| { |
| "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": 19.566913604736328, |
| "learning_rate": 0.0, |
| "loss": 0.842, |
| "mean_token_accuracy": 0.8234314918518066, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.009302325581395349, |
| "grad_norm": 21.503646850585938, |
| "learning_rate": 4.5454545454545457e-07, |
| "loss": 0.8773, |
| "mean_token_accuracy": 0.8220880627632141, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.013953488372093023, |
| "grad_norm": 19.072912216186523, |
| "learning_rate": 9.090909090909091e-07, |
| "loss": 0.8522, |
| "mean_token_accuracy": 0.832254946231842, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.018604651162790697, |
| "grad_norm": 18.07330322265625, |
| "learning_rate": 1.3636363636363636e-06, |
| "loss": 0.8166, |
| "mean_token_accuracy": 0.8297423720359802, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.023255813953488372, |
| "grad_norm": 21.246156692504883, |
| "learning_rate": 1.8181818181818183e-06, |
| "loss": 0.9312, |
| "mean_token_accuracy": 0.8097259998321533, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.027906976744186046, |
| "grad_norm": 18.991504669189453, |
| "learning_rate": 2.2727272727272728e-06, |
| "loss": 0.7816, |
| "mean_token_accuracy": 0.8285066485404968, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.03255813953488372, |
| "grad_norm": 16.567394256591797, |
| "learning_rate": 2.7272727272727272e-06, |
| "loss": 0.8123, |
| "mean_token_accuracy": 0.8268486261367798, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.037209302325581395, |
| "grad_norm": 10.308907508850098, |
| "learning_rate": 3.181818181818182e-06, |
| "loss": 0.6385, |
| "mean_token_accuracy": 0.8507297039031982, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.04186046511627907, |
| "grad_norm": 8.591865539550781, |
| "learning_rate": 3.6363636363636366e-06, |
| "loss": 0.5651, |
| "mean_token_accuracy": 0.863410234451294, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "grad_norm": 9.019761085510254, |
| "learning_rate": 4.0909090909090915e-06, |
| "loss": 0.4933, |
| "mean_token_accuracy": 0.8713976144790649, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05116279069767442, |
| "grad_norm": 9.10396671295166, |
| "learning_rate": 4.5454545454545455e-06, |
| "loss": 0.4211, |
| "mean_token_accuracy": 0.8915254473686218, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.05581395348837209, |
| "grad_norm": 7.293844223022461, |
| "learning_rate": 5e-06, |
| "loss": 0.4411, |
| "mean_token_accuracy": 0.8812285661697388, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.06046511627906977, |
| "grad_norm": 4.323971271514893, |
| "learning_rate": 5.4545454545454545e-06, |
| "loss": 0.4205, |
| "mean_token_accuracy": 0.8759526610374451, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.06511627906976744, |
| "grad_norm": 5.9293413162231445, |
| "learning_rate": 5.90909090909091e-06, |
| "loss": 0.364, |
| "mean_token_accuracy": 0.8886061906814575, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "grad_norm": 3.369750738143921, |
| "learning_rate": 6.363636363636364e-06, |
| "loss": 0.3435, |
| "mean_token_accuracy": 0.8966382145881653, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07441860465116279, |
| "grad_norm": 3.6587915420532227, |
| "learning_rate": 6.818181818181818e-06, |
| "loss": 0.3801, |
| "mean_token_accuracy": 0.8860718607902527, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.07906976744186046, |
| "grad_norm": 3.0630006790161133, |
| "learning_rate": 7.272727272727273e-06, |
| "loss": 0.333, |
| "mean_token_accuracy": 0.9021540880203247, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.08372093023255814, |
| "grad_norm": 3.0884928703308105, |
| "learning_rate": 7.727272727272727e-06, |
| "loss": 0.3774, |
| "mean_token_accuracy": 0.8831896185874939, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.08837209302325581, |
| "grad_norm": 3.343445301055908, |
| "learning_rate": 8.181818181818183e-06, |
| "loss": 0.3834, |
| "mean_token_accuracy": 0.884019136428833, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "grad_norm": 2.862471580505371, |
| "learning_rate": 8.636363636363637e-06, |
| "loss": 0.3523, |
| "mean_token_accuracy": 0.8919129371643066, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09767441860465116, |
| "grad_norm": 3.1519503593444824, |
| "learning_rate": 9.090909090909091e-06, |
| "loss": 0.3994, |
| "mean_token_accuracy": 0.8742711544036865, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.10232558139534884, |
| "grad_norm": 3.08125376701355, |
| "learning_rate": 9.545454545454547e-06, |
| "loss": 0.3518, |
| "mean_token_accuracy": 0.8841822147369385, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.10697674418604651, |
| "grad_norm": 3.0018293857574463, |
| "learning_rate": 1e-05, |
| "loss": 0.345, |
| "mean_token_accuracy": 0.8950249552726746, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.11162790697674418, |
| "grad_norm": 3.267643451690674, |
| "learning_rate": 9.999403846557509e-06, |
| "loss": 0.3704, |
| "mean_token_accuracy": 0.8792986273765564, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.11627906976744186, |
| "grad_norm": 3.051391839981079, |
| "learning_rate": 9.99761554418511e-06, |
| "loss": 0.3331, |
| "mean_token_accuracy": 0.896356999874115, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12093023255813953, |
| "grad_norm": 3.030799627304077, |
| "learning_rate": 9.99463556670619e-06, |
| "loss": 0.3339, |
| "mean_token_accuracy": 0.9024479985237122, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.12558139534883722, |
| "grad_norm": 3.1301109790802, |
| "learning_rate": 9.990464703686895e-06, |
| "loss": 0.3652, |
| "mean_token_accuracy": 0.8962038159370422, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.13023255813953488, |
| "grad_norm": 3.1041147708892822, |
| "learning_rate": 9.985104060226937e-06, |
| "loss": 0.3538, |
| "mean_token_accuracy": 0.8938086032867432, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.13488372093023257, |
| "grad_norm": 3.011711835861206, |
| "learning_rate": 9.978555056666784e-06, |
| "loss": 0.3763, |
| "mean_token_accuracy": 0.878600537776947, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.13953488372093023, |
| "grad_norm": 3.104379653930664, |
| "learning_rate": 9.97081942821133e-06, |
| "loss": 0.3706, |
| "mean_token_accuracy": 0.8877567648887634, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14418604651162792, |
| "grad_norm": 3.3601248264312744, |
| "learning_rate": 9.961899224470146e-06, |
| "loss": 0.3956, |
| "mean_token_accuracy": 0.8821022510528564, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.14883720930232558, |
| "grad_norm": 3.0410044193267822, |
| "learning_rate": 9.95179680891442e-06, |
| "loss": 0.318, |
| "mean_token_accuracy": 0.9060280323028564, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.15348837209302327, |
| "grad_norm": 3.7731399536132812, |
| "learning_rate": 9.940514858250736e-06, |
| "loss": 0.3565, |
| "mean_token_accuracy": 0.8926541209220886, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.15813953488372093, |
| "grad_norm": 2.947474241256714, |
| "learning_rate": 9.928056361711854e-06, |
| "loss": 0.3035, |
| "mean_token_accuracy": 0.9058524370193481, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.16279069767441862, |
| "grad_norm": 3.0079967975616455, |
| "learning_rate": 9.914424620264714e-06, |
| "loss": 0.3581, |
| "mean_token_accuracy": 0.8900263905525208, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.16744186046511628, |
| "grad_norm": 3.0129306316375732, |
| "learning_rate": 9.899623245735798e-06, |
| "loss": 0.3283, |
| "mean_token_accuracy": 0.8980950713157654, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.17209302325581396, |
| "grad_norm": 3.025678873062134, |
| "learning_rate": 9.883656159854166e-06, |
| "loss": 0.3179, |
| "mean_token_accuracy": 0.9024977087974548, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.17674418604651163, |
| "grad_norm": 3.019639253616333, |
| "learning_rate": 9.866527593212355e-06, |
| "loss": 0.3314, |
| "mean_token_accuracy": 0.899016261100769, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.1813953488372093, |
| "grad_norm": 2.9794199466705322, |
| "learning_rate": 9.848242084145462e-06, |
| "loss": 0.3199, |
| "mean_token_accuracy": 0.9022731184959412, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.18604651162790697, |
| "grad_norm": 2.8634836673736572, |
| "learning_rate": 9.82880447752868e-06, |
| "loss": 0.3377, |
| "mean_token_accuracy": 0.8929729461669922, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.19069767441860466, |
| "grad_norm": 3.023061990737915, |
| "learning_rate": 9.808219923493606e-06, |
| "loss": 0.3331, |
| "mean_token_accuracy": 0.8968125581741333, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.19534883720930232, |
| "grad_norm": 3.201726198196411, |
| "learning_rate": 9.786493876063685e-06, |
| "loss": 0.3291, |
| "mean_token_accuracy": 0.8950858116149902, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 3.0741653442382812, |
| "learning_rate": 9.763632091709125e-06, |
| "loss": 0.31, |
| "mean_token_accuracy": 0.8963869214057922, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.20465116279069767, |
| "grad_norm": 2.884732723236084, |
| "learning_rate": 9.739640627821678e-06, |
| "loss": 0.3381, |
| "mean_token_accuracy": 0.8979052901268005, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.20930232558139536, |
| "grad_norm": 3.245725631713867, |
| "learning_rate": 9.714525841109697e-06, |
| "loss": 0.2951, |
| "mean_token_accuracy": 0.9035796523094177, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.21395348837209302, |
| "grad_norm": 3.057401180267334, |
| "learning_rate": 9.68829438591387e-06, |
| "loss": 0.3034, |
| "mean_token_accuracy": 0.9002149701118469, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2186046511627907, |
| "grad_norm": 3.0023374557495117, |
| "learning_rate": 9.660953212444116e-06, |
| "loss": 0.3138, |
| "mean_token_accuracy": 0.8987898826599121, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.22325581395348837, |
| "grad_norm": 2.846851110458374, |
| "learning_rate": 9.632509564938073e-06, |
| "loss": 0.3213, |
| "mean_token_accuracy": 0.8954131603240967, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.22790697674418606, |
| "grad_norm": 2.9974007606506348, |
| "learning_rate": 9.60297097974169e-06, |
| "loss": 0.3149, |
| "mean_token_accuracy": 0.8978151082992554, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.23255813953488372, |
| "grad_norm": 2.860105037689209, |
| "learning_rate": 9.572345283312407e-06, |
| "loss": 0.3152, |
| "mean_token_accuracy": 0.8984004259109497, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2372093023255814, |
| "grad_norm": 3.178861141204834, |
| "learning_rate": 9.540640590145496e-06, |
| "loss": 0.3362, |
| "mean_token_accuracy": 0.8821947574615479, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.24186046511627907, |
| "grad_norm": 2.8864493370056152, |
| "learning_rate": 9.507865300624057e-06, |
| "loss": 0.338, |
| "mean_token_accuracy": 0.8844265937805176, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.24651162790697675, |
| "grad_norm": 2.9779324531555176, |
| "learning_rate": 9.474028098793277e-06, |
| "loss": 0.3133, |
| "mean_token_accuracy": 0.8958209753036499, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.25116279069767444, |
| "grad_norm": 2.81357479095459, |
| "learning_rate": 9.439137950059539e-06, |
| "loss": 0.3293, |
| "mean_token_accuracy": 0.8908188343048096, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.2558139534883721, |
| "grad_norm": 2.7432124614715576, |
| "learning_rate": 9.403204098814965e-06, |
| "loss": 0.3289, |
| "mean_token_accuracy": 0.8898541927337646, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.26046511627906976, |
| "grad_norm": 2.78106689453125, |
| "learning_rate": 9.366236065988053e-06, |
| "loss": 0.3222, |
| "mean_token_accuracy": 0.8953770995140076, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.2651162790697674, |
| "grad_norm": 2.4186606407165527, |
| "learning_rate": 9.32824364652104e-06, |
| "loss": 0.2825, |
| "mean_token_accuracy": 0.908851146697998, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.26976744186046514, |
| "grad_norm": 2.4946393966674805, |
| "learning_rate": 9.289236906774663e-06, |
| "loss": 0.3115, |
| "mean_token_accuracy": 0.8956378698348999, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.2744186046511628, |
| "grad_norm": 2.7663369178771973, |
| "learning_rate": 9.249226181861e-06, |
| "loss": 0.2915, |
| "mean_token_accuracy": 0.9062834978103638, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.27906976744186046, |
| "grad_norm": 2.6216726303100586, |
| "learning_rate": 9.208222072905113e-06, |
| "loss": 0.3069, |
| "mean_token_accuracy": 0.8927038908004761, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2837209302325581, |
| "grad_norm": 2.7621278762817383, |
| "learning_rate": 9.166235444236209e-06, |
| "loss": 0.3425, |
| "mean_token_accuracy": 0.8820893168449402, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.28837209302325584, |
| "grad_norm": 2.748720407485962, |
| "learning_rate": 9.123277420509053e-06, |
| "loss": 0.3364, |
| "mean_token_accuracy": 0.8870337605476379, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.2930232558139535, |
| "grad_norm": 2.5530190467834473, |
| "learning_rate": 9.079359383756411e-06, |
| "loss": 0.3133, |
| "mean_token_accuracy": 0.8994490504264832, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.29767441860465116, |
| "grad_norm": 2.48974609375, |
| "learning_rate": 9.034492970373305e-06, |
| "loss": 0.3035, |
| "mean_token_accuracy": 0.8979023098945618, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3023255813953488, |
| "grad_norm": 2.6978116035461426, |
| "learning_rate": 8.988690068033864e-06, |
| "loss": 0.3339, |
| "mean_token_accuracy": 0.8893972635269165, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.30697674418604654, |
| "grad_norm": 2.308871030807495, |
| "learning_rate": 8.941962812541604e-06, |
| "loss": 0.3016, |
| "mean_token_accuracy": 0.8937329649925232, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.3116279069767442, |
| "grad_norm": 2.511657953262329, |
| "learning_rate": 8.894323584613951e-06, |
| "loss": 0.3194, |
| "mean_token_accuracy": 0.889618456363678, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.31627906976744186, |
| "grad_norm": 2.389920949935913, |
| "learning_rate": 8.845785006601898e-06, |
| "loss": 0.281, |
| "mean_token_accuracy": 0.9037378430366516, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.3209302325581395, |
| "grad_norm": 2.5016298294067383, |
| "learning_rate": 8.796359939145614e-06, |
| "loss": 0.3076, |
| "mean_token_accuracy": 0.8938754200935364, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.32558139534883723, |
| "grad_norm": 2.682018518447876, |
| "learning_rate": 8.74606147776692e-06, |
| "loss": 0.3102, |
| "mean_token_accuracy": 0.8926771879196167, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.3302325581395349, |
| "grad_norm": 2.5323574542999268, |
| "learning_rate": 8.694902949399555e-06, |
| "loss": 0.3095, |
| "mean_token_accuracy": 0.8985507488250732, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.33488372093023255, |
| "grad_norm": 2.5909910202026367, |
| "learning_rate": 8.642897908858096e-06, |
| "loss": 0.3112, |
| "mean_token_accuracy": 0.8959133625030518, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.3395348837209302, |
| "grad_norm": 2.635803461074829, |
| "learning_rate": 8.590060135246516e-06, |
| "loss": 0.3358, |
| "mean_token_accuracy": 0.8812984228134155, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.34418604651162793, |
| "grad_norm": 2.2963192462921143, |
| "learning_rate": 8.53640362830732e-06, |
| "loss": 0.2899, |
| "mean_token_accuracy": 0.9005515575408936, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.3488372093023256, |
| "grad_norm": 2.634748935699463, |
| "learning_rate": 8.481942604712209e-06, |
| "loss": 0.3187, |
| "mean_token_accuracy": 0.891135573387146, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.35348837209302325, |
| "grad_norm": 2.4233202934265137, |
| "learning_rate": 8.426691494295269e-06, |
| "loss": 0.2874, |
| "mean_token_accuracy": 0.9031267762184143, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.3581395348837209, |
| "grad_norm": 2.462113618850708, |
| "learning_rate": 8.370664936229688e-06, |
| "loss": 0.314, |
| "mean_token_accuracy": 0.8929266929626465, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.3627906976744186, |
| "grad_norm": 2.456052780151367, |
| "learning_rate": 8.313877775149009e-06, |
| "loss": 0.2742, |
| "mean_token_accuracy": 0.9058647155761719, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.3674418604651163, |
| "grad_norm": 2.792787790298462, |
| "learning_rate": 8.256345057213925e-06, |
| "loss": 0.3157, |
| "mean_token_accuracy": 0.8885141015052795, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "grad_norm": 2.2764811515808105, |
| "learning_rate": 8.198082026125707e-06, |
| "loss": 0.3285, |
| "mean_token_accuracy": 0.8876305222511292, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3767441860465116, |
| "grad_norm": 2.815459966659546, |
| "learning_rate": 8.139104119087265e-06, |
| "loss": 0.2839, |
| "mean_token_accuracy": 0.9014216065406799, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.3813953488372093, |
| "grad_norm": 2.5127663612365723, |
| "learning_rate": 8.07942696271296e-06, |
| "loss": 0.2825, |
| "mean_token_accuracy": 0.9009503126144409, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.386046511627907, |
| "grad_norm": 2.3554956912994385, |
| "learning_rate": 8.019066368888222e-06, |
| "loss": 0.2873, |
| "mean_token_accuracy": 0.902760922908783, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.39069767441860465, |
| "grad_norm": 2.4911487102508545, |
| "learning_rate": 7.958038330580067e-06, |
| "loss": 0.3324, |
| "mean_token_accuracy": 0.883284866809845, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.3953488372093023, |
| "grad_norm": 2.3755667209625244, |
| "learning_rate": 7.89635901759967e-06, |
| "loss": 0.3, |
| "mean_token_accuracy": 0.8920915126800537, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 2.7483432292938232, |
| "learning_rate": 7.834044772318033e-06, |
| "loss": 0.3282, |
| "mean_token_accuracy": 0.8910906910896301, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.4046511627906977, |
| "grad_norm": 2.4823901653289795, |
| "learning_rate": 7.77111210533597e-06, |
| "loss": 0.3, |
| "mean_token_accuracy": 0.8902961015701294, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.40930232558139534, |
| "grad_norm": 2.6033935546875, |
| "learning_rate": 7.707577691109519e-06, |
| "loss": 0.3548, |
| "mean_token_accuracy": 0.880534827709198, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.413953488372093, |
| "grad_norm": 2.27488374710083, |
| "learning_rate": 7.6434583635319e-06, |
| "loss": 0.3022, |
| "mean_token_accuracy": 0.9012537002563477, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.4186046511627907, |
| "grad_norm": 2.287916660308838, |
| "learning_rate": 7.578771111473276e-06, |
| "loss": 0.2578, |
| "mean_token_accuracy": 0.9131473898887634, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4232558139534884, |
| "grad_norm": 2.3548431396484375, |
| "learning_rate": 7.513533074279427e-06, |
| "loss": 0.2677, |
| "mean_token_accuracy": 0.9082207083702087, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.42790697674418604, |
| "grad_norm": 2.484837532043457, |
| "learning_rate": 7.4477615372305545e-06, |
| "loss": 0.3218, |
| "mean_token_accuracy": 0.8943215012550354, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.4325581395348837, |
| "grad_norm": 2.419360637664795, |
| "learning_rate": 7.3814739269614265e-06, |
| "loss": 0.2945, |
| "mean_token_accuracy": 0.9002562165260315, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.4372093023255814, |
| "grad_norm": 2.4345784187316895, |
| "learning_rate": 7.314687806844067e-06, |
| "loss": 0.3091, |
| "mean_token_accuracy": 0.8968407511711121, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.4418604651162791, |
| "grad_norm": 2.479210376739502, |
| "learning_rate": 7.247420872334221e-06, |
| "loss": 0.3019, |
| "mean_token_accuracy": 0.8969621658325195, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.44651162790697674, |
| "grad_norm": 2.2260143756866455, |
| "learning_rate": 7.179690946282808e-06, |
| "loss": 0.2833, |
| "mean_token_accuracy": 0.9025951027870178, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.4511627906976744, |
| "grad_norm": 2.2926838397979736, |
| "learning_rate": 7.111515974213639e-06, |
| "loss": 0.2491, |
| "mean_token_accuracy": 0.9109234809875488, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.4558139534883721, |
| "grad_norm": 2.386190414428711, |
| "learning_rate": 7.042914019568621e-06, |
| "loss": 0.3028, |
| "mean_token_accuracy": 0.8939149379730225, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.4604651162790698, |
| "grad_norm": 2.2225522994995117, |
| "learning_rate": 6.973903258921719e-06, |
| "loss": 0.2564, |
| "mean_token_accuracy": 0.909423291683197, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.46511627906976744, |
| "grad_norm": 2.3535642623901367, |
| "learning_rate": 6.904501977162949e-06, |
| "loss": 0.3274, |
| "mean_token_accuracy": 0.88499915599823, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4697674418604651, |
| "grad_norm": 2.362877607345581, |
| "learning_rate": 6.834728562653659e-06, |
| "loss": 0.309, |
| "mean_token_accuracy": 0.8906528353691101, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.4744186046511628, |
| "grad_norm": 2.4089605808258057, |
| "learning_rate": 6.764601502354403e-06, |
| "loss": 0.3059, |
| "mean_token_accuracy": 0.8971619009971619, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.4790697674418605, |
| "grad_norm": 2.2496674060821533, |
| "learning_rate": 6.6941393769266995e-06, |
| "loss": 0.2987, |
| "mean_token_accuracy": 0.8985577821731567, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.48372093023255813, |
| "grad_norm": 2.0976436138153076, |
| "learning_rate": 6.6233608558099405e-06, |
| "loss": 0.2774, |
| "mean_token_accuracy": 0.9051709771156311, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.4883720930232558, |
| "grad_norm": 2.2868094444274902, |
| "learning_rate": 6.552284692274803e-06, |
| "loss": 0.3088, |
| "mean_token_accuracy": 0.8942136764526367, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.4930232558139535, |
| "grad_norm": 2.3689169883728027, |
| "learning_rate": 6.48092971845443e-06, |
| "loss": 0.2793, |
| "mean_token_accuracy": 0.9030190706253052, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.49767441860465117, |
| "grad_norm": 2.390408515930176, |
| "learning_rate": 6.409314840354724e-06, |
| "loss": 0.3383, |
| "mean_token_accuracy": 0.8868411779403687, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.5023255813953489, |
| "grad_norm": 2.522303342819214, |
| "learning_rate": 6.337459032845068e-06, |
| "loss": 0.3146, |
| "mean_token_accuracy": 0.8873773217201233, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.5069767441860465, |
| "grad_norm": 2.418745279312134, |
| "learning_rate": 6.2653813346308e-06, |
| "loss": 0.2738, |
| "mean_token_accuracy": 0.9050701260566711, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.5116279069767442, |
| "grad_norm": 2.2483389377593994, |
| "learning_rate": 6.193100843208772e-06, |
| "loss": 0.282, |
| "mean_token_accuracy": 0.8973640203475952, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5162790697674419, |
| "grad_norm": 2.3183794021606445, |
| "learning_rate": 6.120636709807334e-06, |
| "loss": 0.3109, |
| "mean_token_accuracy": 0.8886767029762268, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.5209302325581395, |
| "grad_norm": 2.3985159397125244, |
| "learning_rate": 6.048008134312078e-06, |
| "loss": 0.2891, |
| "mean_token_accuracy": 0.9019830226898193, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.5255813953488372, |
| "grad_norm": 2.401186943054199, |
| "learning_rate": 5.975234360178698e-06, |
| "loss": 0.3263, |
| "mean_token_accuracy": 0.8926165103912354, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.5302325581395348, |
| "grad_norm": 2.2257766723632812, |
| "learning_rate": 5.902334669334287e-06, |
| "loss": 0.2991, |
| "mean_token_accuracy": 0.9015018939971924, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.5348837209302325, |
| "grad_norm": 2.4873902797698975, |
| "learning_rate": 5.829328377068476e-06, |
| "loss": 0.2952, |
| "mean_token_accuracy": 0.8938588500022888, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.5395348837209303, |
| "grad_norm": 2.5127971172332764, |
| "learning_rate": 5.756234826915686e-06, |
| "loss": 0.3015, |
| "mean_token_accuracy": 0.8990825414657593, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.5441860465116279, |
| "grad_norm": 2.7055206298828125, |
| "learning_rate": 5.683073385529938e-06, |
| "loss": 0.3148, |
| "mean_token_accuracy": 0.8902867436408997, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.5488372093023256, |
| "grad_norm": 2.184539794921875, |
| "learning_rate": 5.60986343755352e-06, |
| "loss": 0.2628, |
| "mean_token_accuracy": 0.907613217830658, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.5534883720930233, |
| "grad_norm": 2.460629463195801, |
| "learning_rate": 5.536624380480878e-06, |
| "loss": 0.2526, |
| "mean_token_accuracy": 0.9117704629898071, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.5581395348837209, |
| "grad_norm": 2.3159563541412354, |
| "learning_rate": 5.4633756195191235e-06, |
| "loss": 0.261, |
| "mean_token_accuracy": 0.90885990858078, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5627906976744186, |
| "grad_norm": 2.0507678985595703, |
| "learning_rate": 5.390136562446482e-06, |
| "loss": 0.2262, |
| "mean_token_accuracy": 0.9185211062431335, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.5674418604651162, |
| "grad_norm": 2.456918954849243, |
| "learning_rate": 5.316926614470063e-06, |
| "loss": 0.3052, |
| "mean_token_accuracy": 0.8933428525924683, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.5720930232558139, |
| "grad_norm": 2.683582067489624, |
| "learning_rate": 5.2437651730843165e-06, |
| "loss": 0.3406, |
| "mean_token_accuracy": 0.8779610991477966, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.5767441860465117, |
| "grad_norm": 2.5005733966827393, |
| "learning_rate": 5.170671622931527e-06, |
| "loss": 0.3104, |
| "mean_token_accuracy": 0.8913931250572205, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.5813953488372093, |
| "grad_norm": 2.073763370513916, |
| "learning_rate": 5.097665330665714e-06, |
| "loss": 0.2393, |
| "mean_token_accuracy": 0.9153239727020264, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.586046511627907, |
| "grad_norm": 2.638117551803589, |
| "learning_rate": 5.024765639821305e-06, |
| "loss": 0.321, |
| "mean_token_accuracy": 0.8932949900627136, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.5906976744186047, |
| "grad_norm": 2.077889919281006, |
| "learning_rate": 4.951991865687923e-06, |
| "loss": 0.2523, |
| "mean_token_accuracy": 0.916557788848877, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.5953488372093023, |
| "grad_norm": 2.4227733612060547, |
| "learning_rate": 4.879363290192667e-06, |
| "loss": 0.2931, |
| "mean_token_accuracy": 0.9004586338996887, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 2.7623236179351807, |
| "learning_rate": 4.806899156791231e-06, |
| "loss": 0.359, |
| "mean_token_accuracy": 0.8809077143669128, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.6046511627906976, |
| "grad_norm": 2.4066247940063477, |
| "learning_rate": 4.734618665369202e-06, |
| "loss": 0.2844, |
| "mean_token_accuracy": 0.8950888514518738, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6093023255813953, |
| "grad_norm": 2.34375, |
| "learning_rate": 4.662540967154934e-06, |
| "loss": 0.2673, |
| "mean_token_accuracy": 0.9051871299743652, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.6139534883720931, |
| "grad_norm": 2.1489133834838867, |
| "learning_rate": 4.5906851596452765e-06, |
| "loss": 0.2721, |
| "mean_token_accuracy": 0.9027295112609863, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.6186046511627907, |
| "grad_norm": 2.2944834232330322, |
| "learning_rate": 4.519070281545571e-06, |
| "loss": 0.3041, |
| "mean_token_accuracy": 0.8964738845825195, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.6232558139534884, |
| "grad_norm": 2.323543071746826, |
| "learning_rate": 4.447715307725197e-06, |
| "loss": 0.3137, |
| "mean_token_accuracy": 0.8975229263305664, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.627906976744186, |
| "grad_norm": 2.3029696941375732, |
| "learning_rate": 4.376639144190061e-06, |
| "loss": 0.3004, |
| "mean_token_accuracy": 0.8968156576156616, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.6325581395348837, |
| "grad_norm": 2.538562536239624, |
| "learning_rate": 4.305860623073304e-06, |
| "loss": 0.2989, |
| "mean_token_accuracy": 0.8975074291229248, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.6372093023255814, |
| "grad_norm": 2.164029836654663, |
| "learning_rate": 4.2353984976456e-06, |
| "loss": 0.2795, |
| "mean_token_accuracy": 0.9066439270973206, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.641860465116279, |
| "grad_norm": 2.2238547801971436, |
| "learning_rate": 4.1652714373463435e-06, |
| "loss": 0.2878, |
| "mean_token_accuracy": 0.8984693884849548, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.6465116279069767, |
| "grad_norm": 2.2204103469848633, |
| "learning_rate": 4.095498022837051e-06, |
| "loss": 0.2723, |
| "mean_token_accuracy": 0.9076555967330933, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.6511627906976745, |
| "grad_norm": 2.327342987060547, |
| "learning_rate": 4.026096741078281e-06, |
| "loss": 0.3144, |
| "mean_token_accuracy": 0.8956175446510315, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6558139534883721, |
| "grad_norm": 2.408447027206421, |
| "learning_rate": 3.957085980431382e-06, |
| "loss": 0.3109, |
| "mean_token_accuracy": 0.8903638124465942, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.6604651162790698, |
| "grad_norm": 2.17551851272583, |
| "learning_rate": 3.888484025786364e-06, |
| "loss": 0.2808, |
| "mean_token_accuracy": 0.9039127230644226, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.6651162790697674, |
| "grad_norm": 2.148789405822754, |
| "learning_rate": 3.820309053717195e-06, |
| "loss": 0.2644, |
| "mean_token_accuracy": 0.9068344831466675, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.6697674418604651, |
| "grad_norm": 2.4230973720550537, |
| "learning_rate": 3.75257912766578e-06, |
| "loss": 0.3521, |
| "mean_token_accuracy": 0.8838323354721069, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.6744186046511628, |
| "grad_norm": 2.407576560974121, |
| "learning_rate": 3.6853121931559334e-06, |
| "loss": 0.3176, |
| "mean_token_accuracy": 0.8907623291015625, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.6790697674418604, |
| "grad_norm": 2.257375478744507, |
| "learning_rate": 3.618526073038574e-06, |
| "loss": 0.3402, |
| "mean_token_accuracy": 0.877872109413147, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.6837209302325581, |
| "grad_norm": 2.3605127334594727, |
| "learning_rate": 3.552238462769446e-06, |
| "loss": 0.2822, |
| "mean_token_accuracy": 0.898716390132904, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.6883720930232559, |
| "grad_norm": 2.5195729732513428, |
| "learning_rate": 3.4864669257205745e-06, |
| "loss": 0.2726, |
| "mean_token_accuracy": 0.9063690900802612, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.6930232558139535, |
| "grad_norm": 2.344093084335327, |
| "learning_rate": 3.4212288885267246e-06, |
| "loss": 0.3185, |
| "mean_token_accuracy": 0.8916053771972656, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.6976744186046512, |
| "grad_norm": 2.4580070972442627, |
| "learning_rate": 3.3565416364681016e-06, |
| "loss": 0.2861, |
| "mean_token_accuracy": 0.8970394134521484, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7023255813953488, |
| "grad_norm": 2.1077418327331543, |
| "learning_rate": 3.2924223088904816e-06, |
| "loss": 0.2753, |
| "mean_token_accuracy": 0.9032756090164185, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.7069767441860465, |
| "grad_norm": 2.571012258529663, |
| "learning_rate": 3.228887894664029e-06, |
| "loss": 0.3382, |
| "mean_token_accuracy": 0.8874310851097107, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.7116279069767442, |
| "grad_norm": 2.415187358856201, |
| "learning_rate": 3.1659552276819693e-06, |
| "loss": 0.311, |
| "mean_token_accuracy": 0.8911898136138916, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.7162790697674418, |
| "grad_norm": 2.24096941947937, |
| "learning_rate": 3.1036409824003324e-06, |
| "loss": 0.2866, |
| "mean_token_accuracy": 0.9001513123512268, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.7209302325581395, |
| "grad_norm": 2.1161606311798096, |
| "learning_rate": 3.0419616694199327e-06, |
| "loss": 0.2648, |
| "mean_token_accuracy": 0.9077988862991333, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.7255813953488373, |
| "grad_norm": 2.244520425796509, |
| "learning_rate": 2.98093363111178e-06, |
| "loss": 0.2427, |
| "mean_token_accuracy": 0.9150313138961792, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.7302325581395349, |
| "grad_norm": 2.494776725769043, |
| "learning_rate": 2.92057303728704e-06, |
| "loss": 0.2976, |
| "mean_token_accuracy": 0.8998464941978455, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.7348837209302326, |
| "grad_norm": 2.248281717300415, |
| "learning_rate": 2.860895880912735e-06, |
| "loss": 0.2849, |
| "mean_token_accuracy": 0.9054994583129883, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.7395348837209302, |
| "grad_norm": 2.331533432006836, |
| "learning_rate": 2.801917973874294e-06, |
| "loss": 0.3037, |
| "mean_token_accuracy": 0.8930827379226685, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "grad_norm": 2.3448197841644287, |
| "learning_rate": 2.7436549427860766e-06, |
| "loss": 0.3222, |
| "mean_token_accuracy": 0.889302134513855, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7488372093023256, |
| "grad_norm": 2.071540355682373, |
| "learning_rate": 2.6861222248509926e-06, |
| "loss": 0.2476, |
| "mean_token_accuracy": 0.9146341681480408, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.7534883720930232, |
| "grad_norm": 2.1529202461242676, |
| "learning_rate": 2.6293350637703123e-06, |
| "loss": 0.2813, |
| "mean_token_accuracy": 0.9099606871604919, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.7581395348837209, |
| "grad_norm": 2.4522061347961426, |
| "learning_rate": 2.5733085057047325e-06, |
| "loss": 0.2871, |
| "mean_token_accuracy": 0.9062443971633911, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.7627906976744186, |
| "grad_norm": 2.1827683448791504, |
| "learning_rate": 2.518057395287792e-06, |
| "loss": 0.2984, |
| "mean_token_accuracy": 0.8948549628257751, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.7674418604651163, |
| "grad_norm": 2.5053515434265137, |
| "learning_rate": 2.463596371692681e-06, |
| "loss": 0.297, |
| "mean_token_accuracy": 0.8924633860588074, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.772093023255814, |
| "grad_norm": 2.1398110389709473, |
| "learning_rate": 2.409939864753487e-06, |
| "loss": 0.2976, |
| "mean_token_accuracy": 0.8955926895141602, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.7767441860465116, |
| "grad_norm": 2.19425892829895, |
| "learning_rate": 2.3571020911419067e-06, |
| "loss": 0.2816, |
| "mean_token_accuracy": 0.9085714221000671, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.7813953488372093, |
| "grad_norm": 2.4098033905029297, |
| "learning_rate": 2.3050970506004463e-06, |
| "loss": 0.3113, |
| "mean_token_accuracy": 0.8950749635696411, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.786046511627907, |
| "grad_norm": 2.4144301414489746, |
| "learning_rate": 2.2539385222330797e-06, |
| "loss": 0.2541, |
| "mean_token_accuracy": 0.90910804271698, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.7906976744186046, |
| "grad_norm": 2.286418914794922, |
| "learning_rate": 2.203640060854387e-06, |
| "loss": 0.269, |
| "mean_token_accuracy": 0.9078757166862488, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7953488372093023, |
| "grad_norm": 2.281157970428467, |
| "learning_rate": 2.1542149933981014e-06, |
| "loss": 0.3069, |
| "mean_token_accuracy": 0.893151581287384, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 2.220977544784546, |
| "learning_rate": 2.10567641538605e-06, |
| "loss": 0.279, |
| "mean_token_accuracy": 0.9098817110061646, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.8046511627906977, |
| "grad_norm": 2.178304433822632, |
| "learning_rate": 2.058037187458398e-06, |
| "loss": 0.2903, |
| "mean_token_accuracy": 0.9047447443008423, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.8093023255813954, |
| "grad_norm": 2.4263737201690674, |
| "learning_rate": 2.011309931966136e-06, |
| "loss": 0.2844, |
| "mean_token_accuracy": 0.9039999842643738, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.813953488372093, |
| "grad_norm": 2.2288589477539062, |
| "learning_rate": 1.965507029626695e-06, |
| "loss": 0.2977, |
| "mean_token_accuracy": 0.8857610821723938, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.8186046511627907, |
| "grad_norm": 2.2465760707855225, |
| "learning_rate": 1.920640616243589e-06, |
| "loss": 0.2632, |
| "mean_token_accuracy": 0.9077427387237549, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.8232558139534883, |
| "grad_norm": 2.478376626968384, |
| "learning_rate": 1.8767225794909484e-06, |
| "loss": 0.321, |
| "mean_token_accuracy": 0.8919563889503479, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.827906976744186, |
| "grad_norm": 2.138991594314575, |
| "learning_rate": 1.8337645557637929e-06, |
| "loss": 0.2744, |
| "mean_token_accuracy": 0.9032313227653503, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.8325581395348837, |
| "grad_norm": 2.145294189453125, |
| "learning_rate": 1.7917779270948887e-06, |
| "loss": 0.2934, |
| "mean_token_accuracy": 0.8986738324165344, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.8372093023255814, |
| "grad_norm": 2.3890199661254883, |
| "learning_rate": 1.7507738181390027e-06, |
| "loss": 0.2847, |
| "mean_token_accuracy": 0.9007092118263245, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8418604651162791, |
| "grad_norm": 2.3594157695770264, |
| "learning_rate": 1.7107630932253383e-06, |
| "loss": 0.2853, |
| "mean_token_accuracy": 0.8999655842781067, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.8465116279069768, |
| "grad_norm": 2.2847506999969482, |
| "learning_rate": 1.6717563534789594e-06, |
| "loss": 0.2909, |
| "mean_token_accuracy": 0.9014893174171448, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.8511627906976744, |
| "grad_norm": 2.3248329162597656, |
| "learning_rate": 1.6337639340119476e-06, |
| "loss": 0.2996, |
| "mean_token_accuracy": 0.8940504193305969, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.8558139534883721, |
| "grad_norm": 2.390031576156616, |
| "learning_rate": 1.596795901185037e-06, |
| "loss": 0.305, |
| "mean_token_accuracy": 0.8964377641677856, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.8604651162790697, |
| "grad_norm": 2.054699420928955, |
| "learning_rate": 1.5608620499404628e-06, |
| "loss": 0.2769, |
| "mean_token_accuracy": 0.9020813703536987, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.8651162790697674, |
| "grad_norm": 2.3316433429718018, |
| "learning_rate": 1.5259719012067249e-06, |
| "loss": 0.3028, |
| "mean_token_accuracy": 0.8970876932144165, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.8697674418604651, |
| "grad_norm": 2.2691869735717773, |
| "learning_rate": 1.4921346993759453e-06, |
| "loss": 0.27, |
| "mean_token_accuracy": 0.9035449028015137, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.8744186046511628, |
| "grad_norm": 2.1666178703308105, |
| "learning_rate": 1.459359409854505e-06, |
| "loss": 0.2836, |
| "mean_token_accuracy": 0.9079626202583313, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.8790697674418605, |
| "grad_norm": 2.2185068130493164, |
| "learning_rate": 1.4276547166875946e-06, |
| "loss": 0.2652, |
| "mean_token_accuracy": 0.9092705249786377, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.8837209302325582, |
| "grad_norm": 2.47299861907959, |
| "learning_rate": 1.397029020258313e-06, |
| "loss": 0.2879, |
| "mean_token_accuracy": 0.896272599697113, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8883720930232558, |
| "grad_norm": 2.3769164085388184, |
| "learning_rate": 1.367490435061928e-06, |
| "loss": 0.3358, |
| "mean_token_accuracy": 0.8814517259597778, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.8930232558139535, |
| "grad_norm": 2.21427845954895, |
| "learning_rate": 1.3390467875558855e-06, |
| "loss": 0.2465, |
| "mean_token_accuracy": 0.9141114950180054, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.8976744186046511, |
| "grad_norm": 2.2213754653930664, |
| "learning_rate": 1.3117056140861317e-06, |
| "loss": 0.2912, |
| "mean_token_accuracy": 0.9031753540039062, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.9023255813953488, |
| "grad_norm": 2.2283401489257812, |
| "learning_rate": 1.285474158890304e-06, |
| "loss": 0.2645, |
| "mean_token_accuracy": 0.9112547039985657, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.9069767441860465, |
| "grad_norm": 2.1087920665740967, |
| "learning_rate": 1.2603593721783219e-06, |
| "loss": 0.2653, |
| "mean_token_accuracy": 0.9116804599761963, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.9116279069767442, |
| "grad_norm": 2.2635421752929688, |
| "learning_rate": 1.2363679082908766e-06, |
| "loss": 0.2987, |
| "mean_token_accuracy": 0.8961791396141052, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.9162790697674419, |
| "grad_norm": 2.3147056102752686, |
| "learning_rate": 1.2135061239363161e-06, |
| "loss": 0.2587, |
| "mean_token_accuracy": 0.9121925234794617, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.9209302325581395, |
| "grad_norm": 2.262284755706787, |
| "learning_rate": 1.1917800765063954e-06, |
| "loss": 0.2704, |
| "mean_token_accuracy": 0.9092745780944824, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.9255813953488372, |
| "grad_norm": 2.5080342292785645, |
| "learning_rate": 1.1711955224713209e-06, |
| "loss": 0.2932, |
| "mean_token_accuracy": 0.898510217666626, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.9302325581395349, |
| "grad_norm": 2.2359910011291504, |
| "learning_rate": 1.1517579158545386e-06, |
| "loss": 0.2699, |
| "mean_token_accuracy": 0.9084086418151855, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9348837209302325, |
| "grad_norm": 2.4288928508758545, |
| "learning_rate": 1.1334724067876463e-06, |
| "loss": 0.3007, |
| "mean_token_accuracy": 0.8988877534866333, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.9395348837209302, |
| "grad_norm": 2.267275810241699, |
| "learning_rate": 1.1163438401458358e-06, |
| "loss": 0.2668, |
| "mean_token_accuracy": 0.9053376913070679, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.9441860465116279, |
| "grad_norm": 2.3959038257598877, |
| "learning_rate": 1.1003767542642021e-06, |
| "loss": 0.2833, |
| "mean_token_accuracy": 0.9051226377487183, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.9488372093023256, |
| "grad_norm": 2.2642016410827637, |
| "learning_rate": 1.0855753797352868e-06, |
| "loss": 0.2544, |
| "mean_token_accuracy": 0.9085396528244019, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.9534883720930233, |
| "grad_norm": 2.1275274753570557, |
| "learning_rate": 1.0719436382881466e-06, |
| "loss": 0.2614, |
| "mean_token_accuracy": 0.9060357809066772, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.958139534883721, |
| "grad_norm": 2.3473360538482666, |
| "learning_rate": 1.0594851417492665e-06, |
| "loss": 0.2869, |
| "mean_token_accuracy": 0.9008370637893677, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.9627906976744186, |
| "grad_norm": 2.4919135570526123, |
| "learning_rate": 1.0482031910855804e-06, |
| "loss": 0.3038, |
| "mean_token_accuracy": 0.8915042281150818, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.9674418604651163, |
| "grad_norm": 2.309241533279419, |
| "learning_rate": 1.0381007755298547e-06, |
| "loss": 0.2765, |
| "mean_token_accuracy": 0.9052693843841553, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.9720930232558139, |
| "grad_norm": 2.2533209323883057, |
| "learning_rate": 1.029180571788672e-06, |
| "loss": 0.2576, |
| "mean_token_accuracy": 0.9127118587493896, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.9767441860465116, |
| "grad_norm": 2.08575439453125, |
| "learning_rate": 1.021444943333218e-06, |
| "loss": 0.2668, |
| "mean_token_accuracy": 0.908217191696167, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9813953488372092, |
| "grad_norm": 2.299942970275879, |
| "learning_rate": 1.0148959397730637e-06, |
| "loss": 0.2626, |
| "mean_token_accuracy": 0.9057932496070862, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.986046511627907, |
| "grad_norm": 2.232316017150879, |
| "learning_rate": 1.0095352963131057e-06, |
| "loss": 0.2853, |
| "mean_token_accuracy": 0.9010600447654724, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.9906976744186047, |
| "grad_norm": 2.287255048751831, |
| "learning_rate": 1.0053644332938118e-06, |
| "loss": 0.251, |
| "mean_token_accuracy": 0.9092245697975159, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.9953488372093023, |
| "grad_norm": 2.229083776473999, |
| "learning_rate": 1.0023844558148912e-06, |
| "loss": 0.2969, |
| "mean_token_accuracy": 0.8984347581863403, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.0628480911254883, |
| "learning_rate": 1.0005961534424925e-06, |
| "loss": 0.2309, |
| "mean_token_accuracy": 0.909231960773468, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 215, |
| "total_flos": 2.0144468407196058e+17, |
| "train_loss": 0.325891209826913, |
| "train_runtime": 788.7208, |
| "train_samples_per_second": 8.686, |
| "train_steps_per_second": 0.273 |
| } |
| ], |
| "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 |
| } |
|
|
