| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 215, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004651162790697674, | |
| "grad_norm": 19.567298889160156, | |
| "learning_rate": 0.0, | |
| "loss": 0.842, | |
| "mean_token_accuracy": 0.8234314918518066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009302325581395349, | |
| "grad_norm": 21.546506881713867, | |
| "learning_rate": 4.5454545454545457e-07, | |
| "loss": 0.8778, | |
| "mean_token_accuracy": 0.8231534361839294, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013953488372093023, | |
| "grad_norm": 19.17478370666504, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 0.8512, | |
| "mean_token_accuracy": 0.8325784802436829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018604651162790697, | |
| "grad_norm": 18.24776840209961, | |
| "learning_rate": 1.3636363636363636e-06, | |
| "loss": 0.8166, | |
| "mean_token_accuracy": 0.8310983777046204, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023255813953488372, | |
| "grad_norm": 21.58199691772461, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.9323, | |
| "mean_token_accuracy": 0.8089540600776672, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027906976744186046, | |
| "grad_norm": 18.450977325439453, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 0.7835, | |
| "mean_token_accuracy": 0.8290299773216248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03255813953488372, | |
| "grad_norm": 17.034927368164062, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 0.8108, | |
| "mean_token_accuracy": 0.8261110186576843, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037209302325581395, | |
| "grad_norm": 10.061210632324219, | |
| "learning_rate": 3.181818181818182e-06, | |
| "loss": 0.6384, | |
| "mean_token_accuracy": 0.8510469794273376, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04186046511627907, | |
| "grad_norm": 8.766654014587402, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.5635, | |
| "mean_token_accuracy": 0.8622041344642639, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046511627906976744, | |
| "grad_norm": 9.165151596069336, | |
| "learning_rate": 4.0909090909090915e-06, | |
| "loss": 0.4929, | |
| "mean_token_accuracy": 0.8713976144790649, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05116279069767442, | |
| "grad_norm": 9.168291091918945, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.4219, | |
| "mean_token_accuracy": 0.8905084729194641, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05581395348837209, | |
| "grad_norm": 7.447816848754883, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4407, | |
| "mean_token_accuracy": 0.8805750608444214, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06046511627906977, | |
| "grad_norm": 4.2195329666137695, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 0.4192, | |
| "mean_token_accuracy": 0.8761147856712341, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06511627906976744, | |
| "grad_norm": 6.262633800506592, | |
| "learning_rate": 5.90909090909091e-06, | |
| "loss": 0.365, | |
| "mean_token_accuracy": 0.8887879252433777, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06976744186046512, | |
| "grad_norm": 3.4587056636810303, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 0.3438, | |
| "mean_token_accuracy": 0.896136462688446, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 3.7988815307617188, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 0.3813, | |
| "mean_token_accuracy": 0.8868741989135742, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07906976744186046, | |
| "grad_norm": 3.0814735889434814, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 0.3327, | |
| "mean_token_accuracy": 0.9037970304489136, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08372093023255814, | |
| "grad_norm": 3.080644369125366, | |
| "learning_rate": 7.727272727272727e-06, | |
| "loss": 0.3776, | |
| "mean_token_accuracy": 0.8831896185874939, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08837209302325581, | |
| "grad_norm": 3.344931125640869, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 0.3838, | |
| "mean_token_accuracy": 0.8845933079719543, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "grad_norm": 2.879211902618408, | |
| "learning_rate": 8.636363636363637e-06, | |
| "loss": 0.3506, | |
| "mean_token_accuracy": 0.8925349712371826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09767441860465116, | |
| "grad_norm": 3.1432149410247803, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.3999, | |
| "mean_token_accuracy": 0.8764577507972717, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10232558139534884, | |
| "grad_norm": 3.1957945823669434, | |
| "learning_rate": 9.545454545454547e-06, | |
| "loss": 0.3518, | |
| "mean_token_accuracy": 0.8833417296409607, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10697674418604651, | |
| "grad_norm": 3.03271746635437, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3453, | |
| "mean_token_accuracy": 0.8945419192314148, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11162790697674418, | |
| "grad_norm": 3.291729688644409, | |
| "learning_rate": 9.999403846557509e-06, | |
| "loss": 0.3717, | |
| "mean_token_accuracy": 0.8789581060409546, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 3.003061532974243, | |
| "learning_rate": 9.99761554418511e-06, | |
| "loss": 0.3326, | |
| "mean_token_accuracy": 0.8965391516685486, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12093023255813953, | |
| "grad_norm": 3.0343496799468994, | |
| "learning_rate": 9.99463556670619e-06, | |
| "loss": 0.3348, | |
| "mean_token_accuracy": 0.8980305790901184, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12558139534883722, | |
| "grad_norm": 3.125955581665039, | |
| "learning_rate": 9.990464703686895e-06, | |
| "loss": 0.3642, | |
| "mean_token_accuracy": 0.8900479078292847, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13023255813953488, | |
| "grad_norm": 3.0945956707000732, | |
| "learning_rate": 9.985104060226937e-06, | |
| "loss": 0.3525, | |
| "mean_token_accuracy": 0.8904315233230591, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13488372093023257, | |
| "grad_norm": 2.9179065227508545, | |
| "learning_rate": 9.978555056666784e-06, | |
| "loss": 0.3758, | |
| "mean_token_accuracy": 0.878148078918457, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13953488372093023, | |
| "grad_norm": 3.0580294132232666, | |
| "learning_rate": 9.97081942821133e-06, | |
| "loss": 0.3706, | |
| "mean_token_accuracy": 0.8867707252502441, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14418604651162792, | |
| "grad_norm": 3.400860548019409, | |
| "learning_rate": 9.961899224470146e-06, | |
| "loss": 0.3954, | |
| "mean_token_accuracy": 0.8813920617103577, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 3.082350015640259, | |
| "learning_rate": 9.95179680891442e-06, | |
| "loss": 0.3192, | |
| "mean_token_accuracy": 0.9054816961288452, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15348837209302327, | |
| "grad_norm": 3.6603596210479736, | |
| "learning_rate": 9.940514858250736e-06, | |
| "loss": 0.3557, | |
| "mean_token_accuracy": 0.8928727507591248, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15813953488372093, | |
| "grad_norm": 2.8968210220336914, | |
| "learning_rate": 9.928056361711854e-06, | |
| "loss": 0.3035, | |
| "mean_token_accuracy": 0.9041560888290405, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16279069767441862, | |
| "grad_norm": 3.001267910003662, | |
| "learning_rate": 9.914424620264714e-06, | |
| "loss": 0.3582, | |
| "mean_token_accuracy": 0.8920079469680786, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16744186046511628, | |
| "grad_norm": 3.011969804763794, | |
| "learning_rate": 9.899623245735798e-06, | |
| "loss": 0.3287, | |
| "mean_token_accuracy": 0.8975402116775513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.17209302325581396, | |
| "grad_norm": 3.0174691677093506, | |
| "learning_rate": 9.883656159854166e-06, | |
| "loss": 0.317, | |
| "mean_token_accuracy": 0.9030527472496033, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17674418604651163, | |
| "grad_norm": 3.017667770385742, | |
| "learning_rate": 9.866527593212355e-06, | |
| "loss": 0.3317, | |
| "mean_token_accuracy": 0.898614764213562, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1813953488372093, | |
| "grad_norm": 2.9910168647766113, | |
| "learning_rate": 9.848242084145462e-06, | |
| "loss": 0.3197, | |
| "mean_token_accuracy": 0.9013782143592834, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 2.8677515983581543, | |
| "learning_rate": 9.82880447752868e-06, | |
| "loss": 0.3379, | |
| "mean_token_accuracy": 0.892432451248169, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19069767441860466, | |
| "grad_norm": 2.9924676418304443, | |
| "learning_rate": 9.808219923493606e-06, | |
| "loss": 0.3315, | |
| "mean_token_accuracy": 0.8977129459381104, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19534883720930232, | |
| "grad_norm": 3.1997480392456055, | |
| "learning_rate": 9.786493876063685e-06, | |
| "loss": 0.3294, | |
| "mean_token_accuracy": 0.8943057656288147, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.065096139907837, | |
| "learning_rate": 9.763632091709125e-06, | |
| "loss": 0.3098, | |
| "mean_token_accuracy": 0.8971515893936157, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20465116279069767, | |
| "grad_norm": 2.9235894680023193, | |
| "learning_rate": 9.739640627821678e-06, | |
| "loss": 0.337, | |
| "mean_token_accuracy": 0.8972011804580688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20930232558139536, | |
| "grad_norm": 3.2635066509246826, | |
| "learning_rate": 9.714525841109697e-06, | |
| "loss": 0.2949, | |
| "mean_token_accuracy": 0.9037721157073975, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21395348837209302, | |
| "grad_norm": 3.1191279888153076, | |
| "learning_rate": 9.68829438591387e-06, | |
| "loss": 0.3032, | |
| "mean_token_accuracy": 0.8996775150299072, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2186046511627907, | |
| "grad_norm": 3.006911277770996, | |
| "learning_rate": 9.660953212444116e-06, | |
| "loss": 0.3133, | |
| "mean_token_accuracy": 0.8989732265472412, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": 2.850074529647827, | |
| "learning_rate": 9.632509564938073e-06, | |
| "loss": 0.3208, | |
| "mean_token_accuracy": 0.8968409895896912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22790697674418606, | |
| "grad_norm": 2.948340654373169, | |
| "learning_rate": 9.60297097974169e-06, | |
| "loss": 0.3137, | |
| "mean_token_accuracy": 0.8964706063270569, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 2.8453824520111084, | |
| "learning_rate": 9.572345283312407e-06, | |
| "loss": 0.3159, | |
| "mean_token_accuracy": 0.897345781326294, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2372093023255814, | |
| "grad_norm": 3.1784887313842773, | |
| "learning_rate": 9.540640590145496e-06, | |
| "loss": 0.3353, | |
| "mean_token_accuracy": 0.881118893623352, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.24186046511627907, | |
| "grad_norm": 2.855491876602173, | |
| "learning_rate": 9.507865300624057e-06, | |
| "loss": 0.3362, | |
| "mean_token_accuracy": 0.8851703405380249, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24651162790697675, | |
| "grad_norm": 2.949376106262207, | |
| "learning_rate": 9.474028098793277e-06, | |
| "loss": 0.3125, | |
| "mean_token_accuracy": 0.8956229090690613, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.25116279069767444, | |
| "grad_norm": 2.8063535690307617, | |
| "learning_rate": 9.439137950059539e-06, | |
| "loss": 0.3295, | |
| "mean_token_accuracy": 0.8899326324462891, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2558139534883721, | |
| "grad_norm": 2.7494418621063232, | |
| "learning_rate": 9.403204098814965e-06, | |
| "loss": 0.3284, | |
| "mean_token_accuracy": 0.8907849788665771, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.26046511627906976, | |
| "grad_norm": 2.7804148197174072, | |
| "learning_rate": 9.366236065988053e-06, | |
| "loss": 0.3221, | |
| "mean_token_accuracy": 0.8958985209465027, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2651162790697674, | |
| "grad_norm": 2.4028046131134033, | |
| "learning_rate": 9.32824364652104e-06, | |
| "loss": 0.2815, | |
| "mean_token_accuracy": 0.9091808199882507, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.26976744186046514, | |
| "grad_norm": 2.4756522178649902, | |
| "learning_rate": 9.289236906774663e-06, | |
| "loss": 0.3097, | |
| "mean_token_accuracy": 0.8958024978637695, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2744186046511628, | |
| "grad_norm": 2.751638650894165, | |
| "learning_rate": 9.249226181861e-06, | |
| "loss": 0.2911, | |
| "mean_token_accuracy": 0.9036058783531189, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "grad_norm": 2.585191249847412, | |
| "learning_rate": 9.208222072905113e-06, | |
| "loss": 0.3073, | |
| "mean_token_accuracy": 0.8915842771530151, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2837209302325581, | |
| "grad_norm": 2.779496669769287, | |
| "learning_rate": 9.166235444236209e-06, | |
| "loss": 0.3415, | |
| "mean_token_accuracy": 0.8819169402122498, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.28837209302325584, | |
| "grad_norm": 2.7039053440093994, | |
| "learning_rate": 9.123277420509053e-06, | |
| "loss": 0.3351, | |
| "mean_token_accuracy": 0.8873890042304993, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2930232558139535, | |
| "grad_norm": 2.492391586303711, | |
| "learning_rate": 9.079359383756411e-06, | |
| "loss": 0.3122, | |
| "mean_token_accuracy": 0.899104654788971, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.29767441860465116, | |
| "grad_norm": 2.4722068309783936, | |
| "learning_rate": 9.034492970373305e-06, | |
| "loss": 0.3068, | |
| "mean_token_accuracy": 0.8975745439529419, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3023255813953488, | |
| "grad_norm": 2.647203207015991, | |
| "learning_rate": 8.988690068033864e-06, | |
| "loss": 0.3332, | |
| "mean_token_accuracy": 0.8897951245307922, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.30697674418604654, | |
| "grad_norm": 2.3010151386260986, | |
| "learning_rate": 8.941962812541604e-06, | |
| "loss": 0.2996, | |
| "mean_token_accuracy": 0.8944141864776611, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3116279069767442, | |
| "grad_norm": 2.4877219200134277, | |
| "learning_rate": 8.894323584613951e-06, | |
| "loss": 0.3192, | |
| "mean_token_accuracy": 0.8866016268730164, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.31627906976744186, | |
| "grad_norm": 2.4116365909576416, | |
| "learning_rate": 8.845785006601898e-06, | |
| "loss": 0.2815, | |
| "mean_token_accuracy": 0.9037378430366516, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3209302325581395, | |
| "grad_norm": 2.847550868988037, | |
| "learning_rate": 8.796359939145614e-06, | |
| "loss": 0.3084, | |
| "mean_token_accuracy": 0.8947553634643555, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.32558139534883723, | |
| "grad_norm": 2.678941011428833, | |
| "learning_rate": 8.74606147776692e-06, | |
| "loss": 0.3099, | |
| "mean_token_accuracy": 0.8925092220306396, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3302325581395349, | |
| "grad_norm": 2.5238559246063232, | |
| "learning_rate": 8.694902949399555e-06, | |
| "loss": 0.3082, | |
| "mean_token_accuracy": 0.8990745544433594, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.33488372093023255, | |
| "grad_norm": 2.535845994949341, | |
| "learning_rate": 8.642897908858096e-06, | |
| "loss": 0.3111, | |
| "mean_token_accuracy": 0.8941669464111328, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3395348837209302, | |
| "grad_norm": 2.6473376750946045, | |
| "learning_rate": 8.590060135246516e-06, | |
| "loss": 0.3346, | |
| "mean_token_accuracy": 0.882267415523529, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.34418604651162793, | |
| "grad_norm": 2.2965569496154785, | |
| "learning_rate": 8.53640362830732e-06, | |
| "loss": 0.2884, | |
| "mean_token_accuracy": 0.9010685682296753, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 2.64410400390625, | |
| "learning_rate": 8.481942604712209e-06, | |
| "loss": 0.3173, | |
| "mean_token_accuracy": 0.8925799131393433, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.35348837209302325, | |
| "grad_norm": 2.3445322513580322, | |
| "learning_rate": 8.426691494295269e-06, | |
| "loss": 0.2873, | |
| "mean_token_accuracy": 0.9021676778793335, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3581395348837209, | |
| "grad_norm": 2.4569454193115234, | |
| "learning_rate": 8.370664936229688e-06, | |
| "loss": 0.3131, | |
| "mean_token_accuracy": 0.8937378525733948, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3627906976744186, | |
| "grad_norm": 2.469351053237915, | |
| "learning_rate": 8.313877775149009e-06, | |
| "loss": 0.2738, | |
| "mean_token_accuracy": 0.9056981205940247, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3674418604651163, | |
| "grad_norm": 2.755384922027588, | |
| "learning_rate": 8.256345057213925e-06, | |
| "loss": 0.3137, | |
| "mean_token_accuracy": 0.8920559883117676, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 2.388463020324707, | |
| "learning_rate": 8.198082026125707e-06, | |
| "loss": 0.329, | |
| "mean_token_accuracy": 0.8881613612174988, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3767441860465116, | |
| "grad_norm": 2.511956214904785, | |
| "learning_rate": 8.139104119087265e-06, | |
| "loss": 0.2835, | |
| "mean_token_accuracy": 0.9016087055206299, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3813953488372093, | |
| "grad_norm": 2.458860158920288, | |
| "learning_rate": 8.07942696271296e-06, | |
| "loss": 0.2805, | |
| "mean_token_accuracy": 0.9022295475006104, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.386046511627907, | |
| "grad_norm": 2.3269667625427246, | |
| "learning_rate": 8.019066368888222e-06, | |
| "loss": 0.2873, | |
| "mean_token_accuracy": 0.9029345512390137, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.39069767441860465, | |
| "grad_norm": 2.4445390701293945, | |
| "learning_rate": 7.958038330580067e-06, | |
| "loss": 0.3292, | |
| "mean_token_accuracy": 0.8825581669807434, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3953488372093023, | |
| "grad_norm": 2.364525318145752, | |
| "learning_rate": 7.89635901759967e-06, | |
| "loss": 0.2975, | |
| "mean_token_accuracy": 0.8931054472923279, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.7589550018310547, | |
| "learning_rate": 7.834044772318033e-06, | |
| "loss": 0.3274, | |
| "mean_token_accuracy": 0.8935073018074036, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4046511627906977, | |
| "grad_norm": 2.480086326599121, | |
| "learning_rate": 7.77111210533597e-06, | |
| "loss": 0.3002, | |
| "mean_token_accuracy": 0.8910096287727356, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.40930232558139534, | |
| "grad_norm": 2.7994542121887207, | |
| "learning_rate": 7.707577691109519e-06, | |
| "loss": 0.357, | |
| "mean_token_accuracy": 0.8786247372627258, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.413953488372093, | |
| "grad_norm": 2.2564027309417725, | |
| "learning_rate": 7.6434583635319e-06, | |
| "loss": 0.3001, | |
| "mean_token_accuracy": 0.9035753011703491, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.4186046511627907, | |
| "grad_norm": 2.2497193813323975, | |
| "learning_rate": 7.578771111473276e-06, | |
| "loss": 0.2576, | |
| "mean_token_accuracy": 0.912350594997406, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4232558139534884, | |
| "grad_norm": 2.3696465492248535, | |
| "learning_rate": 7.513533074279427e-06, | |
| "loss": 0.267, | |
| "mean_token_accuracy": 0.907282292842865, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.42790697674418604, | |
| "grad_norm": 2.4598476886749268, | |
| "learning_rate": 7.4477615372305545e-06, | |
| "loss": 0.3204, | |
| "mean_token_accuracy": 0.8929490447044373, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4325581395348837, | |
| "grad_norm": 2.3772904872894287, | |
| "learning_rate": 7.3814739269614265e-06, | |
| "loss": 0.2926, | |
| "mean_token_accuracy": 0.8987920880317688, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4372093023255814, | |
| "grad_norm": 2.3977582454681396, | |
| "learning_rate": 7.314687806844067e-06, | |
| "loss": 0.3063, | |
| "mean_token_accuracy": 0.8976466655731201, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4418604651162791, | |
| "grad_norm": 2.4056527614593506, | |
| "learning_rate": 7.247420872334221e-06, | |
| "loss": 0.3, | |
| "mean_token_accuracy": 0.8967844843864441, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": 2.21224045753479, | |
| "learning_rate": 7.179690946282808e-06, | |
| "loss": 0.2809, | |
| "mean_token_accuracy": 0.9029505848884583, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4511627906976744, | |
| "grad_norm": 2.238804817199707, | |
| "learning_rate": 7.111515974213639e-06, | |
| "loss": 0.2467, | |
| "mean_token_accuracy": 0.9121295809745789, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4558139534883721, | |
| "grad_norm": 2.2870707511901855, | |
| "learning_rate": 7.042914019568621e-06, | |
| "loss": 0.3019, | |
| "mean_token_accuracy": 0.8926584124565125, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4604651162790698, | |
| "grad_norm": 2.1823136806488037, | |
| "learning_rate": 6.973903258921719e-06, | |
| "loss": 0.255, | |
| "mean_token_accuracy": 0.911251425743103, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 2.3375985622406006, | |
| "learning_rate": 6.904501977162949e-06, | |
| "loss": 0.3255, | |
| "mean_token_accuracy": 0.8861442804336548, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4697674418604651, | |
| "grad_norm": 2.354637622833252, | |
| "learning_rate": 6.834728562653659e-06, | |
| "loss": 0.3078, | |
| "mean_token_accuracy": 0.8908148407936096, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4744186046511628, | |
| "grad_norm": 2.4348666667938232, | |
| "learning_rate": 6.764601502354403e-06, | |
| "loss": 0.3055, | |
| "mean_token_accuracy": 0.896285891532898, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4790697674418605, | |
| "grad_norm": 2.2231605052948, | |
| "learning_rate": 6.6941393769266995e-06, | |
| "loss": 0.2961, | |
| "mean_token_accuracy": 0.900016188621521, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.48372093023255813, | |
| "grad_norm": 2.098785638809204, | |
| "learning_rate": 6.6233608558099405e-06, | |
| "loss": 0.2753, | |
| "mean_token_accuracy": 0.906988263130188, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4883720930232558, | |
| "grad_norm": 2.2673146724700928, | |
| "learning_rate": 6.552284692274803e-06, | |
| "loss": 0.3079, | |
| "mean_token_accuracy": 0.8930267095565796, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4930232558139535, | |
| "grad_norm": 2.37483286857605, | |
| "learning_rate": 6.48092971845443e-06, | |
| "loss": 0.2801, | |
| "mean_token_accuracy": 0.9036937355995178, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.49767441860465117, | |
| "grad_norm": 2.382274627685547, | |
| "learning_rate": 6.409314840354724e-06, | |
| "loss": 0.3369, | |
| "mean_token_accuracy": 0.8883913159370422, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.5023255813953489, | |
| "grad_norm": 2.488070011138916, | |
| "learning_rate": 6.337459032845068e-06, | |
| "loss": 0.3148, | |
| "mean_token_accuracy": 0.8880661129951477, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5069767441860465, | |
| "grad_norm": 2.3901352882385254, | |
| "learning_rate": 6.2653813346308e-06, | |
| "loss": 0.2714, | |
| "mean_token_accuracy": 0.9043509364128113, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5116279069767442, | |
| "grad_norm": 2.257891893386841, | |
| "learning_rate": 6.193100843208772e-06, | |
| "loss": 0.2808, | |
| "mean_token_accuracy": 0.8988596200942993, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5162790697674419, | |
| "grad_norm": 2.32903790473938, | |
| "learning_rate": 6.120636709807334e-06, | |
| "loss": 0.3091, | |
| "mean_token_accuracy": 0.8888676762580872, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5209302325581395, | |
| "grad_norm": 2.3868567943573, | |
| "learning_rate": 6.048008134312078e-06, | |
| "loss": 0.2889, | |
| "mean_token_accuracy": 0.9004721641540527, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5255813953488372, | |
| "grad_norm": 2.385404109954834, | |
| "learning_rate": 5.975234360178698e-06, | |
| "loss": 0.3254, | |
| "mean_token_accuracy": 0.8927568793296814, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5302325581395348, | |
| "grad_norm": 2.1846094131469727, | |
| "learning_rate": 5.902334669334287e-06, | |
| "loss": 0.2978, | |
| "mean_token_accuracy": 0.9013272523880005, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5348837209302325, | |
| "grad_norm": 2.44286847114563, | |
| "learning_rate": 5.829328377068476e-06, | |
| "loss": 0.2959, | |
| "mean_token_accuracy": 0.8933088779449463, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5395348837209303, | |
| "grad_norm": 2.484508514404297, | |
| "learning_rate": 5.756234826915686e-06, | |
| "loss": 0.2998, | |
| "mean_token_accuracy": 0.9001529216766357, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5441860465116279, | |
| "grad_norm": 2.573427677154541, | |
| "learning_rate": 5.683073385529938e-06, | |
| "loss": 0.3127, | |
| "mean_token_accuracy": 0.8891766667366028, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5488372093023256, | |
| "grad_norm": 2.2030885219573975, | |
| "learning_rate": 5.60986343755352e-06, | |
| "loss": 0.2615, | |
| "mean_token_accuracy": 0.9069497585296631, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5534883720930233, | |
| "grad_norm": 2.478259563446045, | |
| "learning_rate": 5.536624380480878e-06, | |
| "loss": 0.2509, | |
| "mean_token_accuracy": 0.9125564694404602, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": 2.322470188140869, | |
| "learning_rate": 5.4633756195191235e-06, | |
| "loss": 0.2591, | |
| "mean_token_accuracy": 0.9095374941825867, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5627906976744186, | |
| "grad_norm": 2.01922345161438, | |
| "learning_rate": 5.390136562446482e-06, | |
| "loss": 0.2254, | |
| "mean_token_accuracy": 0.9192219972610474, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5674418604651162, | |
| "grad_norm": 2.3800745010375977, | |
| "learning_rate": 5.316926614470063e-06, | |
| "loss": 0.304, | |
| "mean_token_accuracy": 0.8944166302680969, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5720930232558139, | |
| "grad_norm": 2.6100881099700928, | |
| "learning_rate": 5.2437651730843165e-06, | |
| "loss": 0.3353, | |
| "mean_token_accuracy": 0.8797582387924194, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5767441860465117, | |
| "grad_norm": 2.5042288303375244, | |
| "learning_rate": 5.170671622931527e-06, | |
| "loss": 0.3095, | |
| "mean_token_accuracy": 0.8931896090507507, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 2.073580026626587, | |
| "learning_rate": 5.097665330665714e-06, | |
| "loss": 0.2368, | |
| "mean_token_accuracy": 0.9156667590141296, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.586046511627907, | |
| "grad_norm": 2.621702194213867, | |
| "learning_rate": 5.024765639821305e-06, | |
| "loss": 0.3188, | |
| "mean_token_accuracy": 0.8938697576522827, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5906976744186047, | |
| "grad_norm": 2.060399055480957, | |
| "learning_rate": 4.951991865687923e-06, | |
| "loss": 0.2499, | |
| "mean_token_accuracy": 0.9167211055755615, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5953488372093023, | |
| "grad_norm": 2.3782613277435303, | |
| "learning_rate": 4.879363290192667e-06, | |
| "loss": 0.2941, | |
| "mean_token_accuracy": 0.9021573066711426, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.713759422302246, | |
| "learning_rate": 4.806899156791231e-06, | |
| "loss": 0.3563, | |
| "mean_token_accuracy": 0.882408082485199, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.6046511627906976, | |
| "grad_norm": 2.3701155185699463, | |
| "learning_rate": 4.734618665369202e-06, | |
| "loss": 0.2804, | |
| "mean_token_accuracy": 0.8983374834060669, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6093023255813953, | |
| "grad_norm": 2.3168303966522217, | |
| "learning_rate": 4.662540967154934e-06, | |
| "loss": 0.2654, | |
| "mean_token_accuracy": 0.9053771495819092, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.6139534883720931, | |
| "grad_norm": 2.120966672897339, | |
| "learning_rate": 4.5906851596452765e-06, | |
| "loss": 0.2695, | |
| "mean_token_accuracy": 0.9033912420272827, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6186046511627907, | |
| "grad_norm": 2.2889561653137207, | |
| "learning_rate": 4.519070281545571e-06, | |
| "loss": 0.303, | |
| "mean_token_accuracy": 0.8942157626152039, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6232558139534884, | |
| "grad_norm": 2.269672393798828, | |
| "learning_rate": 4.447715307725197e-06, | |
| "loss": 0.3081, | |
| "mean_token_accuracy": 0.898201584815979, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.627906976744186, | |
| "grad_norm": 2.303313970565796, | |
| "learning_rate": 4.376639144190061e-06, | |
| "loss": 0.2994, | |
| "mean_token_accuracy": 0.8974989652633667, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6325581395348837, | |
| "grad_norm": 2.50627064704895, | |
| "learning_rate": 4.305860623073304e-06, | |
| "loss": 0.2958, | |
| "mean_token_accuracy": 0.9008192420005798, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6372093023255814, | |
| "grad_norm": 2.137214183807373, | |
| "learning_rate": 4.2353984976456e-06, | |
| "loss": 0.2784, | |
| "mean_token_accuracy": 0.9044293165206909, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.641860465116279, | |
| "grad_norm": 2.163482427597046, | |
| "learning_rate": 4.1652714373463435e-06, | |
| "loss": 0.2866, | |
| "mean_token_accuracy": 0.9003401398658752, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6465116279069767, | |
| "grad_norm": 2.2267966270446777, | |
| "learning_rate": 4.095498022837051e-06, | |
| "loss": 0.2717, | |
| "mean_token_accuracy": 0.9080227613449097, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6511627906976745, | |
| "grad_norm": 2.3267011642456055, | |
| "learning_rate": 4.026096741078281e-06, | |
| "loss": 0.311, | |
| "mean_token_accuracy": 0.8933864831924438, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6558139534883721, | |
| "grad_norm": 2.3001527786254883, | |
| "learning_rate": 3.957085980431382e-06, | |
| "loss": 0.3041, | |
| "mean_token_accuracy": 0.8946247100830078, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6604651162790698, | |
| "grad_norm": 2.1713979244232178, | |
| "learning_rate": 3.888484025786364e-06, | |
| "loss": 0.2773, | |
| "mean_token_accuracy": 0.9039127230644226, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6651162790697674, | |
| "grad_norm": 2.095184564590454, | |
| "learning_rate": 3.820309053717195e-06, | |
| "loss": 0.2637, | |
| "mean_token_accuracy": 0.9096311926841736, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6697674418604651, | |
| "grad_norm": 2.4033849239349365, | |
| "learning_rate": 3.75257912766578e-06, | |
| "loss": 0.3494, | |
| "mean_token_accuracy": 0.883319079875946, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6744186046511628, | |
| "grad_norm": 2.389072895050049, | |
| "learning_rate": 3.6853121931559334e-06, | |
| "loss": 0.3182, | |
| "mean_token_accuracy": 0.8909416794776917, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6790697674418604, | |
| "grad_norm": 2.227679491043091, | |
| "learning_rate": 3.618526073038574e-06, | |
| "loss": 0.3339, | |
| "mean_token_accuracy": 0.8817432522773743, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6837209302325581, | |
| "grad_norm": 2.333980083465576, | |
| "learning_rate": 3.552238462769446e-06, | |
| "loss": 0.2787, | |
| "mean_token_accuracy": 0.8988922238349915, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6883720930232559, | |
| "grad_norm": 2.4504194259643555, | |
| "learning_rate": 3.4864669257205745e-06, | |
| "loss": 0.2696, | |
| "mean_token_accuracy": 0.9069134593009949, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6930232558139535, | |
| "grad_norm": 2.3140194416046143, | |
| "learning_rate": 3.4212288885267246e-06, | |
| "loss": 0.3142, | |
| "mean_token_accuracy": 0.8938280344009399, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 2.4520225524902344, | |
| "learning_rate": 3.3565416364681016e-06, | |
| "loss": 0.2822, | |
| "mean_token_accuracy": 0.8983594179153442, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7023255813953488, | |
| "grad_norm": 2.075413942337036, | |
| "learning_rate": 3.2924223088904816e-06, | |
| "loss": 0.2727, | |
| "mean_token_accuracy": 0.905676543712616, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.7069767441860465, | |
| "grad_norm": 2.512186050415039, | |
| "learning_rate": 3.228887894664029e-06, | |
| "loss": 0.3308, | |
| "mean_token_accuracy": 0.8881916999816895, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.7116279069767442, | |
| "grad_norm": 2.395528793334961, | |
| "learning_rate": 3.1659552276819693e-06, | |
| "loss": 0.307, | |
| "mean_token_accuracy": 0.8931879997253418, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.7162790697674418, | |
| "grad_norm": 2.2086777687072754, | |
| "learning_rate": 3.1036409824003324e-06, | |
| "loss": 0.2788, | |
| "mean_token_accuracy": 0.9035131931304932, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7209302325581395, | |
| "grad_norm": 2.0497255325317383, | |
| "learning_rate": 3.0419616694199327e-06, | |
| "loss": 0.2589, | |
| "mean_token_accuracy": 0.9101083874702454, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7255813953488373, | |
| "grad_norm": 2.1646888256073, | |
| "learning_rate": 2.98093363111178e-06, | |
| "loss": 0.2364, | |
| "mean_token_accuracy": 0.9164927005767822, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7302325581395349, | |
| "grad_norm": 2.518139123916626, | |
| "learning_rate": 2.92057303728704e-06, | |
| "loss": 0.2931, | |
| "mean_token_accuracy": 0.8988871574401855, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7348837209302326, | |
| "grad_norm": 2.2062928676605225, | |
| "learning_rate": 2.860895880912735e-06, | |
| "loss": 0.2791, | |
| "mean_token_accuracy": 0.9068917632102966, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.7395348837209302, | |
| "grad_norm": 2.2724952697753906, | |
| "learning_rate": 2.801917973874294e-06, | |
| "loss": 0.2977, | |
| "mean_token_accuracy": 0.8921583890914917, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 2.3431556224823, | |
| "learning_rate": 2.7436549427860766e-06, | |
| "loss": 0.3161, | |
| "mean_token_accuracy": 0.890896201133728, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7488372093023256, | |
| "grad_norm": 2.049577236175537, | |
| "learning_rate": 2.6861222248509926e-06, | |
| "loss": 0.2439, | |
| "mean_token_accuracy": 0.9146341681480408, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7534883720930232, | |
| "grad_norm": 2.081054449081421, | |
| "learning_rate": 2.6293350637703123e-06, | |
| "loss": 0.275, | |
| "mean_token_accuracy": 0.9116692543029785, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7581395348837209, | |
| "grad_norm": 2.4126036167144775, | |
| "learning_rate": 2.5733085057047325e-06, | |
| "loss": 0.2845, | |
| "mean_token_accuracy": 0.9033816456794739, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7627906976744186, | |
| "grad_norm": 2.153229236602783, | |
| "learning_rate": 2.518057395287792e-06, | |
| "loss": 0.2954, | |
| "mean_token_accuracy": 0.8962974548339844, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7674418604651163, | |
| "grad_norm": 2.3502793312072754, | |
| "learning_rate": 2.463596371692681e-06, | |
| "loss": 0.2943, | |
| "mean_token_accuracy": 0.8968009948730469, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.772093023255814, | |
| "grad_norm": 2.0880775451660156, | |
| "learning_rate": 2.409939864753487e-06, | |
| "loss": 0.2911, | |
| "mean_token_accuracy": 0.8983282446861267, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7767441860465116, | |
| "grad_norm": 2.1596920490264893, | |
| "learning_rate": 2.3571020911419067e-06, | |
| "loss": 0.2791, | |
| "mean_token_accuracy": 0.9082539677619934, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7813953488372093, | |
| "grad_norm": 2.390465021133423, | |
| "learning_rate": 2.3050970506004463e-06, | |
| "loss": 0.3074, | |
| "mean_token_accuracy": 0.8939219117164612, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.786046511627907, | |
| "grad_norm": 2.372555732727051, | |
| "learning_rate": 2.2539385222330797e-06, | |
| "loss": 0.2506, | |
| "mean_token_accuracy": 0.9121189117431641, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7906976744186046, | |
| "grad_norm": 2.2378170490264893, | |
| "learning_rate": 2.203640060854387e-06, | |
| "loss": 0.2622, | |
| "mean_token_accuracy": 0.9098626971244812, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7953488372093023, | |
| "grad_norm": 2.170590877532959, | |
| "learning_rate": 2.1542149933981014e-06, | |
| "loss": 0.2962, | |
| "mean_token_accuracy": 0.8975265026092529, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.124481201171875, | |
| "learning_rate": 2.10567641538605e-06, | |
| "loss": 0.2718, | |
| "mean_token_accuracy": 0.9119693636894226, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.8046511627906977, | |
| "grad_norm": 2.1050360202789307, | |
| "learning_rate": 2.058037187458398e-06, | |
| "loss": 0.2849, | |
| "mean_token_accuracy": 0.9058271646499634, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.8093023255813954, | |
| "grad_norm": 2.3637399673461914, | |
| "learning_rate": 2.011309931966136e-06, | |
| "loss": 0.2788, | |
| "mean_token_accuracy": 0.9048888683319092, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 2.147559404373169, | |
| "learning_rate": 1.965507029626695e-06, | |
| "loss": 0.2868, | |
| "mean_token_accuracy": 0.8882931470870972, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8186046511627907, | |
| "grad_norm": 2.1714463233947754, | |
| "learning_rate": 1.920640616243589e-06, | |
| "loss": 0.2567, | |
| "mean_token_accuracy": 0.9111915826797485, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8232558139534883, | |
| "grad_norm": 2.416949987411499, | |
| "learning_rate": 1.8767225794909484e-06, | |
| "loss": 0.3109, | |
| "mean_token_accuracy": 0.8934901356697083, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.827906976744186, | |
| "grad_norm": 2.1006410121917725, | |
| "learning_rate": 1.8337645557637929e-06, | |
| "loss": 0.2695, | |
| "mean_token_accuracy": 0.9039152264595032, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8325581395348837, | |
| "grad_norm": 2.0987040996551514, | |
| "learning_rate": 1.7917779270948887e-06, | |
| "loss": 0.2866, | |
| "mean_token_accuracy": 0.9032930731773376, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "grad_norm": 2.2629261016845703, | |
| "learning_rate": 1.7507738181390027e-06, | |
| "loss": 0.2748, | |
| "mean_token_accuracy": 0.9031832218170166, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8418604651162791, | |
| "grad_norm": 2.3030483722686768, | |
| "learning_rate": 1.7107630932253383e-06, | |
| "loss": 0.279, | |
| "mean_token_accuracy": 0.9027203917503357, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.8465116279069768, | |
| "grad_norm": 2.2115092277526855, | |
| "learning_rate": 1.6717563534789594e-06, | |
| "loss": 0.286, | |
| "mean_token_accuracy": 0.9047191739082336, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8511627906976744, | |
| "grad_norm": 2.2246625423431396, | |
| "learning_rate": 1.6337639340119476e-06, | |
| "loss": 0.2909, | |
| "mean_token_accuracy": 0.8974208831787109, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8558139534883721, | |
| "grad_norm": 2.3031420707702637, | |
| "learning_rate": 1.596795901185037e-06, | |
| "loss": 0.2975, | |
| "mean_token_accuracy": 0.8968049883842468, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8604651162790697, | |
| "grad_norm": 1.9780099391937256, | |
| "learning_rate": 1.5608620499404628e-06, | |
| "loss": 0.2682, | |
| "mean_token_accuracy": 0.9050772786140442, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8651162790697674, | |
| "grad_norm": 2.2406816482543945, | |
| "learning_rate": 1.5259719012067249e-06, | |
| "loss": 0.2987, | |
| "mean_token_accuracy": 0.897251307964325, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8697674418604651, | |
| "grad_norm": 2.239496946334839, | |
| "learning_rate": 1.4921346993759453e-06, | |
| "loss": 0.2618, | |
| "mean_token_accuracy": 0.9043693542480469, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8744186046511628, | |
| "grad_norm": 2.127561569213867, | |
| "learning_rate": 1.459359409854505e-06, | |
| "loss": 0.2789, | |
| "mean_token_accuracy": 0.9073178768157959, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8790697674418605, | |
| "grad_norm": 2.1613924503326416, | |
| "learning_rate": 1.4276547166875946e-06, | |
| "loss": 0.2566, | |
| "mean_token_accuracy": 0.9102585315704346, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8837209302325582, | |
| "grad_norm": 2.329148530960083, | |
| "learning_rate": 1.397029020258313e-06, | |
| "loss": 0.2764, | |
| "mean_token_accuracy": 0.8985316157341003, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8883720930232558, | |
| "grad_norm": 2.314202070236206, | |
| "learning_rate": 1.367490435061928e-06, | |
| "loss": 0.3225, | |
| "mean_token_accuracy": 0.887252688407898, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8930232558139535, | |
| "grad_norm": 2.129060745239258, | |
| "learning_rate": 1.3390467875558855e-06, | |
| "loss": 0.2419, | |
| "mean_token_accuracy": 0.9144599437713623, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8976744186046511, | |
| "grad_norm": 2.1066842079162598, | |
| "learning_rate": 1.3117056140861317e-06, | |
| "loss": 0.2814, | |
| "mean_token_accuracy": 0.9042702913284302, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.9023255813953488, | |
| "grad_norm": 2.0804882049560547, | |
| "learning_rate": 1.285474158890304e-06, | |
| "loss": 0.2551, | |
| "mean_token_accuracy": 0.9151648879051208, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.9069767441860465, | |
| "grad_norm": 2.031214475631714, | |
| "learning_rate": 1.2603593721783219e-06, | |
| "loss": 0.2599, | |
| "mean_token_accuracy": 0.9122833609580994, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9116279069767442, | |
| "grad_norm": 2.1141772270202637, | |
| "learning_rate": 1.2363679082908766e-06, | |
| "loss": 0.2904, | |
| "mean_token_accuracy": 0.8994675874710083, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.9162790697674419, | |
| "grad_norm": 2.212240695953369, | |
| "learning_rate": 1.2135061239363161e-06, | |
| "loss": 0.25, | |
| "mean_token_accuracy": 0.9143472909927368, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.9209302325581395, | |
| "grad_norm": 2.216949701309204, | |
| "learning_rate": 1.1917800765063954e-06, | |
| "loss": 0.2607, | |
| "mean_token_accuracy": 0.907805323600769, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9255813953488372, | |
| "grad_norm": 2.397641897201538, | |
| "learning_rate": 1.1711955224713209e-06, | |
| "loss": 0.2875, | |
| "mean_token_accuracy": 0.8999999761581421, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 2.1358089447021484, | |
| "learning_rate": 1.1517579158545386e-06, | |
| "loss": 0.2614, | |
| "mean_token_accuracy": 0.9109670519828796, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9348837209302325, | |
| "grad_norm": 2.3452868461608887, | |
| "learning_rate": 1.1334724067876463e-06, | |
| "loss": 0.2916, | |
| "mean_token_accuracy": 0.9004044532775879, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.9395348837209302, | |
| "grad_norm": 2.092285633087158, | |
| "learning_rate": 1.1163438401458358e-06, | |
| "loss": 0.2579, | |
| "mean_token_accuracy": 0.9101744890213013, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.9441860465116279, | |
| "grad_norm": 2.291351556777954, | |
| "learning_rate": 1.1003767542642021e-06, | |
| "loss": 0.2757, | |
| "mean_token_accuracy": 0.9074675440788269, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.9488372093023256, | |
| "grad_norm": 2.112213134765625, | |
| "learning_rate": 1.0855753797352868e-06, | |
| "loss": 0.2423, | |
| "mean_token_accuracy": 0.9122452139854431, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.9534883720930233, | |
| "grad_norm": 2.0437917709350586, | |
| "learning_rate": 1.0719436382881466e-06, | |
| "loss": 0.2536, | |
| "mean_token_accuracy": 0.9097141027450562, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.958139534883721, | |
| "grad_norm": 2.1376430988311768, | |
| "learning_rate": 1.0594851417492665e-06, | |
| "loss": 0.2731, | |
| "mean_token_accuracy": 0.9037346839904785, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.9627906976744186, | |
| "grad_norm": 2.3502485752105713, | |
| "learning_rate": 1.0482031910855804e-06, | |
| "loss": 0.2933, | |
| "mean_token_accuracy": 0.8957337141036987, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.9674418604651163, | |
| "grad_norm": 2.2085719108581543, | |
| "learning_rate": 1.0381007755298547e-06, | |
| "loss": 0.2683, | |
| "mean_token_accuracy": 0.9104006290435791, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.9720930232558139, | |
| "grad_norm": 2.1255626678466797, | |
| "learning_rate": 1.029180571788672e-06, | |
| "loss": 0.2489, | |
| "mean_token_accuracy": 0.9149152636528015, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9767441860465116, | |
| "grad_norm": 1.9947309494018555, | |
| "learning_rate": 1.021444943333218e-06, | |
| "loss": 0.2553, | |
| "mean_token_accuracy": 0.9112606048583984, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9813953488372092, | |
| "grad_norm": 2.163604259490967, | |
| "learning_rate": 1.0148959397730637e-06, | |
| "loss": 0.2527, | |
| "mean_token_accuracy": 0.9116041660308838, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.986046511627907, | |
| "grad_norm": 2.048002243041992, | |
| "learning_rate": 1.0095352963131057e-06, | |
| "loss": 0.277, | |
| "mean_token_accuracy": 0.9047472476959229, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.9906976744186047, | |
| "grad_norm": 2.163034200668335, | |
| "learning_rate": 1.0053644332938118e-06, | |
| "loss": 0.2457, | |
| "mean_token_accuracy": 0.9106945991516113, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.9953488372093023, | |
| "grad_norm": 2.1395816802978516, | |
| "learning_rate": 1.0023844558148912e-06, | |
| "loss": 0.2891, | |
| "mean_token_accuracy": 0.901391327381134, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.9503026008605957, | |
| "learning_rate": 1.0005961534424925e-06, | |
| "loss": 0.2207, | |
| "mean_token_accuracy": 0.9134988188743591, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 215, | |
| "total_flos": 2.0144468407196058e+17, | |
| "train_loss": 0.32299984568773316, | |
| "train_runtime": 801.4765, | |
| "train_samples_per_second": 8.548, | |
| "train_steps_per_second": 0.268 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 215, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0144468407196058e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |