326.0, | |
| "eval_loss": 10.86677360534668, | |
| "eval_runtime": 1.5533, | |
| "eval_samples_per_second": 79.184, | |
| "eval_steps_per_second": 10.3, | |
| "step": 20212 | |
| }, | |
| { | |
| "epoch": 327.0, | |
| "eval_loss": 11.009995460510254, | |
| "eval_runtime": 1.5673, | |
| "eval_samples_per_second": 78.478, | |
| "eval_steps_per_second": 10.209, | |
| "step": 20274 | |
| }, | |
| { | |
| "epoch": 328.0, | |
| "eval_loss": 10.875937461853027, | |
| "eval_runtime": 1.5499, | |
| "eval_samples_per_second": 79.359, | |
| "eval_steps_per_second": 10.323, | |
| "step": 20336 | |
| }, | |
| { | |
| "epoch": 329.0, | |
| "eval_loss": 10.965596199035645, | |
| "eval_runtime": 1.562, | |
| "eval_samples_per_second": 78.744, | |
| "eval_steps_per_second": 10.243, | |
| "step": 20398 | |
| }, | |
| { | |
| "epoch": 330.0, | |
| "eval_loss": 11.007844924926758, | |
| "eval_runtime": 1.5553, | |
| "eval_samples_per_second": 79.085, | |
| "eval_steps_per_second": 10.287, | |
| "step": 20460 | |
| }, | |
| { | |
| "epoch": 330.65, | |
| "learning_rate": 2.370967741935484e-08, | |
| "loss": 10.0223, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 331.0, | |
| "eval_loss": 11.0198335647583, | |
| "eval_runtime": 1.5833, | |
| "eval_samples_per_second": 77.688, | |
| "eval_steps_per_second": 10.106, | |
| "step": 20522 | |
| }, | |
| { | |
| "epoch": 332.0, | |
| "eval_loss": 11.088841438293457, | |
| "eval_runtime": 1.5649, | |
| "eval_samples_per_second": 78.601, | |
| "eval_steps_per_second": 10.224, | |
| "step": 20584 | |
| }, | |
| { | |
| "epoch": 333.0, | |
| "eval_loss": 11.105833053588867, | |
| "eval_runtime": 1.5609, | |
| "eval_samples_per_second": 78.798, | |
| "eval_steps_per_second": 10.25, | |
| "step": 20646 | |
| }, | |
| { | |
| "epoch": 334.0, | |
| "eval_loss": 10.942315101623535, | |
| "eval_runtime": 1.5599, | |
| "eval_samples_per_second": 78.853, | |
| "eval_steps_per_second": 10.257, | |
| "step": 20708 | |
| }, | |
| { | |
| "epoch": 335.0, | |
| "eval_loss": 11.103010177612305, | |
| "eval_runtime": 1.5806, | |
| "eval_samples_per_second": 77.817, | |
| "eval_steps_per_second": 10.123, | |
| "step": 20770 | |
| }, | |
| { | |
| "epoch": 336.0, | |
| "eval_loss": 11.081936836242676, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.366, | |
| "eval_steps_per_second": 10.324, | |
| "step": 20832 | |
| }, | |
| { | |
| "epoch": 337.0, | |
| "eval_loss": 10.90597152709961, | |
| "eval_runtime": 1.55, | |
| "eval_samples_per_second": 79.356, | |
| "eval_steps_per_second": 10.323, | |
| "step": 20894 | |
| }, | |
| { | |
| "epoch": 338.0, | |
| "eval_loss": 11.074986457824707, | |
| "eval_runtime": 1.5577, | |
| "eval_samples_per_second": 78.962, | |
| "eval_steps_per_second": 10.271, | |
| "step": 20956 | |
| }, | |
| { | |
| "epoch": 338.71, | |
| "learning_rate": 2.2580645161290325e-08, | |
| "loss": 10.0321, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 339.0, | |
| "eval_loss": 11.110125541687012, | |
| "eval_runtime": 1.5561, | |
| "eval_samples_per_second": 79.046, | |
| "eval_steps_per_second": 10.282, | |
| "step": 21018 | |
| }, | |
| { | |
| "epoch": 340.0, | |
| "eval_loss": 10.971090316772461, | |
| "eval_runtime": 1.5625, | |
| "eval_samples_per_second": 78.722, | |
| "eval_steps_per_second": 10.24, | |
| "step": 21080 | |
| }, | |
| { | |
| "epoch": 341.0, | |
| "eval_loss": 10.92870044708252, | |
| "eval_runtime": 1.5635, | |
| "eval_samples_per_second": 78.668, | |
| "eval_steps_per_second": 10.233, | |
| "step": 21142 | |
| }, | |
| { | |
| "epoch": 342.0, | |
| "eval_loss": 10.796195983886719, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.978, | |
| "eval_steps_per_second": 10.273, | |
| "step": 21204 | |
| }, | |
| { | |
| "epoch": 343.0, | |
| "eval_loss": 11.136199951171875, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.976, | |
| "eval_steps_per_second": 10.273, | |
| "step": 21266 | |
| }, | |
| { | |
| "epoch": 344.0, | |
| "eval_loss": 11.102249145507812, | |
| "eval_runtime": 1.551, | |
| "eval_samples_per_second": 79.302, | |
| "eval_steps_per_second": 10.316, | |
| "step": 21328 | |
| }, | |
| { | |
| "epoch": 345.0, | |
| "eval_loss": 10.999671936035156, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.392, | |
| "eval_steps_per_second": 10.327, | |
| "step": 21390 | |
| }, | |
| { | |
| "epoch": 346.0, | |
| "eval_loss": 10.876097679138184, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.366, | |
| "eval_steps_per_second": 10.324, | |
| "step": 21452 | |
| }, | |
| { | |
| "epoch": 346.77, | |
| "learning_rate": 2.145161290322581e-08, | |
| "loss": 10.0226, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 347.0, | |
| "eval_loss": 10.934317588806152, | |
| "eval_runtime": 1.5612, | |
| "eval_samples_per_second": 78.786, | |
| "eval_steps_per_second": 10.249, | |
| "step": 21514 | |
| }, | |
| { | |
| "epoch": 348.0, | |
| "eval_loss": 10.910962104797363, | |
| "eval_runtime": 1.5564, | |
| "eval_samples_per_second": 79.028, | |
| "eval_steps_per_second": 10.28, | |
| "step": 21576 | |
| }, | |
| { | |
| "epoch": 349.0, | |
| "eval_loss": 11.034477233886719, | |
| "eval_runtime": 1.5584, | |
| "eval_samples_per_second": 78.929, | |
| "eval_steps_per_second": 10.267, | |
| "step": 21638 | |
| }, | |
| { | |
| "epoch": 350.0, | |
| "eval_loss": 10.88716983795166, | |
| "eval_runtime": 1.5754, | |
| "eval_samples_per_second": 78.075, | |
| "eval_steps_per_second": 10.156, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 351.0, | |
| "eval_loss": 10.766716957092285, | |
| "eval_runtime": 1.5893, | |
| "eval_samples_per_second": 77.394, | |
| "eval_steps_per_second": 10.067, | |
| "step": 21762 | |
| }, | |
| { | |
| "epoch": 352.0, | |
| "eval_loss": 11.056756973266602, | |
| "eval_runtime": 1.5503, | |
| "eval_samples_per_second": 79.339, | |
| "eval_steps_per_second": 10.321, | |
| "step": 21824 | |
| }, | |
| { | |
| "epoch": 353.0, | |
| "eval_loss": 11.028831481933594, | |
| "eval_runtime": 1.5494, | |
| "eval_samples_per_second": 79.385, | |
| "eval_steps_per_second": 10.326, | |
| "step": 21886 | |
| }, | |
| { | |
| "epoch": 354.0, | |
| "eval_loss": 11.066434860229492, | |
| "eval_runtime": 1.5562, | |
| "eval_samples_per_second": 79.039, | |
| "eval_steps_per_second": 10.281, | |
| "step": 21948 | |
| }, | |
| { | |
| "epoch": 354.84, | |
| "learning_rate": 2.0322580645161293e-08, | |
| "loss": 10.033, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 355.0, | |
| "eval_loss": 10.975112915039062, | |
| "eval_runtime": 1.5594, | |
| "eval_samples_per_second": 78.876, | |
| "eval_steps_per_second": 10.26, | |
| "step": 22010 | |
| }, | |
| { | |
| "epoch": 356.0, | |
| "eval_loss": 10.856056213378906, | |
| "eval_runtime": 1.5565, | |
| "eval_samples_per_second": 79.022, | |
| "eval_steps_per_second": 10.279, | |
| "step": 22072 | |
| }, | |
| { | |
| "epoch": 357.0, | |
| "eval_loss": 10.960885047912598, | |
| "eval_runtime": 1.5772, | |
| "eval_samples_per_second": 77.988, | |
| "eval_steps_per_second": 10.145, | |
| "step": 22134 | |
| }, | |
| { | |
| "epoch": 358.0, | |
| "eval_loss": 11.000205993652344, | |
| "eval_runtime": 1.5685, | |
| "eval_samples_per_second": 78.418, | |
| "eval_steps_per_second": 10.201, | |
| "step": 22196 | |
| }, | |
| { | |
| "epoch": 359.0, | |
| "eval_loss": 11.056760787963867, | |
| "eval_runtime": 1.5597, | |
| "eval_samples_per_second": 78.862, | |
| "eval_steps_per_second": 10.259, | |
| "step": 22258 | |
| }, | |
| { | |
| "epoch": 360.0, | |
| "eval_loss": 10.958597183227539, | |
| "eval_runtime": 1.5568, | |
| "eval_samples_per_second": 79.009, | |
| "eval_steps_per_second": 10.278, | |
| "step": 22320 | |
| }, | |
| { | |
| "epoch": 361.0, | |
| "eval_loss": 10.925392150878906, | |
| "eval_runtime": 1.5568, | |
| "eval_samples_per_second": 79.007, | |
| "eval_steps_per_second": 10.277, | |
| "step": 22382 | |
| }, | |
| { | |
| "epoch": 362.0, | |
| "eval_loss": 11.065186500549316, | |
| "eval_runtime": 1.5511, | |
| "eval_samples_per_second": 79.297, | |
| "eval_steps_per_second": 10.315, | |
| "step": 22444 | |
| }, | |
| { | |
| "epoch": 362.9, | |
| "learning_rate": 1.9193548387096775e-08, | |
| "loss": 10.0084, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 363.0, | |
| "eval_loss": 10.965627670288086, | |
| "eval_runtime": 1.5573, | |
| "eval_samples_per_second": 78.985, | |
| "eval_steps_per_second": 10.274, | |
| "step": 22506 | |
| }, | |
| { | |
| "epoch": 364.0, | |
| "eval_loss": 11.061145782470703, | |
| "eval_runtime": 1.5616, | |
| "eval_samples_per_second": 78.765, | |
| "eval_steps_per_second": 10.246, | |
| "step": 22568 | |
| }, | |
| { | |
| "epoch": 365.0, | |
| "eval_loss": 10.833497047424316, | |
| "eval_runtime": 1.5633, | |
| "eval_samples_per_second": 78.678, | |
| "eval_steps_per_second": 10.235, | |
| "step": 22630 | |
| }, | |
| { | |
| "epoch": 366.0, | |
| "eval_loss": 10.980859756469727, | |
| "eval_runtime": 1.5593, | |
| "eval_samples_per_second": 78.883, | |
| "eval_steps_per_second": 10.261, | |
| "step": 22692 | |
| }, | |
| { | |
| "epoch": 367.0, | |
| "eval_loss": 11.020894050598145, | |
| "eval_runtime": 1.5581, | |
| "eval_samples_per_second": 78.94, | |
| "eval_steps_per_second": 10.269, | |
| "step": 22754 | |
| }, | |
| { | |
| "epoch": 368.0, | |
| "eval_loss": 10.91490364074707, | |
| "eval_runtime": 1.574, | |
| "eval_samples_per_second": 78.142, | |
| "eval_steps_per_second": 10.165, | |
| "step": 22816 | |
| }, | |
| { | |
| "epoch": 369.0, | |
| "eval_loss": 11.020668029785156, | |
| "eval_runtime": 1.5554, | |
| "eval_samples_per_second": 79.078, | |
| "eval_steps_per_second": 10.287, | |
| "step": 22878 | |
| }, | |
| { | |
| "epoch": 370.0, | |
| "eval_loss": 10.877435684204102, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.374, | |
| "eval_steps_per_second": 10.325, | |
| "step": 22940 | |
| }, | |
| { | |
| "epoch": 370.97, | |
| "learning_rate": 1.806451612903226e-08, | |
| "loss": 10.024, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 371.0, | |
| "eval_loss": 10.985451698303223, | |
| "eval_runtime": 1.5536, | |
| "eval_samples_per_second": 79.173, | |
| "eval_steps_per_second": 10.299, | |
| "step": 23002 | |
| }, | |
| { | |
| "epoch": 372.0, | |
| "eval_loss": 10.90639877319336, | |
| "eval_runtime": 1.5566, | |
| "eval_samples_per_second": 79.018, | |
| "eval_steps_per_second": 10.279, | |
| "step": 23064 | |
| }, | |
| { | |
| "epoch": 373.0, | |
| "eval_loss": 10.95183277130127, | |
| "eval_runtime": 1.5635, | |
| "eval_samples_per_second": 78.669, | |
| "eval_steps_per_second": 10.233, | |
| "step": 23126 | |
| }, | |
| { | |
| "epoch": 374.0, | |
| "eval_loss": 10.877464294433594, | |
| "eval_runtime": 1.5564, | |
| "eval_samples_per_second": 79.031, | |
| "eval_steps_per_second": 10.28, | |
| "step": 23188 | |
| }, | |
| { | |
| "epoch": 375.0, | |
| "eval_loss": 10.91928768157959, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.971, | |
| "eval_steps_per_second": 10.273, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 376.0, | |
| "eval_loss": 11.109807968139648, | |
| "eval_runtime": 1.5563, | |
| "eval_samples_per_second": 79.033, | |
| "eval_steps_per_second": 10.281, | |
| "step": 23312 | |
| }, | |
| { | |
| "epoch": 377.0, | |
| "eval_loss": 11.148626327514648, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.392, | |
| "eval_steps_per_second": 10.327, | |
| "step": 23374 | |
| }, | |
| { | |
| "epoch": 378.0, | |
| "eval_loss": 11.089497566223145, | |
| "eval_runtime": 1.5491, | |
| "eval_samples_per_second": 79.4, | |
| "eval_steps_per_second": 10.329, | |
| "step": 23436 | |
| }, | |
| { | |
| "epoch": 379.0, | |
| "eval_loss": 10.915903091430664, | |
| "eval_runtime": 1.5528, | |
| "eval_samples_per_second": 79.214, | |
| "eval_steps_per_second": 10.304, | |
| "step": 23498 | |
| }, | |
| { | |
| "epoch": 379.03, | |
| "learning_rate": 1.6935483870967743e-08, | |
| "loss": 10.0052, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 380.0, | |
| "eval_loss": 11.109511375427246, | |
| "eval_runtime": 1.5576, | |
| "eval_samples_per_second": 78.966, | |
| "eval_steps_per_second": 10.272, | |
| "step": 23560 | |
| }, | |
| { | |
| "epoch": 381.0, | |
| "eval_loss": 11.094901084899902, | |
| "eval_runtime": 1.5561, | |
| "eval_samples_per_second": 79.044, | |
| "eval_steps_per_second": 10.282, | |
| "step": 23622 | |
| }, | |
| { | |
| "epoch": 382.0, | |
| "eval_loss": 10.983734130859375, | |
| "eval_runtime": 1.5557, | |
| "eval_samples_per_second": 79.066, | |
| "eval_steps_per_second": 10.285, | |
| "step": 23684 | |
| }, | |
| { | |
| "epoch": 383.0, | |
| "eval_loss": 10.943252563476562, | |
| "eval_runtime": 1.577, | |
| "eval_samples_per_second": 77.998, | |
| "eval_steps_per_second": 10.146, | |
| "step": 23746 | |
| }, | |
| { | |
| "epoch": 384.0, | |
| "eval_loss": 10.910370826721191, | |
| "eval_runtime": 1.5682, | |
| "eval_samples_per_second": 78.434, | |
| "eval_steps_per_second": 10.203, | |
| "step": 23808 | |
| }, | |
| { | |
| "epoch": 385.0, | |
| "eval_loss": 10.95122241973877, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.28, | |
| "eval_steps_per_second": 10.313, | |
| "step": 23870 | |
| }, | |
| { | |
| "epoch": 386.0, | |
| "eval_loss": 11.107484817504883, | |
| "eval_runtime": 1.5487, | |
| "eval_samples_per_second": 79.422, | |
| "eval_steps_per_second": 10.331, | |
| "step": 23932 | |
| }, | |
| { | |
| "epoch": 387.0, | |
| "eval_loss": 10.865962982177734, | |
| "eval_runtime": 1.5535, | |
| "eval_samples_per_second": 79.176, | |
| "eval_steps_per_second": 10.299, | |
| "step": 23994 | |
| }, | |
| { | |
| "epoch": 387.1, | |
| "learning_rate": 1.5806451612903228e-08, | |
| "loss": 10.0218, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 388.0, | |
| "eval_loss": 11.052102088928223, | |
| "eval_runtime": 1.5572, | |
| "eval_samples_per_second": 78.988, | |
| "eval_steps_per_second": 10.275, | |
| "step": 24056 | |
| }, | |
| { | |
| "epoch": 389.0, | |
| "eval_loss": 10.898940086364746, | |
| "eval_runtime": 1.5627, | |
| "eval_samples_per_second": 78.712, | |
| "eval_steps_per_second": 10.239, | |
| "step": 24118 | |
| }, | |
| { | |
| "epoch": 390.0, | |
| "eval_loss": 10.913924217224121, | |
| "eval_runtime": 1.5799, | |
| "eval_samples_per_second": 77.852, | |
| "eval_steps_per_second": 10.127, | |
| "step": 24180 | |
| }, | |
| { | |
| "epoch": 391.0, | |
| "eval_loss": 11.10788345336914, | |
| "eval_runtime": 1.5783, | |
| "eval_samples_per_second": 77.934, | |
| "eval_steps_per_second": 10.138, | |
| "step": 24242 | |
| }, | |
| { | |
| "epoch": 392.0, | |
| "eval_loss": 10.906310081481934, | |
| "eval_runtime": 1.5568, | |
| "eval_samples_per_second": 79.006, | |
| "eval_steps_per_second": 10.277, | |
| "step": 24304 | |
| }, | |
| { | |
| "epoch": 393.0, | |
| "eval_loss": 11.085139274597168, | |
| "eval_runtime": 1.5494, | |
| "eval_samples_per_second": 79.384, | |
| "eval_steps_per_second": 10.326, | |
| "step": 24366 | |
| }, | |
| { | |
| "epoch": 394.0, | |
| "eval_loss": 10.980916023254395, | |
| "eval_runtime": 1.5522, | |
| "eval_samples_per_second": 79.244, | |
| "eval_steps_per_second": 10.308, | |
| "step": 24428 | |
| }, | |
| { | |
| "epoch": 395.0, | |
| "eval_loss": 10.932045936584473, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.389, | |
| "eval_steps_per_second": 10.327, | |
| "step": 24490 | |
| }, | |
| { | |
| "epoch": 395.16, | |
| "learning_rate": 1.467741935483871e-08, | |
| "loss": 10.0039, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 396.0, | |
| "eval_loss": 11.052530288696289, | |
| "eval_runtime": 1.5595, | |
| "eval_samples_per_second": 78.871, | |
| "eval_steps_per_second": 10.26, | |
| "step": 24552 | |
| }, | |
| { | |
| "epoch": 397.0, | |
| "eval_loss": 11.037784576416016, | |
| "eval_runtime": 1.5581, | |
| "eval_samples_per_second": 78.943, | |
| "eval_steps_per_second": 10.269, | |
| "step": 24614 | |
| }, | |
| { | |
| "epoch": 398.0, | |
| "eval_loss": 11.000636100769043, | |
| "eval_runtime": 1.5574, | |
| "eval_samples_per_second": 78.979, | |
| "eval_steps_per_second": 10.274, | |
| "step": 24676 | |
| }, | |
| { | |
| "epoch": 399.0, | |
| "eval_loss": 11.028385162353516, | |
| "eval_runtime": 1.5601, | |
| "eval_samples_per_second": 78.842, | |
| "eval_steps_per_second": 10.256, | |
| "step": 24738 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "eval_loss": 11.005521774291992, | |
| "eval_runtime": 1.5704, | |
| "eval_samples_per_second": 78.326, | |
| "eval_steps_per_second": 10.189, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 401.0, | |
| "eval_loss": 11.010418891906738, | |
| "eval_runtime": 1.55, | |
| "eval_samples_per_second": 79.356, | |
| "eval_steps_per_second": 10.323, | |
| "step": 24862 | |
| }, | |
| { | |
| "epoch": 402.0, | |
| "eval_loss": 11.11683464050293, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.377, | |
| "eval_steps_per_second": 10.325, | |
| "step": 24924 | |
| }, | |
| { | |
| "epoch": 403.0, | |
| "eval_loss": 10.831143379211426, | |
| "eval_runtime": 1.5514, | |
| "eval_samples_per_second": 79.284, | |
| "eval_steps_per_second": 10.313, | |
| "step": 24986 | |
| }, | |
| { | |
| "epoch": 403.23, | |
| "learning_rate": 1.3548387096774193e-08, | |
| "loss": 10.0186, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 404.0, | |
| "eval_loss": 10.890425682067871, | |
| "eval_runtime": 1.5613, | |
| "eval_samples_per_second": 78.78, | |
| "eval_steps_per_second": 10.248, | |
| "step": 25048 | |
| }, | |
| { | |
| "epoch": 405.0, | |
| "eval_loss": 10.861490249633789, | |
| "eval_runtime": 1.5685, | |
| "eval_samples_per_second": 78.418, | |
| "eval_steps_per_second": 10.201, | |
| "step": 25110 | |
| }, | |
| { | |
| "epoch": 406.0, | |
| "eval_loss": 10.951952934265137, | |
| "eval_runtime": 1.5597, | |
| "eval_samples_per_second": 78.863, | |
| "eval_steps_per_second": 10.259, | |
| "step": 25172 | |
| }, | |
| { | |
| "epoch": 407.0, | |
| "eval_loss": 10.911187171936035, | |
| "eval_runtime": 1.5579, | |
| "eval_samples_per_second": 78.953, | |
| "eval_steps_per_second": 10.27, | |
| "step": 25234 | |
| }, | |
| { | |
| "epoch": 408.0, | |
| "eval_loss": 11.027958869934082, | |
| "eval_runtime": 1.5537, | |
| "eval_samples_per_second": 79.165, | |
| "eval_steps_per_second": 10.298, | |
| "step": 25296 | |
| }, | |
| { | |
| "epoch": 409.0, | |
| "eval_loss": 10.828099250793457, | |
| "eval_runtime": 1.5453, | |
| "eval_samples_per_second": 79.597, | |
| "eval_steps_per_second": 10.354, | |
| "step": 25358 | |
| }, | |
| { | |
| "epoch": 410.0, | |
| "eval_loss": 11.187531471252441, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.375, | |
| "eval_steps_per_second": 10.325, | |
| "step": 25420 | |
| }, | |
| { | |
| "epoch": 411.0, | |
| "eval_loss": 11.00891399383545, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.231, | |
| "eval_steps_per_second": 10.306, | |
| "step": 25482 | |
| }, | |
| { | |
| "epoch": 411.29, | |
| "learning_rate": 1.241935483870968e-08, | |
| "loss": 10.0146, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 412.0, | |
| "eval_loss": 11.038575172424316, | |
| "eval_runtime": 1.5665, | |
| "eval_samples_per_second": 78.518, | |
| "eval_steps_per_second": 10.214, | |
| "step": 25544 | |
| }, | |
| { | |
| "epoch": 413.0, | |
| "eval_loss": 10.815169334411621, | |
| "eval_runtime": 1.558, | |
| "eval_samples_per_second": 78.948, | |
| "eval_steps_per_second": 10.27, | |
| "step": 25606 | |
| }, | |
| { | |
| "epoch": 414.0, | |
| "eval_loss": 10.946043014526367, | |
| "eval_runtime": 1.5604, | |
| "eval_samples_per_second": 78.824, | |
| "eval_steps_per_second": 10.254, | |
| "step": 25668 | |
| }, | |
| { | |
| "epoch": 415.0, | |
| "eval_loss": 10.9921875, | |
| "eval_runtime": 1.5586, | |
| "eval_samples_per_second": 78.917, | |
| "eval_steps_per_second": 10.266, | |
| "step": 25730 | |
| }, | |
| { | |
| "epoch": 416.0, | |
| "eval_loss": 11.085003852844238, | |
| "eval_runtime": 1.5606, | |
| "eval_samples_per_second": 78.817, | |
| "eval_steps_per_second": 10.253, | |
| "step": 25792 | |
| }, | |
| { | |
| "epoch": 417.0, | |
| "eval_loss": 11.002412796020508, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.276, | |
| "eval_steps_per_second": 10.312, | |
| "step": 25854 | |
| }, | |
| { | |
| "epoch": 418.0, | |
| "eval_loss": 11.093355178833008, | |
| "eval_runtime": 1.5531, | |
| "eval_samples_per_second": 79.196, | |
| "eval_steps_per_second": 10.302, | |
| "step": 25916 | |
| }, | |
| { | |
| "epoch": 419.0, | |
| "eval_loss": 11.095279693603516, | |
| "eval_runtime": 1.5495, | |
| "eval_samples_per_second": 79.379, | |
| "eval_steps_per_second": 10.326, | |
| "step": 25978 | |
| }, | |
| { | |
| "epoch": 419.35, | |
| "learning_rate": 1.1290322580645162e-08, | |
| "loss": 10.0251, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 420.0, | |
| "eval_loss": 10.89963150024414, | |
| "eval_runtime": 1.5606, | |
| "eval_samples_per_second": 78.815, | |
| "eval_steps_per_second": 10.252, | |
| "step": 26040 | |
| }, | |
| { | |
| "epoch": 421.0, | |
| "eval_loss": 10.983254432678223, | |
| "eval_runtime": 1.5556, | |
| "eval_samples_per_second": 79.068, | |
| "eval_steps_per_second": 10.285, | |
| "step": 26102 | |
| }, | |
| { | |
| "epoch": 422.0, | |
| "eval_loss": 10.754561424255371, | |
| "eval_runtime": 1.558, | |
| "eval_samples_per_second": 78.947, | |
| "eval_steps_per_second": 10.27, | |
| "step": 26164 | |
| }, | |
| { | |
| "epoch": 423.0, | |
| "eval_loss": 10.976980209350586, | |
| "eval_runtime": 1.577, | |
| "eval_samples_per_second": 77.995, | |
| "eval_steps_per_second": 10.146, | |
| "step": 26226 | |
| }, | |
| { | |
| "epoch": 424.0, | |
| "eval_loss": 11.063197135925293, | |
| "eval_runtime": 1.5683, | |
| "eval_samples_per_second": 78.427, | |
| "eval_steps_per_second": 10.202, | |
| "step": 26288 | |
| }, | |
| { | |
| "epoch": 425.0, | |
| "eval_loss": 10.924360275268555, | |
| "eval_runtime": 1.5498, | |
| "eval_samples_per_second": 79.364, | |
| "eval_steps_per_second": 10.324, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 426.0, | |
| "eval_loss": 10.937601089477539, | |
| "eval_runtime": 1.5495, | |
| "eval_samples_per_second": 79.379, | |
| "eval_steps_per_second": 10.326, | |
| "step": 26412 | |
| }, | |
| { | |
| "epoch": 427.0, | |
| "eval_loss": 11.044069290161133, | |
| "eval_runtime": 1.5501, | |
| "eval_samples_per_second": 79.351, | |
| "eval_steps_per_second": 10.322, | |
| "step": 26474 | |
| }, | |
| { | |
| "epoch": 427.42, | |
| "learning_rate": 1.0161290322580647e-08, | |
| "loss": 9.9776, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 428.0, | |
| "eval_loss": 11.067927360534668, | |
| "eval_runtime": 1.5604, | |
| "eval_samples_per_second": 78.827, | |
| "eval_steps_per_second": 10.254, | |
| "step": 26536 | |
| }, | |
| { | |
| "epoch": 429.0, | |
| "eval_loss": 11.066262245178223, | |
| "eval_runtime": 1.5875, | |
| "eval_samples_per_second": 77.482, | |
| "eval_steps_per_second": 10.079, | |
| "step": 26598 | |
| }, | |
| { | |
| "epoch": 430.0, | |
| "eval_loss": 10.988542556762695, | |
| "eval_runtime": 1.5716, | |
| "eval_samples_per_second": 78.264, | |
| "eval_steps_per_second": 10.181, | |
| "step": 26660 | |
| }, | |
| { | |
| "epoch": 431.0, | |
| "eval_loss": 10.956550598144531, | |
| "eval_runtime": 1.558, | |
| "eval_samples_per_second": 78.949, | |
| "eval_steps_per_second": 10.27, | |
| "step": 26722 | |
| }, | |
| { | |
| "epoch": 432.0, | |
| "eval_loss": 11.156039237976074, | |
| "eval_runtime": 1.5566, | |
| "eval_samples_per_second": 79.019, | |
| "eval_steps_per_second": 10.279, | |
| "step": 26784 | |
| }, | |
| { | |
| "epoch": 433.0, | |
| "eval_loss": 11.059048652648926, | |
| "eval_runtime": 1.5499, | |
| "eval_samples_per_second": 79.358, | |
| "eval_steps_per_second": 10.323, | |
| "step": 26846 | |
| }, | |
| { | |
| "epoch": 434.0, | |
| "eval_loss": 11.01535415649414, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.233, | |
| "eval_steps_per_second": 10.307, | |
| "step": 26908 | |
| }, | |
| { | |
| "epoch": 435.0, | |
| "eval_loss": 10.964756965637207, | |
| "eval_runtime": 1.553, | |
| "eval_samples_per_second": 79.204, | |
| "eval_steps_per_second": 10.303, | |
| "step": 26970 | |
| }, | |
| { | |
| "epoch": 435.48, | |
| "learning_rate": 9.03225806451613e-09, | |
| "loss": 10.0079, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 436.0, | |
| "eval_loss": 11.084016799926758, | |
| "eval_runtime": 1.559, | |
| "eval_samples_per_second": 78.895, | |
| "eval_steps_per_second": 10.263, | |
| "step": 27032 | |
| }, | |
| { | |
| "epoch": 437.0, | |
| "eval_loss": 10.810328483581543, | |
| "eval_runtime": 1.5654, | |
| "eval_samples_per_second": 78.574, | |
| "eval_steps_per_second": 10.221, | |
| "step": 27094 | |
| }, | |
| { | |
| "epoch": 438.0, | |
| "eval_loss": 10.89944839477539, | |
| "eval_runtime": 1.557, | |
| "eval_samples_per_second": 79.0, | |
| "eval_steps_per_second": 10.276, | |
| "step": 27156 | |
| }, | |
| { | |
| "epoch": 439.0, | |
| "eval_loss": 11.036003112792969, | |
| "eval_runtime": 1.5567, | |
| "eval_samples_per_second": 79.015, | |
| "eval_steps_per_second": 10.278, | |
| "step": 27218 | |
| }, | |
| { | |
| "epoch": 440.0, | |
| "eval_loss": 10.909425735473633, | |
| "eval_runtime": 1.5567, | |
| "eval_samples_per_second": 79.013, | |
| "eval_steps_per_second": 10.278, | |
| "step": 27280 | |
| }, | |
| { | |
| "epoch": 441.0, | |
| "eval_loss": 10.940203666687012, | |
| "eval_runtime": 1.5862, | |
| "eval_samples_per_second": 77.542, | |
| "eval_steps_per_second": 10.087, | |
| "step": 27342 | |
| }, | |
| { | |
| "epoch": 442.0, | |
| "eval_loss": 10.877068519592285, | |
| "eval_runtime": 1.5493, | |
| "eval_samples_per_second": 79.388, | |
| "eval_steps_per_second": 10.327, | |
| "step": 27404 | |
| }, | |
| { | |
| "epoch": 443.0, | |
| "eval_loss": 11.093377113342285, | |
| "eval_runtime": 1.5504, | |
| "eval_samples_per_second": 79.335, | |
| "eval_steps_per_second": 10.32, | |
| "step": 27466 | |
| }, | |
| { | |
| "epoch": 443.55, | |
| "learning_rate": 7.903225806451614e-09, | |
| "loss": 10.0049, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 444.0, | |
| "eval_loss": 11.089668273925781, | |
| "eval_runtime": 1.5636, | |
| "eval_samples_per_second": 78.663, | |
| "eval_steps_per_second": 10.233, | |
| "step": 27528 | |
| }, | |
| { | |
| "epoch": 445.0, | |
| "eval_loss": 11.049309730529785, | |
| "eval_runtime": 1.5562, | |
| "eval_samples_per_second": 79.038, | |
| "eval_steps_per_second": 10.281, | |
| "step": 27590 | |
| }, | |
| { | |
| "epoch": 446.0, | |
| "eval_loss": 11.039472579956055, | |
| "eval_runtime": 1.5633, | |
| "eval_samples_per_second": 78.678, | |
| "eval_steps_per_second": 10.235, | |
| "step": 27652 | |
| }, | |
| { | |
| "epoch": 447.0, | |
| "eval_loss": 10.898978233337402, | |
| "eval_runtime": 1.5657, | |
| "eval_samples_per_second": 78.558, | |
| "eval_steps_per_second": 10.219, | |
| "step": 27714 | |
| }, | |
| { | |
| "epoch": 448.0, | |
| "eval_loss": 11.16734504699707, | |
| "eval_runtime": 1.5575, | |
| "eval_samples_per_second": 78.975, | |
| "eval_steps_per_second": 10.273, | |
| "step": 27776 | |
| }, | |
| { | |
| "epoch": 449.0, | |
| "eval_loss": 11.158203125, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.235, | |
| "eval_steps_per_second": 10.307, | |
| "step": 27838 | |
| }, | |
| { | |
| "epoch": 450.0, | |
| "eval_loss": 10.85914421081543, | |
| "eval_runtime": 1.5491, | |
| "eval_samples_per_second": 79.399, | |
| "eval_steps_per_second": 10.328, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 451.0, | |
| "eval_loss": 11.079207420349121, | |
| "eval_runtime": 1.5491, | |
| "eval_samples_per_second": 79.398, | |
| "eval_steps_per_second": 10.328, | |
| "step": 27962 | |
| }, | |
| { | |
| "epoch": 451.61, | |
| "learning_rate": 6.774193548387097e-09, | |
| "loss": 9.9924, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 452.0, | |
| "eval_loss": 11.144965171813965, | |
| "eval_runtime": 1.5578, | |
| "eval_samples_per_second": 78.958, | |
| "eval_steps_per_second": 10.271, | |
| "step": 28024 | |
| }, | |
| { | |
| "epoch": 453.0, | |
| "eval_loss": 10.981874465942383, | |
| "eval_runtime": 1.5581, | |
| "eval_samples_per_second": 78.94, | |
| "eval_steps_per_second": 10.269, | |
| "step": 28086 | |
| }, | |
| { | |
| "epoch": 454.0, | |
| "eval_loss": 10.887094497680664, | |
| "eval_runtime": 1.5515, | |
| "eval_samples_per_second": 79.28, | |
| "eval_steps_per_second": 10.313, | |
| "step": 28148 | |
| }, | |
| { | |
| "epoch": 455.0, | |
| "eval_loss": 10.99148178100586, | |
| "eval_runtime": 1.558, | |
| "eval_samples_per_second": 78.947, | |
| "eval_steps_per_second": 10.27, | |
| "step": 28210 | |
| }, | |
| { | |
| "epoch": 456.0, | |
| "eval_loss": 11.03730583190918, | |
| "eval_runtime": 1.5584, | |
| "eval_samples_per_second": 78.926, | |
| "eval_steps_per_second": 10.267, | |
| "step": 28272 | |
| }, | |
| { | |
| "epoch": 457.0, | |
| "eval_loss": 10.938337326049805, | |
| "eval_runtime": 1.5696, | |
| "eval_samples_per_second": 78.366, | |
| "eval_steps_per_second": 10.194, | |
| "step": 28334 | |
| }, | |
| { | |
| "epoch": 458.0, | |
| "eval_loss": 11.129241943359375, | |
| "eval_runtime": 1.5563, | |
| "eval_samples_per_second": 79.032, | |
| "eval_steps_per_second": 10.281, | |
| "step": 28396 | |
| }, | |
| { | |
| "epoch": 459.0, | |
| "eval_loss": 11.168819427490234, | |
| "eval_runtime": 1.5502, | |
| "eval_samples_per_second": 79.343, | |
| "eval_steps_per_second": 10.321, | |
| "step": 28458 | |
| }, | |
| { | |
| "epoch": 459.68, | |
| "learning_rate": 5.645161290322581e-09, | |
| "loss": 9.9918, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 460.0, | |
| "eval_loss": 11.043048858642578, | |
| "eval_runtime": 1.5622, | |
| "eval_samples_per_second": 78.736, | |
| "eval_steps_per_second": 10.242, | |
| "step": 28520 | |
| }, | |
| { | |
| "epoch": 461.0, | |
| "eval_loss": 11.071016311645508, | |
| "eval_runtime": 1.5582, | |
| "eval_samples_per_second": 78.938, | |
| "eval_steps_per_second": 10.268, | |
| "step": 28582 | |
| }, | |
| { | |
| "epoch": 462.0, | |
| "eval_loss": 11.011009216308594, | |
| "eval_runtime": 1.554, | |
| "eval_samples_per_second": 79.151, | |
| "eval_steps_per_second": 10.296, | |
| "step": 28644 | |
| }, | |
| { | |
| "epoch": 463.0, | |
| "eval_loss": 11.087599754333496, | |
| "eval_runtime": 1.5566, | |
| "eval_samples_per_second": 79.02, | |
| "eval_steps_per_second": 10.279, | |
| "step": 28706 | |
| }, | |
| { | |
| "epoch": 464.0, | |
| "eval_loss": 11.0982027053833, | |
| "eval_runtime": 1.5598, | |
| "eval_samples_per_second": 78.856, | |
| "eval_steps_per_second": 10.258, | |
| "step": 28768 | |
| }, | |
| { | |
| "epoch": 465.0, | |
| "eval_loss": 10.962496757507324, | |
| "eval_runtime": 1.5771, | |
| "eval_samples_per_second": 77.992, | |
| "eval_steps_per_second": 10.145, | |
| "step": 28830 | |
| }, | |
| { | |
| "epoch": 466.0, | |
| "eval_loss": 10.964188575744629, | |
| "eval_runtime": 1.5492, | |
| "eval_samples_per_second": 79.395, | |
| "eval_steps_per_second": 10.328, | |
| "step": 28892 | |
| }, | |
| { | |
| "epoch": 467.0, | |
| "eval_loss": 10.798909187316895, | |
| "eval_runtime": 1.5512, | |
| "eval_samples_per_second": 79.296, | |
| "eval_steps_per_second": 10.315, | |
| "step": 28954 | |
| }, | |
| { | |
| "epoch": 467.74, | |
| "learning_rate": 4.516129032258065e-09, | |
| "loss": 9.9799, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 468.0, | |
| "eval_loss": 11.00378131866455, | |
| "eval_runtime": 1.562, | |
| "eval_samples_per_second": 78.745, | |
| "eval_steps_per_second": 10.243, | |
| "step": 29016 | |
| }, | |
| { | |
| "epoch": 469.0, | |
| "eval_loss": 11.124489784240723, | |
| "eval_runtime": 1.5579, | |
| "eval_samples_per_second": 78.951, | |
| "eval_steps_per_second": 10.27, | |
| "step": 29078 | |
| }, | |
| { | |
| "epoch": 470.0, | |
| "eval_loss": 10.913480758666992, | |
| "eval_runtime": 1.5763, | |
| "eval_samples_per_second": 78.031, | |
| "eval_steps_per_second": 10.15, | |
| "step": 29140 | |
| }, | |
| { | |
| "epoch": 471.0, | |
| "eval_loss": 10.943198204040527, | |
| "eval_runtime": 1.5563, | |
| "eval_samples_per_second": 79.031, | |
| "eval_steps_per_second": 10.281, | |
| "step": 29202 | |
| }, | |
| { | |
| "epoch": 472.0, | |
| "eval_loss": 10.829460144042969, | |
| "eval_runtime": 1.5569, | |
| "eval_samples_per_second": 79.005, | |
| "eval_steps_per_second": 10.277, | |
| "step": 29264 | |
| }, | |
| { | |
| "epoch": 473.0, | |
| "eval_loss": 10.927714347839355, | |
| "eval_runtime": 1.5542, | |
| "eval_samples_per_second": 79.141, | |
| "eval_steps_per_second": 10.295, | |
| "step": 29326 | |
| }, | |
| { | |
| "epoch": 474.0, | |
| "eval_loss": 11.094922065734863, | |
| "eval_runtime": 1.5516, | |
| "eval_samples_per_second": 79.274, | |
| "eval_steps_per_second": 10.312, | |
| "step": 29388 | |
| }, | |
| { | |
| "epoch": 475.0, | |
| "eval_loss": 11.037424087524414, | |
| "eval_runtime": 1.5502, | |
| "eval_samples_per_second": 79.343, | |
| "eval_steps_per_second": 10.321, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 475.81, | |
| "learning_rate": 3.3870967741935484e-09, | |
| "loss": 9.9961, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 476.0, | |
| "eval_loss": 10.958832740783691, | |
| "eval_runtime": 1.5596, | |
| "eval_samples_per_second": 78.865, | |
| "eval_steps_per_second": 10.259, | |
| "step": 29512 | |
| }, | |
| { | |
| "epoch": 477.0, | |
| "eval_loss": 11.034053802490234, | |
| "eval_runtime": 1.5537, | |
| "eval_samples_per_second": 79.168, | |
| "eval_steps_per_second": 10.298, | |
| "step": 29574 | |
| }, | |
| { | |
| "epoch": 478.0, | |
| "eval_loss": 10.954147338867188, | |
| "eval_runtime": 1.563, | |
| "eval_samples_per_second": 78.695, | |
| "eval_steps_per_second": 10.237, | |
| "step": 29636 | |
| }, | |
| { | |
| "epoch": 479.0, | |
| "eval_loss": 10.934306144714355, | |
| "eval_runtime": 1.5578, | |
| "eval_samples_per_second": 78.957, | |
| "eval_steps_per_second": 10.271, | |
| "step": 29698 | |
| }, | |
| { | |
| "epoch": 480.0, | |
| "eval_loss": 10.959942817687988, | |
| "eval_runtime": 1.5525, | |
| "eval_samples_per_second": 79.225, | |
| "eval_steps_per_second": 10.306, | |
| "step": 29760 | |
| }, | |
| { | |
| "epoch": 481.0, | |
| "eval_loss": 10.95332145690918, | |
| "eval_runtime": 1.5572, | |
| "eval_samples_per_second": 78.988, | |
| "eval_steps_per_second": 10.275, | |
| "step": 29822 | |
| }, | |
| { | |
| "epoch": 482.0, | |
| "eval_loss": 11.204573631286621, | |
| "eval_runtime": 1.5776, | |
| "eval_samples_per_second": 77.964, | |
| "eval_steps_per_second": 10.142, | |
| "step": 29884 | |
| }, | |
| { | |
| "epoch": 483.0, | |
| "eval_loss": 10.935157775878906, | |
| "eval_runtime": 1.5461, | |
| "eval_samples_per_second": 79.557, | |
| "eval_steps_per_second": 10.349, | |
| "step": 29946 | |
| }, | |
| { | |
| "epoch": 483.87, | |
| "learning_rate": 2.2580645161290324e-09, | |
| "loss": 10.006, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 484.0, | |
| "eval_loss": 11.172720909118652, | |
| "eval_runtime": 1.5619, | |
| "eval_samples_per_second": 78.751, | |
| "eval_steps_per_second": 10.244, | |
| "step": 30008 | |
| }, | |
| { | |
| "epoch": 485.0, | |
| "eval_loss": 10.99561595916748, | |
| "eval_runtime": 1.5552, | |
| "eval_samples_per_second": 79.09, | |
| "eval_steps_per_second": 10.288, | |
| "step": 30070 | |
| }, | |
| { | |
| "epoch": 486.0, | |
| "eval_loss": 11.166374206542969, | |
| "eval_runtime": 1.5713, | |
| "eval_samples_per_second": 78.281, | |
| "eval_steps_per_second": 10.183, | |
| "step": 30132 | |
| }, | |
| { | |
| "epoch": 487.0, | |
| "eval_loss": 11.094931602478027, | |
| "eval_runtime": 1.553, | |
| "eval_samples_per_second": 79.2, | |
| "eval_steps_per_second": 10.302, | |
| "step": 30194 | |
| }, | |
| { | |
| "epoch": 488.0, | |
| "eval_loss": 10.948943138122559, | |
| "eval_runtime": 1.5549, | |
| "eval_samples_per_second": 79.102, | |
| "eval_steps_per_second": 10.29, | |
| "step": 30256 | |
| }, | |
| { | |
| "epoch": 489.0, | |
| "eval_loss": 11.004921913146973, | |
| "eval_runtime": 1.5546, | |
| "eval_samples_per_second": 79.121, | |
| "eval_steps_per_second": 10.292, | |
| "step": 30318 | |
| }, | |
| { | |
| "epoch": 490.0, | |
| "eval_loss": 11.18515396118164, | |
| "eval_runtime": 1.5529, | |
| "eval_samples_per_second": 79.207, | |
| "eval_steps_per_second": 10.303, | |
| "step": 30380 | |
| }, | |
| { | |
| "epoch": 491.0, | |
| "eval_loss": 11.10179615020752, | |
| "eval_runtime": 1.5524, | |
| "eval_samples_per_second": 79.232, | |
| "eval_steps_per_second": 10.307, | |
| "step": 30442 | |
| }, | |
| { | |
| "epoch": 491.94, | |
| "learning_rate": 1.1290322580645162e-09, | |
| "loss": 10.0083, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 492.0, | |
| "eval_loss": 10.913029670715332, | |
| "eval_runtime": 1.5534, | |
| "eval_samples_per_second": 79.18, | |
| "eval_steps_per_second": 10.3, | |
| "step": 30504 | |
| }, | |
| { | |
| "epoch": 493.0, | |
| "eval_loss": 10.935208320617676, | |
| "eval_runtime": 1.5558, | |
| "eval_samples_per_second": 79.058, | |
| "eval_steps_per_second": 10.284, | |
| "step": 30566 | |
| }, | |
| { | |
| "epoch": 494.0, | |
| "eval_loss": 10.9716157913208, | |
| "eval_runtime": 1.5545, | |
| "eval_samples_per_second": 79.127, | |
| "eval_steps_per_second": 10.293, | |
| "step": 30628 | |
| }, | |
| { | |
| "epoch": 495.0, | |
| "eval_loss": 11.111549377441406, | |
| "eval_runtime": 1.5613, | |
| "eval_samples_per_second": 78.778, | |
| "eval_steps_per_second": 10.248, | |
| "step": 30690 | |
| }, | |
| { | |
| "epoch": 496.0, | |
| "eval_loss": 10.980956077575684, | |
| "eval_runtime": 1.5565, | |
| "eval_samples_per_second": 79.022, | |
| "eval_steps_per_second": 10.279, | |
| "step": 30752 | |
| }, | |
| { | |
| "epoch": 497.0, | |
| "eval_loss": 10.970294952392578, | |
| "eval_runtime": 1.5649, | |
| "eval_samples_per_second": 78.597, | |
| "eval_steps_per_second": 10.224, | |
| "step": 30814 | |
| }, | |
| { | |
| "epoch": 498.0, | |
| "eval_loss": 10.939518928527832, | |
| "eval_runtime": 1.547, | |
| "eval_samples_per_second": 79.51, | |
| "eval_steps_per_second": 10.343, | |
| "step": 30876 | |
| }, | |
| { | |
| "epoch": 499.0, | |
| "eval_loss": 11.018895149230957, | |
| "eval_runtime": 1.5496, | |
| "eval_samples_per_second": 79.375, | |
| "eval_steps_per_second": 10.325, | |
| "step": 30938 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "learning_rate": 0.0, | |
| "loss": 10.0106, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "eval_loss": 10.97592544555664, | |
| "eval_runtime": 1.5827, | |
| "eval_samples_per_second": 77.713, | |
| "eval_steps_per_second": 10.109, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "step": 31000, | |
| "total_flos": 1.6136618439168e+16, | |
| "train_loss": 11.119525689894154, | |
| "train_runtime": 17411.7991, | |
| "train_samples_per_second": 14.042, | |
| "train_steps_per_second": 1.78 | |
| } | |
| ], | |
| "max_steps": 31000, | |
| "num_train_epochs": 500, | |
| "total_flos": 1.6136618439168e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |