| { | |
| "best_metric": 0.42307427525520325, | |
| "best_model_checkpoint": "ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v4/checkpoint-552", | |
| "epoch": 9.99864314789688, | |
| "global_step": 1380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8e-08, | |
| "loss": 0.1429, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.6e-07, | |
| "loss": 0.1481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.4e-07, | |
| "loss": 0.1462, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.2e-07, | |
| "loss": 0.1509, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4e-07, | |
| "loss": 0.1472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.8e-07, | |
| "loss": 0.1351, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.1424, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 6.4e-07, | |
| "loss": 0.1417, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.2e-07, | |
| "loss": 0.1396, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8e-07, | |
| "loss": 0.1409, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.799999999999999e-07, | |
| "loss": 0.1424, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.6e-07, | |
| "loss": 0.1196, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.04e-06, | |
| "loss": 0.1335, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4255823493003845, | |
| "eval_runtime": 221.8873, | |
| "eval_samples_per_second": 8.856, | |
| "eval_steps_per_second": 1.109, | |
| "eval_wer": 0.16052615365658307, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.12e-06, | |
| "loss": 0.1412, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.2e-06, | |
| "loss": 0.1357, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.28e-06, | |
| "loss": 0.1437, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 0.134, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.44e-06, | |
| "loss": 0.1426, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.5199999999999998e-06, | |
| "loss": 0.1353, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.6e-06, | |
| "loss": 0.1406, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.6799999999999998e-06, | |
| "loss": 0.1403, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.752e-06, | |
| "loss": 0.136, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.832e-06, | |
| "loss": 0.1392, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.9119999999999997e-06, | |
| "loss": 0.1462, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9919999999999997e-06, | |
| "loss": 0.1266, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.072e-06, | |
| "loss": 0.1296, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.152e-06, | |
| "loss": 0.1288, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.42343059182167053, | |
| "eval_runtime": 220.812, | |
| "eval_samples_per_second": 8.899, | |
| "eval_steps_per_second": 1.114, | |
| "eval_wer": 0.1602181011644384, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.232e-06, | |
| "loss": 0.1483, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.3119999999999996e-06, | |
| "loss": 0.1344, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.3919999999999997e-06, | |
| "loss": 0.1253, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.472e-06, | |
| "loss": 0.1559, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.552e-06, | |
| "loss": 0.1326, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.632e-06, | |
| "loss": 0.1303, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.712e-06, | |
| "loss": 0.131, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.7919999999999997e-06, | |
| "loss": 0.1474, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.8719999999999998e-06, | |
| "loss": 0.1302, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.952e-06, | |
| "loss": 0.1304, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.032e-06, | |
| "loss": 0.1452, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.112e-06, | |
| "loss": 0.1344, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.192e-06, | |
| "loss": 0.1307, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.2719999999999998e-06, | |
| "loss": 0.1278, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4242633581161499, | |
| "eval_runtime": 220.7296, | |
| "eval_samples_per_second": 8.902, | |
| "eval_steps_per_second": 1.114, | |
| "eval_wer": 0.15966360667857804, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.352e-06, | |
| "loss": 0.1423, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.432e-06, | |
| "loss": 0.1306, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.512e-06, | |
| "loss": 0.1348, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.592e-06, | |
| "loss": 0.1445, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.672e-06, | |
| "loss": 0.1418, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.7519999999999994e-06, | |
| "loss": 0.1356, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3.832e-06, | |
| "loss": 0.1291, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 3.912e-06, | |
| "loss": 0.1318, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.992e-06, | |
| "loss": 0.1342, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.9590909090909085e-06, | |
| "loss": 0.1184, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 3.913636363636363e-06, | |
| "loss": 0.1338, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.868181818181818e-06, | |
| "loss": 0.1372, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.822727272727272e-06, | |
| "loss": 0.127, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.7772727272727273e-06, | |
| "loss": 0.1345, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.42307427525520325, | |
| "eval_runtime": 221.8583, | |
| "eval_samples_per_second": 8.857, | |
| "eval_steps_per_second": 1.109, | |
| "eval_wer": 0.1596944119277925, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.731818181818182e-06, | |
| "loss": 0.1328, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.6863636363636365e-06, | |
| "loss": 0.1305, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.640909090909091e-06, | |
| "loss": 0.1344, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 3.595454545454545e-06, | |
| "loss": 0.1362, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.5499999999999995e-06, | |
| "loss": 0.1335, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 3.504545454545454e-06, | |
| "loss": 0.1309, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 3.4590909090909087e-06, | |
| "loss": 0.129, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 3.4136363636363633e-06, | |
| "loss": 0.1321, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 3.368181818181818e-06, | |
| "loss": 0.1276, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 3.3227272727272724e-06, | |
| "loss": 0.1304, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 3.277272727272727e-06, | |
| "loss": 0.1308, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.2318181818181816e-06, | |
| "loss": 0.1257, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 3.1863636363636362e-06, | |
| "loss": 0.1299, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.140909090909091e-06, | |
| "loss": 0.1344, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.4246298372745514, | |
| "eval_runtime": 221.0199, | |
| "eval_samples_per_second": 8.891, | |
| "eval_steps_per_second": 1.113, | |
| "eval_wer": 0.15966360667857804, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 3.095454545454545e-06, | |
| "loss": 0.1366, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 3.0499999999999996e-06, | |
| "loss": 0.1345, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 3.004545454545454e-06, | |
| "loss": 0.1286, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.959090909090909e-06, | |
| "loss": 0.1336, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.9136363636363634e-06, | |
| "loss": 0.1267, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 2.868181818181818e-06, | |
| "loss": 0.1202, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 2.8227272727272726e-06, | |
| "loss": 0.1252, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.777272727272727e-06, | |
| "loss": 0.1257, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.7318181818181818e-06, | |
| "loss": 0.1151, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 2.6863636363636364e-06, | |
| "loss": 0.1254, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2.640909090909091e-06, | |
| "loss": 0.1289, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 2.595454545454545e-06, | |
| "loss": 0.1289, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 2.5499999999999997e-06, | |
| "loss": 0.1237, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.4279264509677887, | |
| "eval_runtime": 221.1731, | |
| "eval_samples_per_second": 8.884, | |
| "eval_steps_per_second": 1.112, | |
| "eval_wer": 0.15954038568172016, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.5045454545454543e-06, | |
| "loss": 0.138, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 2.459090909090909e-06, | |
| "loss": 0.1273, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 2.4136363636363635e-06, | |
| "loss": 0.1264, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 2.368181818181818e-06, | |
| "loss": 0.1172, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 2.3227272727272727e-06, | |
| "loss": 0.1273, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 2.2772727272727273e-06, | |
| "loss": 0.1186, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 2.231818181818182e-06, | |
| "loss": 0.1229, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 2.1863636363636365e-06, | |
| "loss": 0.1341, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 2.140909090909091e-06, | |
| "loss": 0.125, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 2.0954545454545453e-06, | |
| "loss": 0.124, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 2.05e-06, | |
| "loss": 0.1303, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 2.0045454545454544e-06, | |
| "loss": 0.1371, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.959090909090909e-06, | |
| "loss": 0.115, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.9136363636363636e-06, | |
| "loss": 0.1109, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.435354620218277, | |
| "eval_runtime": 221.7806, | |
| "eval_samples_per_second": 8.86, | |
| "eval_steps_per_second": 1.109, | |
| "eval_wer": 0.1573224077382786, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.868181818181818e-06, | |
| "loss": 0.1374, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.8227272727272726e-06, | |
| "loss": 0.1225, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 1.7772727272727272e-06, | |
| "loss": 0.1217, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.7318181818181818e-06, | |
| "loss": 0.1215, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.6863636363636362e-06, | |
| "loss": 0.1235, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.6409090909090908e-06, | |
| "loss": 0.1183, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.5954545454545454e-06, | |
| "loss": 0.1248, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1.55e-06, | |
| "loss": 0.1274, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.5045454545454546e-06, | |
| "loss": 0.1287, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.459090909090909e-06, | |
| "loss": 0.127, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.4136363636363636e-06, | |
| "loss": 0.1281, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 1.3681818181818182e-06, | |
| "loss": 0.1223, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.3227272727272727e-06, | |
| "loss": 0.1163, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.2772727272727273e-06, | |
| "loss": 0.1247, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.43181082606315613, | |
| "eval_runtime": 222.5795, | |
| "eval_samples_per_second": 8.828, | |
| "eval_steps_per_second": 1.105, | |
| "eval_wer": 0.15698354999691946, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 1.231818181818182e-06, | |
| "loss": 0.1235, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.1863636363636363e-06, | |
| "loss": 0.1212, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.140909090909091e-06, | |
| "loss": 0.1265, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 1.0954545454545453e-06, | |
| "loss": 0.1243, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 1.05e-06, | |
| "loss": 0.1187, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1.0045454545454545e-06, | |
| "loss": 0.1182, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 9.59090909090909e-07, | |
| "loss": 0.1266, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 9.136363636363637e-07, | |
| "loss": 0.1288, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.681818181818182e-07, | |
| "loss": 0.1149, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.227272727272727e-07, | |
| "loss": 0.122, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 7.772727272727272e-07, | |
| "loss": 0.1195, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 7.318181818181818e-07, | |
| "loss": 0.1144, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 6.863636363636363e-07, | |
| "loss": 0.1185, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 6.409090909090908e-07, | |
| "loss": 0.1372, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4340789318084717, | |
| "eval_runtime": 224.1668, | |
| "eval_samples_per_second": 8.766, | |
| "eval_steps_per_second": 1.097, | |
| "eval_wer": 0.15726079723984968, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 5.954545454545454e-07, | |
| "loss": 0.1214, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 5.5e-07, | |
| "loss": 0.1147, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 5.045454545454545e-07, | |
| "loss": 0.1161, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 4.5909090909090906e-07, | |
| "loss": 0.1334, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 4.136363636363636e-07, | |
| "loss": 0.1165, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 3.6818181818181815e-07, | |
| "loss": 0.1171, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 3.2272727272727274e-07, | |
| "loss": 0.1327, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.772727272727273e-07, | |
| "loss": 0.1171, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 2.318181818181818e-07, | |
| "loss": 0.1204, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.8636363636363637e-07, | |
| "loss": 0.1298, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 1.4090909090909089e-07, | |
| "loss": 0.1305, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 9.545454545454546e-08, | |
| "loss": 0.1294, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 5e-08, | |
| "loss": 0.115, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.545454545454545e-09, | |
| "loss": 0.1256, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.4328223168849945, | |
| "eval_runtime": 221.2478, | |
| "eval_samples_per_second": 8.881, | |
| "eval_steps_per_second": 1.112, | |
| "eval_wer": 0.1575072392335654, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1380, | |
| "total_flos": 5.359319261116583e+19, | |
| "train_loss": 0.13009323823279229, | |
| "train_runtime": 33247.4378, | |
| "train_samples_per_second": 5.319, | |
| "train_steps_per_second": 0.042 | |
| } | |
| ], | |
| "max_steps": 1380, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.359319261116583e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |