| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 82, | |
| "global_step": 245, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004081632653061225, | |
| "grad_norm": 0.03618604317307472, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004081632653061225, | |
| "eval_loss": 1.2217298746109009, | |
| "eval_runtime": 117.7701, | |
| "eval_samples_per_second": 20.735, | |
| "eval_steps_per_second": 10.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00816326530612245, | |
| "grad_norm": 0.03361086547374725, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1923, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012244897959183673, | |
| "grad_norm": 0.034457892179489136, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0744, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "grad_norm": 0.03408154472708702, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2796, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.03475559875369072, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024489795918367346, | |
| "grad_norm": 0.03768599033355713, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 0.03434902802109718, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2194, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0326530612244898, | |
| "grad_norm": 0.029295403510332108, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1522, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036734693877551024, | |
| "grad_norm": 0.027247965335845947, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1636, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.027813177555799484, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044897959183673466, | |
| "grad_norm": 0.027455640956759453, | |
| "learning_rate": 0.00019999906115681734, | |
| "loss": 1.2151, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04897959183673469, | |
| "grad_norm": 0.026825131848454475, | |
| "learning_rate": 0.0001999962446448979, | |
| "loss": 1.1751, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.053061224489795916, | |
| "grad_norm": 0.026261834427714348, | |
| "learning_rate": 0.0001999915505171269, | |
| "loss": 1.0573, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 0.022048471495509148, | |
| "learning_rate": 0.0001999849788616454, | |
| "loss": 1.1997, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 0.01966056413948536, | |
| "learning_rate": 0.00019997652980184843, | |
| "loss": 1.1469, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0653061224489796, | |
| "grad_norm": 0.021213103085756302, | |
| "learning_rate": 0.00019996620349638285, | |
| "loss": 1.15, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06938775510204082, | |
| "grad_norm": 0.02238585613667965, | |
| "learning_rate": 0.00019995400013914427, | |
| "loss": 1.206, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07346938775510205, | |
| "grad_norm": 0.02359834685921669, | |
| "learning_rate": 0.0001999399199592735, | |
| "loss": 1.3413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07755102040816327, | |
| "grad_norm": 0.022565221413969994, | |
| "learning_rate": 0.00019992396322115213, | |
| "loss": 1.1798, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.02135898545384407, | |
| "learning_rate": 0.0001999061302243977, | |
| "loss": 1.1602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 0.02203250862658024, | |
| "learning_rate": 0.00019988642130385788, | |
| "loss": 1.0915, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08979591836734693, | |
| "grad_norm": 0.01716572232544422, | |
| "learning_rate": 0.00019986483682960445, | |
| "loss": 1.1858, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09387755102040816, | |
| "grad_norm": 0.01753074862062931, | |
| "learning_rate": 0.00019984137720692612, | |
| "loss": 1.1849, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09795918367346938, | |
| "grad_norm": 0.017932750284671783, | |
| "learning_rate": 0.00019981604287632102, | |
| "loss": 1.1579, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.017208363860845566, | |
| "learning_rate": 0.00019978883431348845, | |
| "loss": 1.1223, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10612244897959183, | |
| "grad_norm": 0.01637221872806549, | |
| "learning_rate": 0.00019975975202931982, | |
| "loss": 1.1809, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11020408163265306, | |
| "grad_norm": 0.016254756599664688, | |
| "learning_rate": 0.0001997287965698893, | |
| "loss": 1.1978, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 0.016743820160627365, | |
| "learning_rate": 0.00019969596851644327, | |
| "loss": 1.1273, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11836734693877551, | |
| "grad_norm": 0.020556606352329254, | |
| "learning_rate": 0.0001996612684853896, | |
| "loss": 1.1638, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 0.019542187452316284, | |
| "learning_rate": 0.00019962469712828614, | |
| "loss": 1.2558, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12653061224489795, | |
| "grad_norm": 0.01658390648663044, | |
| "learning_rate": 0.00019958625513182815, | |
| "loss": 1.2176, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1306122448979592, | |
| "grad_norm": 0.017420461401343346, | |
| "learning_rate": 0.00019954594321783584, | |
| "loss": 1.2671, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1346938775510204, | |
| "grad_norm": 0.01890096440911293, | |
| "learning_rate": 0.00019950376214324052, | |
| "loss": 1.1448, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13877551020408163, | |
| "grad_norm": 0.016807271167635918, | |
| "learning_rate": 0.00019945971270007043, | |
| "loss": 1.2085, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.015759294852614403, | |
| "learning_rate": 0.00019941379571543596, | |
| "loss": 1.2207, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1469387755102041, | |
| "grad_norm": 0.016418293118476868, | |
| "learning_rate": 0.00019936601205151414, | |
| "loss": 1.1031, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1510204081632653, | |
| "grad_norm": 0.017639920115470886, | |
| "learning_rate": 0.00019931636260553224, | |
| "loss": 1.1439, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15510204081632653, | |
| "grad_norm": 0.01651432178914547, | |
| "learning_rate": 0.00019926484830975113, | |
| "loss": 1.1111, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15918367346938775, | |
| "grad_norm": 0.016843752935528755, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.2519, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.016024339944124222, | |
| "learning_rate": 0.00019915622907289694, | |
| "loss": 1.2122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1673469387755102, | |
| "grad_norm": 0.017350338399410248, | |
| "learning_rate": 0.00019909912617135244, | |
| "loss": 1.2104, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 0.01698286086320877, | |
| "learning_rate": 0.00019904016249902763, | |
| "loss": 1.2258, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17551020408163265, | |
| "grad_norm": 0.016692234203219414, | |
| "learning_rate": 0.00019897933916307543, | |
| "loss": 1.1614, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17959183673469387, | |
| "grad_norm": 0.01875966228544712, | |
| "learning_rate": 0.00019891665730556725, | |
| "loss": 1.2314, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 0.016782566905021667, | |
| "learning_rate": 0.00019885211810347184, | |
| "loss": 1.2096, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18775510204081633, | |
| "grad_norm": 0.017428990453481674, | |
| "learning_rate": 0.00019878572276863294, | |
| "loss": 1.0537, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19183673469387755, | |
| "grad_norm": 0.016738982871174812, | |
| "learning_rate": 0.00019871747254774673, | |
| "loss": 1.2018, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19591836734693877, | |
| "grad_norm": 0.018019411712884903, | |
| "learning_rate": 0.0001986473687223383, | |
| "loss": 1.2504, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.017473606392741203, | |
| "learning_rate": 0.0001985754126087376, | |
| "loss": 1.0481, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 0.017300540581345558, | |
| "learning_rate": 0.00019850160555805486, | |
| "loss": 1.2109, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20816326530612245, | |
| "grad_norm": 0.0182975921779871, | |
| "learning_rate": 0.00019842594895615488, | |
| "loss": 1.1598, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.21224489795918366, | |
| "grad_norm": 0.020277326926589012, | |
| "learning_rate": 0.00019834844422363142, | |
| "loss": 1.1177, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.2163265306122449, | |
| "grad_norm": 0.018494602292776108, | |
| "learning_rate": 0.00019826909281578026, | |
| "loss": 1.1037, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.22040816326530613, | |
| "grad_norm": 0.017682479694485664, | |
| "learning_rate": 0.00019818789622257196, | |
| "loss": 1.1358, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.22448979591836735, | |
| "grad_norm": 0.0186194758862257, | |
| "learning_rate": 0.00019810485596862392, | |
| "loss": 1.1403, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.018025796860456467, | |
| "learning_rate": 0.00019801997361317163, | |
| "loss": 1.1959, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.23265306122448978, | |
| "grad_norm": 0.01819712296128273, | |
| "learning_rate": 0.0001979332507500395, | |
| "loss": 1.1181, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.23673469387755103, | |
| "grad_norm": 0.018991166725754738, | |
| "learning_rate": 0.00019784468900761095, | |
| "loss": 1.1393, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.24081632653061225, | |
| "grad_norm": 0.01914682239294052, | |
| "learning_rate": 0.0001977542900487977, | |
| "loss": 1.182, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.01992950588464737, | |
| "learning_rate": 0.00019766205557100868, | |
| "loss": 1.1629, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24897959183673468, | |
| "grad_norm": 0.024829212576150894, | |
| "learning_rate": 0.00019756798730611813, | |
| "loss": 1.0753, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2530612244897959, | |
| "grad_norm": 0.02457556687295437, | |
| "learning_rate": 0.00019747208702043296, | |
| "loss": 1.1718, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2571428571428571, | |
| "grad_norm": 0.019101744517683983, | |
| "learning_rate": 0.0001973743565146599, | |
| "loss": 1.1343, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2612244897959184, | |
| "grad_norm": 0.020323360338807106, | |
| "learning_rate": 0.00019727479762387116, | |
| "loss": 1.1689, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "grad_norm": 0.018925843760371208, | |
| "learning_rate": 0.00019717341221747056, | |
| "loss": 1.2098, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2693877551020408, | |
| "grad_norm": 0.019229738041758537, | |
| "learning_rate": 0.00019707020219915806, | |
| "loss": 1.1542, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.27346938775510204, | |
| "grad_norm": 0.019665885716676712, | |
| "learning_rate": 0.00019696516950689404, | |
| "loss": 1.1154, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.27755102040816326, | |
| "grad_norm": 0.019163204357028008, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 1.1726, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2816326530612245, | |
| "grad_norm": 0.019880875945091248, | |
| "learning_rate": 0.00019674964402343684, | |
| "loss": 1.1441, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.019096847623586655, | |
| "learning_rate": 0.00019663915527913625, | |
| "loss": 1.2021, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2897959183673469, | |
| "grad_norm": 0.019253911450505257, | |
| "learning_rate": 0.00019652685195459344, | |
| "loss": 1.1237, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2938775510204082, | |
| "grad_norm": 0.020909370854496956, | |
| "learning_rate": 0.00019641273615851257, | |
| "loss": 1.0575, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2979591836734694, | |
| "grad_norm": 0.019176874309778214, | |
| "learning_rate": 0.00019629681003363044, | |
| "loss": 1.0377, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3020408163265306, | |
| "grad_norm": 0.019969960674643517, | |
| "learning_rate": 0.00019617907575667602, | |
| "loss": 1.1471, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.019450997933745384, | |
| "learning_rate": 0.00019605953553832988, | |
| "loss": 1.2022, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31020408163265306, | |
| "grad_norm": 0.02082456275820732, | |
| "learning_rate": 0.00019593819162318232, | |
| "loss": 1.0932, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3142857142857143, | |
| "grad_norm": 0.020122263580560684, | |
| "learning_rate": 0.00019581504628969154, | |
| "loss": 1.0826, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3183673469387755, | |
| "grad_norm": 0.020104922354221344, | |
| "learning_rate": 0.00019569010185014062, | |
| "loss": 1.1404, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3224489795918367, | |
| "grad_norm": 0.021288864314556122, | |
| "learning_rate": 0.00019556336065059432, | |
| "loss": 1.0951, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.02072795107960701, | |
| "learning_rate": 0.00019543482507085482, | |
| "loss": 1.0649, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3306122448979592, | |
| "grad_norm": 0.020123451948165894, | |
| "learning_rate": 0.00019530449752441718, | |
| "loss": 1.1333, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3346938775510204, | |
| "grad_norm": 0.020374584943056107, | |
| "learning_rate": 0.00019517238045842404, | |
| "loss": 1.147, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3346938775510204, | |
| "eval_loss": 1.1397618055343628, | |
| "eval_runtime": 120.3925, | |
| "eval_samples_per_second": 20.284, | |
| "eval_steps_per_second": 10.142, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.33877551020408164, | |
| "grad_norm": 0.0197721179574728, | |
| "learning_rate": 0.00019503847635361944, | |
| "loss": 1.0954, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.021181972697377205, | |
| "learning_rate": 0.00019490278772430256, | |
| "loss": 1.1145, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3469387755102041, | |
| "grad_norm": 0.021057790145277977, | |
| "learning_rate": 0.00019476531711828027, | |
| "loss": 1.2255, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3510204081632653, | |
| "grad_norm": 0.0207724217325449, | |
| "learning_rate": 0.00019462606711681936, | |
| "loss": 1.0366, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3551020408163265, | |
| "grad_norm": 0.021172018721699715, | |
| "learning_rate": 0.00019448504033459818, | |
| "loss": 1.0835, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.35918367346938773, | |
| "grad_norm": 0.02109033428132534, | |
| "learning_rate": 0.00019434223941965738, | |
| "loss": 1.0902, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.363265306122449, | |
| "grad_norm": 0.02078443393111229, | |
| "learning_rate": 0.00019419766705335026, | |
| "loss": 1.087, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 0.020614784210920334, | |
| "learning_rate": 0.0001940513259502924, | |
| "loss": 1.0834, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37142857142857144, | |
| "grad_norm": 0.020187893882393837, | |
| "learning_rate": 0.0001939032188583108, | |
| "loss": 1.1847, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.37551020408163266, | |
| "grad_norm": 0.020622489973902702, | |
| "learning_rate": 0.0001937533485583921, | |
| "loss": 1.1767, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3795918367346939, | |
| "grad_norm": 0.02118833176791668, | |
| "learning_rate": 0.00019360171786463043, | |
| "loss": 1.1491, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3836734693877551, | |
| "grad_norm": 0.021402837708592415, | |
| "learning_rate": 0.00019344832962417475, | |
| "loss": 1.1547, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3877551020408163, | |
| "grad_norm": 0.02148307114839554, | |
| "learning_rate": 0.0001932931867171751, | |
| "loss": 1.2062, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.39183673469387753, | |
| "grad_norm": 0.022203955799341202, | |
| "learning_rate": 0.00019313629205672868, | |
| "loss": 1.1271, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.39591836734693875, | |
| "grad_norm": 0.02081882208585739, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 1.0965, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.021749386563897133, | |
| "learning_rate": 0.00019281725929229127, | |
| "loss": 1.11, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.40408163265306124, | |
| "grad_norm": 0.02319493517279625, | |
| "learning_rate": 0.00019265512717873498, | |
| "loss": 1.0196, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.021901512518525124, | |
| "learning_rate": 0.0001924912552924889, | |
| "loss": 1.1552, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4122448979591837, | |
| "grad_norm": 0.02368365228176117, | |
| "learning_rate": 0.00019232564671055306, | |
| "loss": 1.2047, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4163265306122449, | |
| "grad_norm": 0.022438503801822662, | |
| "learning_rate": 0.00019215830454253724, | |
| "loss": 1.1429, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4204081632653061, | |
| "grad_norm": 0.022685807198286057, | |
| "learning_rate": 0.00019198923193060254, | |
| "loss": 1.0717, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.42448979591836733, | |
| "grad_norm": 0.023902015760540962, | |
| "learning_rate": 0.00019181843204940232, | |
| "loss": 1.1139, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.022928839549422264, | |
| "learning_rate": 0.00019164590810602262, | |
| "loss": 1.1515, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4326530612244898, | |
| "grad_norm": 0.02210794948041439, | |
| "learning_rate": 0.00019147166333992205, | |
| "loss": 1.1762, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.43673469387755104, | |
| "grad_norm": 0.023219434544444084, | |
| "learning_rate": 0.00019129570102287082, | |
| "loss": 1.1925, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.44081632653061226, | |
| "grad_norm": 0.023004446178674698, | |
| "learning_rate": 0.00019111802445888936, | |
| "loss": 1.1449, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.4448979591836735, | |
| "grad_norm": 0.023740626871585846, | |
| "learning_rate": 0.00019093863698418627, | |
| "loss": 1.2179, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 0.06276971846818924, | |
| "learning_rate": 0.00019075754196709572, | |
| "loss": 1.2497, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4530612244897959, | |
| "grad_norm": 0.023355931043624878, | |
| "learning_rate": 0.00019057474280801415, | |
| "loss": 1.1625, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.03020629473030567, | |
| "learning_rate": 0.00019039024293933645, | |
| "loss": 1.0821, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.46122448979591835, | |
| "grad_norm": 0.022392934188246727, | |
| "learning_rate": 0.00019020404582539152, | |
| "loss": 1.1074, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.46530612244897956, | |
| "grad_norm": 0.023577727377414703, | |
| "learning_rate": 0.00019001615496237712, | |
| "loss": 1.1128, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.46938775510204084, | |
| "grad_norm": 0.023507297039031982, | |
| "learning_rate": 0.00018982657387829445, | |
| "loss": 1.1345, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.47346938775510206, | |
| "grad_norm": 0.023036476224660873, | |
| "learning_rate": 0.0001896353061328816, | |
| "loss": 1.128, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.4775510204081633, | |
| "grad_norm": 0.023640332743525505, | |
| "learning_rate": 0.00018944235531754698, | |
| "loss": 1.062, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.4816326530612245, | |
| "grad_norm": 0.022972116246819496, | |
| "learning_rate": 0.00018924772505530174, | |
| "loss": 1.1024, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.4857142857142857, | |
| "grad_norm": 0.023795459419488907, | |
| "learning_rate": 0.00018905141900069178, | |
| "loss": 1.1595, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.02379484474658966, | |
| "learning_rate": 0.00018885344083972914, | |
| "loss": 1.1492, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49387755102040815, | |
| "grad_norm": 0.023673737421631813, | |
| "learning_rate": 0.00018865379428982271, | |
| "loss": 1.1571, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.49795918367346936, | |
| "grad_norm": 0.02365570329129696, | |
| "learning_rate": 0.00018845248309970854, | |
| "loss": 1.1216, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5020408163265306, | |
| "grad_norm": 0.025217821821570396, | |
| "learning_rate": 0.00018824951104937947, | |
| "loss": 1.1422, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5061224489795918, | |
| "grad_norm": 0.02457055076956749, | |
| "learning_rate": 0.00018804488195001392, | |
| "loss": 1.119, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 0.023103831335902214, | |
| "learning_rate": 0.00018783859964390464, | |
| "loss": 1.153, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 0.02386569045484066, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.137, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5183673469387755, | |
| "grad_norm": 0.024395650252699852, | |
| "learning_rate": 0.00018742109093576313, | |
| "loss": 1.1592, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5224489795918368, | |
| "grad_norm": 0.024944225326180458, | |
| "learning_rate": 0.000187209872373235, | |
| "loss": 1.1395, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5265306122448979, | |
| "grad_norm": 0.023946771398186684, | |
| "learning_rate": 0.00018699701628282407, | |
| "loss": 1.1779, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 0.02391199767589569, | |
| "learning_rate": 0.00018678252666130013, | |
| "loss": 1.1299, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5346938775510204, | |
| "grad_norm": 0.0230008065700531, | |
| "learning_rate": 0.00018656640753610563, | |
| "loss": 1.1087, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5387755102040817, | |
| "grad_norm": 0.023263461887836456, | |
| "learning_rate": 0.0001863486629652799, | |
| "loss": 1.0835, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5428571428571428, | |
| "grad_norm": 0.024622686207294464, | |
| "learning_rate": 0.000186129297037383, | |
| "loss": 1.0911, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5469387755102041, | |
| "grad_norm": 0.023301225155591965, | |
| "learning_rate": 0.0001859083138714191, | |
| "loss": 1.1345, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5510204081632653, | |
| "grad_norm": 0.023047855123877525, | |
| "learning_rate": 0.00018568571761675893, | |
| "loss": 1.1353, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5551020408163265, | |
| "grad_norm": 0.025225356221199036, | |
| "learning_rate": 0.00018546151245306205, | |
| "loss": 1.149, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.5591836734693878, | |
| "grad_norm": 0.024374982342123985, | |
| "learning_rate": 0.00018523570259019827, | |
| "loss": 1.0618, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.563265306122449, | |
| "grad_norm": 0.024517694488167763, | |
| "learning_rate": 0.00018500829226816853, | |
| "loss": 1.148, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5673469387755102, | |
| "grad_norm": 0.022940896451473236, | |
| "learning_rate": 0.0001847792857570255, | |
| "loss": 1.0824, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.025163279846310616, | |
| "learning_rate": 0.0001845486873567932, | |
| "loss": 1.112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5755102040816327, | |
| "grad_norm": 0.024664800614118576, | |
| "learning_rate": 0.00018431650139738633, | |
| "loss": 1.1398, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5795918367346938, | |
| "grad_norm": 0.02429143153131008, | |
| "learning_rate": 0.000184082732238529, | |
| "loss": 1.2003, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.5836734693877551, | |
| "grad_norm": 0.026087280362844467, | |
| "learning_rate": 0.00018384738426967283, | |
| "loss": 1.1151, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5877551020408164, | |
| "grad_norm": 0.025691909715533257, | |
| "learning_rate": 0.00018361046190991455, | |
| "loss": 1.1526, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5918367346938775, | |
| "grad_norm": 0.024672340601682663, | |
| "learning_rate": 0.00018337196960791302, | |
| "loss": 1.1781, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5959183673469388, | |
| "grad_norm": 0.025797029957175255, | |
| "learning_rate": 0.00018313191184180568, | |
| "loss": 1.2053, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.025542639195919037, | |
| "learning_rate": 0.0001828902931191244, | |
| "loss": 1.0819, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6040816326530613, | |
| "grad_norm": 0.025126414373517036, | |
| "learning_rate": 0.0001826471179767111, | |
| "loss": 1.1935, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6081632653061224, | |
| "grad_norm": 0.02403743751347065, | |
| "learning_rate": 0.0001824023909806322, | |
| "loss": 1.1151, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.025347478687763214, | |
| "learning_rate": 0.00018215611672609317, | |
| "loss": 1.0863, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6163265306122448, | |
| "grad_norm": 0.024234246462583542, | |
| "learning_rate": 0.00018190829983735207, | |
| "loss": 0.9933, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6204081632653061, | |
| "grad_norm": 0.02541242353618145, | |
| "learning_rate": 0.00018165894496763286, | |
| "loss": 1.016, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6244897959183674, | |
| "grad_norm": 0.025475289672613144, | |
| "learning_rate": 0.00018140805679903795, | |
| "loss": 1.1199, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 0.025047162547707558, | |
| "learning_rate": 0.00018115564004246023, | |
| "loss": 1.1866, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6326530612244898, | |
| "grad_norm": 0.024512339383363724, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.0407, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.636734693877551, | |
| "grad_norm": 0.027875879779458046, | |
| "learning_rate": 0.0001806462397523496, | |
| "loss": 1.1148, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6408163265306123, | |
| "grad_norm": 0.027647798880934715, | |
| "learning_rate": 0.00018038926578375653, | |
| "loss": 1.1748, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6448979591836734, | |
| "grad_norm": 0.0258516576141119, | |
| "learning_rate": 0.0001801307823568806, | |
| "loss": 1.156, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6489795918367347, | |
| "grad_norm": 0.02649206854403019, | |
| "learning_rate": 0.00017987079432522996, | |
| "loss": 1.0625, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.027242302894592285, | |
| "learning_rate": 0.00017960930657056438, | |
| "loss": 1.0624, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6571428571428571, | |
| "grad_norm": 0.026996418833732605, | |
| "learning_rate": 0.0001793463240028038, | |
| "loss": 1.0979, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.6612244897959184, | |
| "grad_norm": 0.025911618024110794, | |
| "learning_rate": 0.00017908185155993605, | |
| "loss": 1.0767, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.6653061224489796, | |
| "grad_norm": 0.02710540033876896, | |
| "learning_rate": 0.0001788158942079241, | |
| "loss": 0.9389, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.6693877551020408, | |
| "grad_norm": 0.026086492463946342, | |
| "learning_rate": 0.00017854845694061292, | |
| "loss": 1.1475, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.6693877551020408, | |
| "eval_loss": 1.1236058473587036, | |
| "eval_runtime": 120.3474, | |
| "eval_samples_per_second": 20.291, | |
| "eval_steps_per_second": 10.146, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.673469387755102, | |
| "grad_norm": 0.02641923353075981, | |
| "learning_rate": 0.00017827954477963557, | |
| "loss": 1.1128, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6775510204081633, | |
| "grad_norm": 0.026196755468845367, | |
| "learning_rate": 0.00017800916277431908, | |
| "loss": 1.059, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.6816326530612244, | |
| "grad_norm": 0.025523358955979347, | |
| "learning_rate": 0.00017773731600158947, | |
| "loss": 1.1618, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.026307355612516403, | |
| "learning_rate": 0.00017746400956587653, | |
| "loss": 1.0585, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.689795918367347, | |
| "grad_norm": 0.026362139731645584, | |
| "learning_rate": 0.00017718924859901793, | |
| "loss": 1.0543, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6938775510204082, | |
| "grad_norm": 0.02530169114470482, | |
| "learning_rate": 0.0001769130382601629, | |
| "loss": 1.1009, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6979591836734694, | |
| "grad_norm": 0.026273014023900032, | |
| "learning_rate": 0.0001766353837356753, | |
| "loss": 1.1963, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7020408163265306, | |
| "grad_norm": 0.026570703834295273, | |
| "learning_rate": 0.00017635629023903627, | |
| "loss": 1.1098, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7061224489795919, | |
| "grad_norm": 0.02533114328980446, | |
| "learning_rate": 0.0001760757630107464, | |
| "loss": 1.2321, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.710204081632653, | |
| "grad_norm": 0.02558620274066925, | |
| "learning_rate": 0.00017579380731822712, | |
| "loss": 1.1174, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.028141306713223457, | |
| "learning_rate": 0.00017551042845572208, | |
| "loss": 1.0609, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7183673469387755, | |
| "grad_norm": 0.028484290465712547, | |
| "learning_rate": 0.00017522563174419753, | |
| "loss": 1.0779, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7224489795918367, | |
| "grad_norm": 0.0262393057346344, | |
| "learning_rate": 0.00017493942253124248, | |
| "loss": 1.0889, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.726530612244898, | |
| "grad_norm": 0.029188042506575584, | |
| "learning_rate": 0.00017465180619096832, | |
| "loss": 1.1816, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7306122448979592, | |
| "grad_norm": 0.02816024050116539, | |
| "learning_rate": 0.00017436278812390786, | |
| "loss": 1.155, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 0.026962874457240105, | |
| "learning_rate": 0.00017407237375691392, | |
| "loss": 1.0784, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7387755102040816, | |
| "grad_norm": 0.027746373787522316, | |
| "learning_rate": 0.00017378056854305747, | |
| "loss": 1.1896, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 0.02716743014752865, | |
| "learning_rate": 0.00017348737796152522, | |
| "loss": 1.0722, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.746938775510204, | |
| "grad_norm": 0.02938067726790905, | |
| "learning_rate": 0.0001731928075175168, | |
| "loss": 1.0179, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7510204081632653, | |
| "grad_norm": 0.03580696880817413, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 1.0951, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.7551020408163265, | |
| "grad_norm": 0.02849019691348076, | |
| "learning_rate": 0.0001725995491923131, | |
| "loss": 1.1006, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7591836734693878, | |
| "grad_norm": 0.026822512969374657, | |
| "learning_rate": 0.00017230087245064858, | |
| "loss": 1.1535, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.763265306122449, | |
| "grad_norm": 0.027751388028264046, | |
| "learning_rate": 0.00017200083812536, | |
| "loss": 1.0975, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.7673469387755102, | |
| "grad_norm": 0.027201151475310326, | |
| "learning_rate": 0.00017169945185015106, | |
| "loss": 1.1022, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.7714285714285715, | |
| "grad_norm": 0.026958104223012924, | |
| "learning_rate": 0.00017139671928411072, | |
| "loss": 1.14, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.7755102040816326, | |
| "grad_norm": 0.026919234544038773, | |
| "learning_rate": 0.00017109264611160708, | |
| "loss": 1.1056, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7795918367346939, | |
| "grad_norm": 0.027088504284620285, | |
| "learning_rate": 0.00017078723804218066, | |
| "loss": 1.2057, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.7836734693877551, | |
| "grad_norm": 0.027464529499411583, | |
| "learning_rate": 0.00017048050081043713, | |
| "loss": 1.1709, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7877551020408163, | |
| "grad_norm": 0.028090914711356163, | |
| "learning_rate": 0.0001701724401759397, | |
| "loss": 1.1489, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.7918367346938775, | |
| "grad_norm": 0.026381971314549446, | |
| "learning_rate": 0.00016986306192310084, | |
| "loss": 1.0724, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.7959183673469388, | |
| "grad_norm": 0.027733104303479195, | |
| "learning_rate": 0.00016955237186107387, | |
| "loss": 1.1281, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.026476366445422173, | |
| "learning_rate": 0.0001692403758236437, | |
| "loss": 1.19, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8040816326530612, | |
| "grad_norm": 0.02931978367269039, | |
| "learning_rate": 0.0001689270796691174, | |
| "loss": 1.0904, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8081632653061225, | |
| "grad_norm": 0.02770647406578064, | |
| "learning_rate": 0.00016861248928021411, | |
| "loss": 1.1499, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8122448979591836, | |
| "grad_norm": 0.02689889818429947, | |
| "learning_rate": 0.00016829661056395474, | |
| "loss": 1.1525, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.02684464119374752, | |
| "learning_rate": 0.0001679794494515508, | |
| "loss": 1.0428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8204081632653061, | |
| "grad_norm": 0.026796666905283928, | |
| "learning_rate": 0.0001676610118982933, | |
| "loss": 1.1829, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.8244897959183674, | |
| "grad_norm": 0.028474919497966766, | |
| "learning_rate": 0.00016734130388344073, | |
| "loss": 1.0853, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.8285714285714286, | |
| "grad_norm": 0.027959391474723816, | |
| "learning_rate": 0.00016702033141010694, | |
| "loss": 1.0554, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.8326530612244898, | |
| "grad_norm": 0.027617380023002625, | |
| "learning_rate": 0.00016669810050514827, | |
| "loss": 1.2237, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8367346938775511, | |
| "grad_norm": 0.028105339035391808, | |
| "learning_rate": 0.00016637461721905045, | |
| "loss": 1.0778, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8408163265306122, | |
| "grad_norm": 0.028216930106282234, | |
| "learning_rate": 0.00016604988762581512, | |
| "loss": 1.1507, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.8448979591836735, | |
| "grad_norm": 0.026569265872240067, | |
| "learning_rate": 0.00016572391782284547, | |
| "loss": 1.0134, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.8489795918367347, | |
| "grad_norm": 0.027188677340745926, | |
| "learning_rate": 0.00016539671393083215, | |
| "loss": 1.0784, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.8530612244897959, | |
| "grad_norm": 0.02793797291815281, | |
| "learning_rate": 0.00016506828209363796, | |
| "loss": 1.1477, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.027332162484526634, | |
| "learning_rate": 0.00016473862847818277, | |
| "loss": 1.1653, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8612244897959184, | |
| "grad_norm": 0.02860257215797901, | |
| "learning_rate": 0.00016440775927432753, | |
| "loss": 1.1599, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.8653061224489796, | |
| "grad_norm": 0.028649616986513138, | |
| "learning_rate": 0.0001640756806947582, | |
| "loss": 1.1796, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.8693877551020408, | |
| "grad_norm": 0.027630403637886047, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.1315, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.8734693877551021, | |
| "grad_norm": 0.027829712256789207, | |
| "learning_rate": 0.00016340792037264527, | |
| "loss": 1.0573, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.8775510204081632, | |
| "grad_norm": 0.027864307165145874, | |
| "learning_rate": 0.00016307225116854622, | |
| "loss": 1.083, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8816326530612245, | |
| "grad_norm": 0.028005510568618774, | |
| "learning_rate": 0.0001627353976653866, | |
| "loss": 1.238, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.8857142857142857, | |
| "grad_norm": 0.02755396068096161, | |
| "learning_rate": 0.00016239736618821885, | |
| "loss": 1.1124, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.889795918367347, | |
| "grad_norm": 0.026409147307276726, | |
| "learning_rate": 0.00016205816308421386, | |
| "loss": 1.1627, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.8938775510204081, | |
| "grad_norm": 0.02800268866121769, | |
| "learning_rate": 0.00016171779472254206, | |
| "loss": 1.0921, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 0.02667434886097908, | |
| "learning_rate": 0.00016137626749425377, | |
| "loss": 1.207, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9020408163265307, | |
| "grad_norm": 0.027823835611343384, | |
| "learning_rate": 0.0001610335878121592, | |
| "loss": 1.0776, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.9061224489795918, | |
| "grad_norm": 0.02820996195077896, | |
| "learning_rate": 0.000160689762110708, | |
| "loss": 1.0903, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.9102040816326531, | |
| "grad_norm": 0.02725161425769329, | |
| "learning_rate": 0.00016034479684586854, | |
| "loss": 1.1587, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.027408665046095848, | |
| "learning_rate": 0.0001599986984950065, | |
| "loss": 1.1058, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 0.027829701080918312, | |
| "learning_rate": 0.00015965147355676343, | |
| "loss": 1.1037, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9224489795918367, | |
| "grad_norm": 0.027295254170894623, | |
| "learning_rate": 0.0001593031285509347, | |
| "loss": 1.0681, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.926530612244898, | |
| "grad_norm": 0.028630707412958145, | |
| "learning_rate": 0.00015895367001834694, | |
| "loss": 1.1282, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.9306122448979591, | |
| "grad_norm": 0.02818943001329899, | |
| "learning_rate": 0.0001586031045207354, | |
| "loss": 1.1101, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.9346938775510204, | |
| "grad_norm": 0.028520913794636726, | |
| "learning_rate": 0.0001582514386406206, | |
| "loss": 1.1716, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.9387755102040817, | |
| "grad_norm": 0.027190426364541054, | |
| "learning_rate": 0.0001578986789811849, | |
| "loss": 1.0615, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9428571428571428, | |
| "grad_norm": 0.028909413143992424, | |
| "learning_rate": 0.00015754483216614821, | |
| "loss": 1.0757, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.9469387755102041, | |
| "grad_norm": 0.028231430798768997, | |
| "learning_rate": 0.000157189904839644, | |
| "loss": 1.14, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.9510204081632653, | |
| "grad_norm": 0.02774875983595848, | |
| "learning_rate": 0.00015683390366609426, | |
| "loss": 1.0429, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.9551020408163265, | |
| "grad_norm": 0.030419837683439255, | |
| "learning_rate": 0.00015647683533008455, | |
| "loss": 1.113, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.9591836734693877, | |
| "grad_norm": 0.028292929753661156, | |
| "learning_rate": 0.00015611870653623825, | |
| "loss": 1.1127, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.963265306122449, | |
| "grad_norm": 0.028285473585128784, | |
| "learning_rate": 0.00015575952400909092, | |
| "loss": 1.0493, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.9673469387755103, | |
| "grad_norm": 0.028861958533525467, | |
| "learning_rate": 0.00015539929449296392, | |
| "loss": 1.0879, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 0.02901526540517807, | |
| "learning_rate": 0.00015503802475183773, | |
| "loss": 1.21, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.9755102040816327, | |
| "grad_norm": 0.02809295803308487, | |
| "learning_rate": 0.00015467572156922503, | |
| "loss": 1.1949, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.03164355456829071, | |
| "learning_rate": 0.00015431239174804328, | |
| "loss": 1.068, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9836734693877551, | |
| "grad_norm": 0.029855625703930855, | |
| "learning_rate": 0.00015394804211048702, | |
| "loss": 1.1485, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.9877551020408163, | |
| "grad_norm": 0.027486370876431465, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 1.0449, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.9918367346938776, | |
| "grad_norm": 0.02765297144651413, | |
| "learning_rate": 0.0001532163107706452, | |
| "loss": 1.0341, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.9959183673469387, | |
| "grad_norm": 0.02840602956712246, | |
| "learning_rate": 0.0001528489428079793, | |
| "loss": 1.2001, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.028239021077752113, | |
| "learning_rate": 0.00015248058250792008, | |
| "loss": 1.1528, | |
| "step": 245 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 735, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 245, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.954959055015117e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |