| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 357, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008403361344537815, |
| "grad_norm": 104.4372376808565, |
| "learning_rate": 0.0, |
| "loss": 3.9089, |
| "mean_token_accuracy": 0.45122942328453064, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01680672268907563, |
| "grad_norm": 98.10999336930358, |
| "learning_rate": 2.7777777777777776e-07, |
| "loss": 3.8963, |
| "mean_token_accuracy": 0.44380152225494385, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.025210084033613446, |
| "grad_norm": 92.87120481263348, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": 3.7997, |
| "mean_token_accuracy": 0.4492985010147095, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.03361344537815126, |
| "grad_norm": 110.57230858204892, |
| "learning_rate": 8.333333333333333e-07, |
| "loss": 3.928, |
| "mean_token_accuracy": 0.460836261510849, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.04201680672268908, |
| "grad_norm": 90.06819058581009, |
| "learning_rate": 1.111111111111111e-06, |
| "loss": 3.8577, |
| "mean_token_accuracy": 0.4474605321884155, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05042016806722689, |
| "grad_norm": 75.40855511519277, |
| "learning_rate": 1.3888888888888892e-06, |
| "loss": 3.6608, |
| "mean_token_accuracy": 0.4779656231403351, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.058823529411764705, |
| "grad_norm": 73.89732588358957, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 3.5469, |
| "mean_token_accuracy": 0.47866302728652954, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.06722689075630252, |
| "grad_norm": 82.73222876396211, |
| "learning_rate": 1.944444444444445e-06, |
| "loss": 3.5171, |
| "mean_token_accuracy": 0.5113741159439087, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.07563025210084033, |
| "grad_norm": 63.249017072704156, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": 3.1294, |
| "mean_token_accuracy": 0.5332269072532654, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.08403361344537816, |
| "grad_norm": 68.85631329508037, |
| "learning_rate": 2.5e-06, |
| "loss": 3.0802, |
| "mean_token_accuracy": 0.5294961929321289, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09243697478991597, |
| "grad_norm": 63.64196255828432, |
| "learning_rate": 2.7777777777777783e-06, |
| "loss": 2.8732, |
| "mean_token_accuracy": 0.560966968536377, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.10084033613445378, |
| "grad_norm": 49.122370073792986, |
| "learning_rate": 3.055555555555556e-06, |
| "loss": 2.6325, |
| "mean_token_accuracy": 0.601875364780426, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.1092436974789916, |
| "grad_norm": 49.70719812298082, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 2.3901, |
| "mean_token_accuracy": 0.6398412585258484, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.11764705882352941, |
| "grad_norm": 35.41862792612833, |
| "learning_rate": 3.6111111111111115e-06, |
| "loss": 2.3466, |
| "mean_token_accuracy": 0.6401209831237793, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.12605042016806722, |
| "grad_norm": 23.460448508418253, |
| "learning_rate": 3.88888888888889e-06, |
| "loss": 2.1613, |
| "mean_token_accuracy": 0.6581956148147583, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.13445378151260504, |
| "grad_norm": 15.423461248854473, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 2.06, |
| "mean_token_accuracy": 0.6584842205047607, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 21.841734671506178, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": 1.9113, |
| "mean_token_accuracy": 0.6887879371643066, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.15126050420168066, |
| "grad_norm": 15.39983628389419, |
| "learning_rate": 4.722222222222222e-06, |
| "loss": 1.8525, |
| "mean_token_accuracy": 0.673430860042572, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.15966386554621848, |
| "grad_norm": 11.345224686864404, |
| "learning_rate": 5e-06, |
| "loss": 1.8167, |
| "mean_token_accuracy": 0.6806354522705078, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.16806722689075632, |
| "grad_norm": 11.383664059901358, |
| "learning_rate": 5.2777777777777785e-06, |
| "loss": 1.7013, |
| "mean_token_accuracy": 0.701542854309082, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.17647058823529413, |
| "grad_norm": 11.159627826273717, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": 1.7317, |
| "mean_token_accuracy": 0.7015882730484009, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.18487394957983194, |
| "grad_norm": 8.698161210836846, |
| "learning_rate": 5.833333333333334e-06, |
| "loss": 1.6502, |
| "mean_token_accuracy": 0.6944286823272705, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.19327731092436976, |
| "grad_norm": 8.203426143652768, |
| "learning_rate": 6.111111111111112e-06, |
| "loss": 1.6564, |
| "mean_token_accuracy": 0.689929723739624, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.20168067226890757, |
| "grad_norm": 8.72947231703438, |
| "learning_rate": 6.3888888888888885e-06, |
| "loss": 1.6837, |
| "mean_token_accuracy": 0.6912056803703308, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.21008403361344538, |
| "grad_norm": 10.019554814681394, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 1.6172, |
| "mean_token_accuracy": 0.7055233716964722, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2184873949579832, |
| "grad_norm": 8.762233964431482, |
| "learning_rate": 6.944444444444445e-06, |
| "loss": 1.735, |
| "mean_token_accuracy": 0.6735965609550476, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.226890756302521, |
| "grad_norm": 9.496890907951315, |
| "learning_rate": 7.222222222222223e-06, |
| "loss": 1.5669, |
| "mean_token_accuracy": 0.7112628221511841, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.23529411764705882, |
| "grad_norm": 8.640365266893888, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 1.5914, |
| "mean_token_accuracy": 0.6973623037338257, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.24369747899159663, |
| "grad_norm": 8.935200690656034, |
| "learning_rate": 7.77777777777778e-06, |
| "loss": 1.5966, |
| "mean_token_accuracy": 0.6914668083190918, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.25210084033613445, |
| "grad_norm": 9.84167532128932, |
| "learning_rate": 8.055555555555557e-06, |
| "loss": 1.5734, |
| "mean_token_accuracy": 0.7058435678482056, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2605042016806723, |
| "grad_norm": 10.013168019527438, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 1.572, |
| "mean_token_accuracy": 0.7126001715660095, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.2689075630252101, |
| "grad_norm": 9.112923015452898, |
| "learning_rate": 8.611111111111112e-06, |
| "loss": 1.5385, |
| "mean_token_accuracy": 0.7096664905548096, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2773109243697479, |
| "grad_norm": 9.793020899518824, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 1.518, |
| "mean_token_accuracy": 0.7187545895576477, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 9.628147058943762, |
| "learning_rate": 9.166666666666666e-06, |
| "loss": 1.5619, |
| "mean_token_accuracy": 0.7068073749542236, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.29411764705882354, |
| "grad_norm": 9.322487467869243, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 1.5095, |
| "mean_token_accuracy": 0.7060914635658264, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.3025210084033613, |
| "grad_norm": 10.594179592003238, |
| "learning_rate": 9.722222222222223e-06, |
| "loss": 1.4832, |
| "mean_token_accuracy": 0.7262417078018188, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.31092436974789917, |
| "grad_norm": 10.083169080805554, |
| "learning_rate": 1e-05, |
| "loss": 1.4928, |
| "mean_token_accuracy": 0.7256395220756531, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.31932773109243695, |
| "grad_norm": 9.92763598568147, |
| "learning_rate": 9.999784489352286e-06, |
| "loss": 1.3933, |
| "mean_token_accuracy": 0.7489925026893616, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.3277310924369748, |
| "grad_norm": 11.057230462379247, |
| "learning_rate": 9.999137978051292e-06, |
| "loss": 1.3839, |
| "mean_token_accuracy": 0.7571026086807251, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.33613445378151263, |
| "grad_norm": 10.082650172151949, |
| "learning_rate": 9.998060528021493e-06, |
| "loss": 1.4143, |
| "mean_token_accuracy": 0.7438783645629883, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3445378151260504, |
| "grad_norm": 9.30493256103091, |
| "learning_rate": 9.99655224246376e-06, |
| "loss": 1.3787, |
| "mean_token_accuracy": 0.7577965259552002, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.35294117647058826, |
| "grad_norm": 9.743435910238581, |
| "learning_rate": 9.994613265845468e-06, |
| "loss": 1.3323, |
| "mean_token_accuracy": 0.7646293640136719, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.36134453781512604, |
| "grad_norm": 9.969788801557407, |
| "learning_rate": 9.992243783886663e-06, |
| "loss": 1.404, |
| "mean_token_accuracy": 0.7562830448150635, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.3697478991596639, |
| "grad_norm": 9.82178466303166, |
| "learning_rate": 9.989444023542278e-06, |
| "loss": 1.3116, |
| "mean_token_accuracy": 0.769361138343811, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.37815126050420167, |
| "grad_norm": 9.678366165178637, |
| "learning_rate": 9.986214252980384e-06, |
| "loss": 1.365, |
| "mean_token_accuracy": 0.7564687728881836, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3865546218487395, |
| "grad_norm": 9.818428882137175, |
| "learning_rate": 9.982554781556512e-06, |
| "loss": 1.2655, |
| "mean_token_accuracy": 0.7726576924324036, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3949579831932773, |
| "grad_norm": 9.835594218628971, |
| "learning_rate": 9.978465959784022e-06, |
| "loss": 1.3105, |
| "mean_token_accuracy": 0.7650916576385498, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.40336134453781514, |
| "grad_norm": 9.914615259627901, |
| "learning_rate": 9.973948179300528e-06, |
| "loss": 1.2849, |
| "mean_token_accuracy": 0.7597100138664246, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.4117647058823529, |
| "grad_norm": 9.536239789922774, |
| "learning_rate": 9.969001872830383e-06, |
| "loss": 1.2684, |
| "mean_token_accuracy": 0.7620344758033752, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.42016806722689076, |
| "grad_norm": 9.149544132237768, |
| "learning_rate": 9.963627514143235e-06, |
| "loss": 1.2362, |
| "mean_token_accuracy": 0.7652192711830139, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 8.919296728152334, |
| "learning_rate": 9.957825618008653e-06, |
| "loss": 1.2549, |
| "mean_token_accuracy": 0.7582887411117554, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.4369747899159664, |
| "grad_norm": 8.368972719074613, |
| "learning_rate": 9.951596740146809e-06, |
| "loss": 1.3071, |
| "mean_token_accuracy": 0.7387862801551819, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.44537815126050423, |
| "grad_norm": 8.317783553834479, |
| "learning_rate": 9.944941477175258e-06, |
| "loss": 1.2612, |
| "mean_token_accuracy": 0.7465383410453796, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.453781512605042, |
| "grad_norm": 8.35597079044532, |
| "learning_rate": 9.9378604665518e-06, |
| "loss": 1.2092, |
| "mean_token_accuracy": 0.7614982724189758, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.46218487394957986, |
| "grad_norm": 7.956620910361454, |
| "learning_rate": 9.930354386513399e-06, |
| "loss": 1.1718, |
| "mean_token_accuracy": 0.7644634246826172, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.47058823529411764, |
| "grad_norm": 7.2835787111036865, |
| "learning_rate": 9.922423956011245e-06, |
| "loss": 1.1805, |
| "mean_token_accuracy": 0.7627302408218384, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.4789915966386555, |
| "grad_norm": 6.932403381323147, |
| "learning_rate": 9.914069934641877e-06, |
| "loss": 1.2061, |
| "mean_token_accuracy": 0.752274751663208, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.48739495798319327, |
| "grad_norm": 6.343299562405531, |
| "learning_rate": 9.905293122574433e-06, |
| "loss": 1.12, |
| "mean_token_accuracy": 0.7687320709228516, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.4957983193277311, |
| "grad_norm": 5.543396984847555, |
| "learning_rate": 9.896094360474e-06, |
| "loss": 1.1802, |
| "mean_token_accuracy": 0.7473610639572144, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.5042016806722689, |
| "grad_norm": 5.121375049126032, |
| "learning_rate": 9.886474529421108e-06, |
| "loss": 1.1593, |
| "mean_token_accuracy": 0.7524569034576416, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5126050420168067, |
| "grad_norm": 5.031005200717522, |
| "learning_rate": 9.876434550827315e-06, |
| "loss": 1.1189, |
| "mean_token_accuracy": 0.7657356858253479, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.5210084033613446, |
| "grad_norm": 4.373010543661186, |
| "learning_rate": 9.865975386346977e-06, |
| "loss": 1.1085, |
| "mean_token_accuracy": 0.7596036195755005, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.5294117647058824, |
| "grad_norm": 3.661434030339827, |
| "learning_rate": 9.855098037785118e-06, |
| "loss": 1.1622, |
| "mean_token_accuracy": 0.7517811059951782, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.5378151260504201, |
| "grad_norm": 3.078839220181403, |
| "learning_rate": 9.843803547001487e-06, |
| "loss": 1.2342, |
| "mean_token_accuracy": 0.7375519275665283, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.5462184873949579, |
| "grad_norm": 3.3400715637598446, |
| "learning_rate": 9.832092995810763e-06, |
| "loss": 1.0596, |
| "mean_token_accuracy": 0.780117928981781, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5546218487394958, |
| "grad_norm": 2.8550783454393773, |
| "learning_rate": 9.819967505878932e-06, |
| "loss": 1.0918, |
| "mean_token_accuracy": 0.7683150172233582, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.5630252100840336, |
| "grad_norm": 3.093651064477546, |
| "learning_rate": 9.807428238615858e-06, |
| "loss": 1.0957, |
| "mean_token_accuracy": 0.7789058089256287, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 2.960983075251036, |
| "learning_rate": 9.794476395064032e-06, |
| "loss": 1.1268, |
| "mean_token_accuracy": 0.7565435767173767, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.5798319327731093, |
| "grad_norm": 2.8817853958410145, |
| "learning_rate": 9.781113215783541e-06, |
| "loss": 1.1262, |
| "mean_token_accuracy": 0.7553396821022034, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.5882352941176471, |
| "grad_norm": 2.850151755259942, |
| "learning_rate": 9.76733998073324e-06, |
| "loss": 1.137, |
| "mean_token_accuracy": 0.7587066292762756, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5966386554621849, |
| "grad_norm": 2.992963756739842, |
| "learning_rate": 9.75315800914815e-06, |
| "loss": 1.11, |
| "mean_token_accuracy": 0.7620386481285095, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.6050420168067226, |
| "grad_norm": 3.1922451576730735, |
| "learning_rate": 9.738568659413116e-06, |
| "loss": 1.114, |
| "mean_token_accuracy": 0.7604764103889465, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.6134453781512605, |
| "grad_norm": 3.2221397960034266, |
| "learning_rate": 9.723573328932669e-06, |
| "loss": 1.1063, |
| "mean_token_accuracy": 0.7661125063896179, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.6218487394957983, |
| "grad_norm": 3.048363865232976, |
| "learning_rate": 9.708173453997202e-06, |
| "loss": 1.1882, |
| "mean_token_accuracy": 0.7403683066368103, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.6302521008403361, |
| "grad_norm": 3.0892769258313533, |
| "learning_rate": 9.692370509645396e-06, |
| "loss": 1.0613, |
| "mean_token_accuracy": 0.7737182974815369, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6386554621848739, |
| "grad_norm": 2.9578404772617675, |
| "learning_rate": 9.676166009522925e-06, |
| "loss": 1.116, |
| "mean_token_accuracy": 0.7655495405197144, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.6470588235294118, |
| "grad_norm": 3.1583547042694926, |
| "learning_rate": 9.659561505737486e-06, |
| "loss": 1.1386, |
| "mean_token_accuracy": 0.7496492862701416, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.6554621848739496, |
| "grad_norm": 3.17445671844221, |
| "learning_rate": 9.64255858871013e-06, |
| "loss": 0.9822, |
| "mean_token_accuracy": 0.7807889580726624, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.6638655462184874, |
| "grad_norm": 3.004016438011611, |
| "learning_rate": 9.62515888702293e-06, |
| "loss": 1.017, |
| "mean_token_accuracy": 0.7823821902275085, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.6722689075630253, |
| "grad_norm": 2.9647806910582504, |
| "learning_rate": 9.607364067262988e-06, |
| "loss": 1.0829, |
| "mean_token_accuracy": 0.7621784806251526, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.680672268907563, |
| "grad_norm": 2.740020920509613, |
| "learning_rate": 9.58917583386281e-06, |
| "loss": 1.2256, |
| "mean_token_accuracy": 0.733435332775116, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.6890756302521008, |
| "grad_norm": 2.546166061674224, |
| "learning_rate": 9.57059592893704e-06, |
| "loss": 1.0641, |
| "mean_token_accuracy": 0.764522910118103, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.6974789915966386, |
| "grad_norm": 2.5362939949339114, |
| "learning_rate": 9.55162613211561e-06, |
| "loss": 1.0637, |
| "mean_token_accuracy": 0.766620934009552, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.7058823529411765, |
| "grad_norm": 2.672979034931999, |
| "learning_rate": 9.53226826037328e-06, |
| "loss": 0.9843, |
| "mean_token_accuracy": 0.7884352207183838, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.455065490024706, |
| "learning_rate": 9.51252416785559e-06, |
| "loss": 1.0195, |
| "mean_token_accuracy": 0.7825503349304199, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7226890756302521, |
| "grad_norm": 2.3693414239443897, |
| "learning_rate": 9.492395745701287e-06, |
| "loss": 1.1646, |
| "mean_token_accuracy": 0.7410282492637634, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.7310924369747899, |
| "grad_norm": 2.458895527399391, |
| "learning_rate": 9.471884921861165e-06, |
| "loss": 1.1175, |
| "mean_token_accuracy": 0.7548961043357849, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.7394957983193278, |
| "grad_norm": 2.3848761193475587, |
| "learning_rate": 9.450993660913418e-06, |
| "loss": 1.0716, |
| "mean_token_accuracy": 0.759257972240448, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.7478991596638656, |
| "grad_norm": 2.2417278733421995, |
| "learning_rate": 9.429723963875454e-06, |
| "loss": 1.0341, |
| "mean_token_accuracy": 0.773446261882782, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.7563025210084033, |
| "grad_norm": 2.224722679174331, |
| "learning_rate": 9.408077868012248e-06, |
| "loss": 1.064, |
| "mean_token_accuracy": 0.7724658250808716, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7647058823529411, |
| "grad_norm": 2.302623362463434, |
| "learning_rate": 9.386057446641195e-06, |
| "loss": 0.9708, |
| "mean_token_accuracy": 0.7837342619895935, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.773109243697479, |
| "grad_norm": 2.131194431916736, |
| "learning_rate": 9.363664808933529e-06, |
| "loss": 1.1295, |
| "mean_token_accuracy": 0.753643810749054, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.7815126050420168, |
| "grad_norm": 2.4261127329171117, |
| "learning_rate": 9.340902099712294e-06, |
| "loss": 1.1255, |
| "mean_token_accuracy": 0.7631184458732605, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.7899159663865546, |
| "grad_norm": 2.1187942609232526, |
| "learning_rate": 9.317771499246918e-06, |
| "loss": 1.0471, |
| "mean_token_accuracy": 0.7643110156059265, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.7983193277310925, |
| "grad_norm": 1.9980151763738605, |
| "learning_rate": 9.294275223044372e-06, |
| "loss": 1.0263, |
| "mean_token_accuracy": 0.7738521099090576, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8067226890756303, |
| "grad_norm": 2.033786742643822, |
| "learning_rate": 9.270415521636971e-06, |
| "loss": 1.084, |
| "mean_token_accuracy": 0.7599940896034241, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.8151260504201681, |
| "grad_norm": 2.168443561732016, |
| "learning_rate": 9.246194680366802e-06, |
| "loss": 1.047, |
| "mean_token_accuracy": 0.7660160660743713, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.8235294117647058, |
| "grad_norm": 1.998790146565347, |
| "learning_rate": 9.221615019166844e-06, |
| "loss": 1.1367, |
| "mean_token_accuracy": 0.7494749426841736, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.8319327731092437, |
| "grad_norm": 1.9129114293452298, |
| "learning_rate": 9.19667889233874e-06, |
| "loss": 1.098, |
| "mean_token_accuracy": 0.7525637745857239, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.8403361344537815, |
| "grad_norm": 1.9382375740584845, |
| "learning_rate": 9.171388688327307e-06, |
| "loss": 1.0382, |
| "mean_token_accuracy": 0.7737355828285217, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8487394957983193, |
| "grad_norm": 2.012931555112626, |
| "learning_rate": 9.145746829491775e-06, |
| "loss": 1.0205, |
| "mean_token_accuracy": 0.7717574834823608, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 1.9857323536700038, |
| "learning_rate": 9.119755771873737e-06, |
| "loss": 1.1345, |
| "mean_token_accuracy": 0.7516574859619141, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.865546218487395, |
| "grad_norm": 2.0206369529828723, |
| "learning_rate": 9.093418004961939e-06, |
| "loss": 1.0117, |
| "mean_token_accuracy": 0.7809069156646729, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.8739495798319328, |
| "grad_norm": 1.9912220371473022, |
| "learning_rate": 9.066736051453802e-06, |
| "loss": 1.1656, |
| "mean_token_accuracy": 0.7395861148834229, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.8823529411764706, |
| "grad_norm": 2.1335788688419135, |
| "learning_rate": 9.039712467013808e-06, |
| "loss": 1.1239, |
| "mean_token_accuracy": 0.7545720934867859, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.8907563025210085, |
| "grad_norm": 2.272579879171099, |
| "learning_rate": 9.012349840028707e-06, |
| "loss": 1.0229, |
| "mean_token_accuracy": 0.7670172452926636, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.8991596638655462, |
| "grad_norm": 2.0353968319884834, |
| "learning_rate": 8.984650791359596e-06, |
| "loss": 1.077, |
| "mean_token_accuracy": 0.7584921717643738, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.907563025210084, |
| "grad_norm": 1.9860241702061474, |
| "learning_rate": 8.956617974090879e-06, |
| "loss": 1.138, |
| "mean_token_accuracy": 0.7530872821807861, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.9159663865546218, |
| "grad_norm": 1.8039419277889777, |
| "learning_rate": 8.928254073276166e-06, |
| "loss": 1.1177, |
| "mean_token_accuracy": 0.755870521068573, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.9243697478991597, |
| "grad_norm": 1.9777313920085413, |
| "learning_rate": 8.899561805681067e-06, |
| "loss": 1.0633, |
| "mean_token_accuracy": 0.7670658826828003, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9327731092436975, |
| "grad_norm": 1.9837274369580524, |
| "learning_rate": 8.870543919522996e-06, |
| "loss": 1.0557, |
| "mean_token_accuracy": 0.7702457904815674, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.9411764705882353, |
| "grad_norm": 1.8612596386033633, |
| "learning_rate": 8.841203194207925e-06, |
| "loss": 0.9907, |
| "mean_token_accuracy": 0.7775035500526428, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.9495798319327731, |
| "grad_norm": 2.034853673482078, |
| "learning_rate": 8.811542440064174e-06, |
| "loss": 1.2261, |
| "mean_token_accuracy": 0.7283035516738892, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.957983193277311, |
| "grad_norm": 1.9548359467744874, |
| "learning_rate": 8.781564498073226e-06, |
| "loss": 1.0533, |
| "mean_token_accuracy": 0.7671497464179993, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.9663865546218487, |
| "grad_norm": 1.9022866929004814, |
| "learning_rate": 8.751272239597612e-06, |
| "loss": 1.0574, |
| "mean_token_accuracy": 0.7680447697639465, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.9747899159663865, |
| "grad_norm": 1.8866837322531922, |
| "learning_rate": 8.720668566105883e-06, |
| "loss": 1.1859, |
| "mean_token_accuracy": 0.7381235957145691, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.9831932773109243, |
| "grad_norm": 1.8348643484595748, |
| "learning_rate": 8.689756408894709e-06, |
| "loss": 1.0349, |
| "mean_token_accuracy": 0.7731918692588806, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.9915966386554622, |
| "grad_norm": 2.0203019049012094, |
| "learning_rate": 8.658538728808097e-06, |
| "loss": 0.9747, |
| "mean_token_accuracy": 0.7861313819885254, |
| "step": 118 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.8151270192332218, |
| "learning_rate": 8.627018515953807e-06, |
| "loss": 1.0169, |
| "mean_token_accuracy": 0.7644779682159424, |
| "step": 119 |
| }, |
| { |
| "epoch": 1.0084033613445378, |
| "grad_norm": 2.858568409053351, |
| "learning_rate": 8.595198789416943e-06, |
| "loss": 0.8765, |
| "mean_token_accuracy": 0.8038392066955566, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0168067226890756, |
| "grad_norm": 2.563535999934096, |
| "learning_rate": 8.563082596970785e-06, |
| "loss": 0.8011, |
| "mean_token_accuracy": 0.8078204989433289, |
| "step": 121 |
| }, |
| { |
| "epoch": 1.0252100840336134, |
| "grad_norm": 2.2281587546425365, |
| "learning_rate": 8.530673014784857e-06, |
| "loss": 0.9006, |
| "mean_token_accuracy": 0.7865578532218933, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0336134453781514, |
| "grad_norm": 1.8772863169719356, |
| "learning_rate": 8.497973147130296e-06, |
| "loss": 0.8306, |
| "mean_token_accuracy": 0.8074118494987488, |
| "step": 123 |
| }, |
| { |
| "epoch": 1.0420168067226891, |
| "grad_norm": 1.8041988985955282, |
| "learning_rate": 8.4649861260825e-06, |
| "loss": 0.8681, |
| "mean_token_accuracy": 0.796225368976593, |
| "step": 124 |
| }, |
| { |
| "epoch": 1.050420168067227, |
| "grad_norm": 2.320587748605426, |
| "learning_rate": 8.431715111221152e-06, |
| "loss": 0.8577, |
| "mean_token_accuracy": 0.7973388433456421, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.0588235294117647, |
| "grad_norm": 3.390802826249011, |
| "learning_rate": 8.398163289327568e-06, |
| "loss": 0.8007, |
| "mean_token_accuracy": 0.8107035756111145, |
| "step": 126 |
| }, |
| { |
| "epoch": 1.0672268907563025, |
| "grad_norm": 2.500716325470751, |
| "learning_rate": 8.364333874079462e-06, |
| "loss": 0.8029, |
| "mean_token_accuracy": 0.810440182685852, |
| "step": 127 |
| }, |
| { |
| "epoch": 1.0756302521008403, |
| "grad_norm": 1.9737423505205354, |
| "learning_rate": 8.330230105743147e-06, |
| "loss": 0.8521, |
| "mean_token_accuracy": 0.7987682223320007, |
| "step": 128 |
| }, |
| { |
| "epoch": 1.084033613445378, |
| "grad_norm": 1.8133876990453317, |
| "learning_rate": 8.295855250863156e-06, |
| "loss": 0.7874, |
| "mean_token_accuracy": 0.8133313655853271, |
| "step": 129 |
| }, |
| { |
| "epoch": 1.092436974789916, |
| "grad_norm": 1.7704884430147076, |
| "learning_rate": 8.261212601949374e-06, |
| "loss": 0.8614, |
| "mean_token_accuracy": 0.7912753224372864, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.1008403361344539, |
| "grad_norm": 1.9029134321486696, |
| "learning_rate": 8.226305477161669e-06, |
| "loss": 0.9127, |
| "mean_token_accuracy": 0.7861339449882507, |
| "step": 131 |
| }, |
| { |
| "epoch": 1.1092436974789917, |
| "grad_norm": 1.9422789961546394, |
| "learning_rate": 8.191137219992073e-06, |
| "loss": 0.8379, |
| "mean_token_accuracy": 0.8037659525871277, |
| "step": 132 |
| }, |
| { |
| "epoch": 1.1176470588235294, |
| "grad_norm": 1.836152314149856, |
| "learning_rate": 8.155711198944536e-06, |
| "loss": 0.8096, |
| "mean_token_accuracy": 0.8135814666748047, |
| "step": 133 |
| }, |
| { |
| "epoch": 1.1260504201680672, |
| "grad_norm": 1.9512642996739955, |
| "learning_rate": 8.120030807212276e-06, |
| "loss": 0.805, |
| "mean_token_accuracy": 0.8122808337211609, |
| "step": 134 |
| }, |
| { |
| "epoch": 1.134453781512605, |
| "grad_norm": 1.7415637300579179, |
| "learning_rate": 8.084099462352772e-06, |
| "loss": 0.8007, |
| "mean_token_accuracy": 0.8150731921195984, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 1.8482338825609754, |
| "learning_rate": 8.047920605960428e-06, |
| "loss": 0.7917, |
| "mean_token_accuracy": 0.8171132206916809, |
| "step": 136 |
| }, |
| { |
| "epoch": 1.1512605042016806, |
| "grad_norm": 1.884493107778714, |
| "learning_rate": 8.011497703336921e-06, |
| "loss": 0.898, |
| "mean_token_accuracy": 0.7803546190261841, |
| "step": 137 |
| }, |
| { |
| "epoch": 1.1596638655462184, |
| "grad_norm": 1.746134878476434, |
| "learning_rate": 7.974834243159288e-06, |
| "loss": 0.8086, |
| "mean_token_accuracy": 0.8132433891296387, |
| "step": 138 |
| }, |
| { |
| "epoch": 1.1680672268907564, |
| "grad_norm": 1.81867124622388, |
| "learning_rate": 7.937933737145777e-06, |
| "loss": 0.889, |
| "mean_token_accuracy": 0.7920069098472595, |
| "step": 139 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 1.8766821031228575, |
| "learning_rate": 7.900799719719473e-06, |
| "loss": 0.8136, |
| "mean_token_accuracy": 0.8072178959846497, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.184873949579832, |
| "grad_norm": 2.0915138411757592, |
| "learning_rate": 7.863435747669781e-06, |
| "loss": 0.7758, |
| "mean_token_accuracy": 0.816449761390686, |
| "step": 141 |
| }, |
| { |
| "epoch": 1.1932773109243697, |
| "grad_norm": 1.9258493343252368, |
| "learning_rate": 7.825845399811723e-06, |
| "loss": 0.8785, |
| "mean_token_accuracy": 0.7919079065322876, |
| "step": 142 |
| }, |
| { |
| "epoch": 1.2016806722689075, |
| "grad_norm": 1.79704777405251, |
| "learning_rate": 7.788032276643181e-06, |
| "loss": 0.8391, |
| "mean_token_accuracy": 0.805074155330658, |
| "step": 143 |
| }, |
| { |
| "epoch": 1.2100840336134453, |
| "grad_norm": 1.8565096562958643, |
| "learning_rate": 7.75e-06, |
| "loss": 0.8627, |
| "mean_token_accuracy": 0.7953042984008789, |
| "step": 144 |
| }, |
| { |
| "epoch": 1.2184873949579833, |
| "grad_norm": 1.7568303758649213, |
| "learning_rate": 7.711752212709106e-06, |
| "loss": 0.7859, |
| "mean_token_accuracy": 0.8123944997787476, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.226890756302521, |
| "grad_norm": 1.769664699980329, |
| "learning_rate": 7.673292578239569e-06, |
| "loss": 0.8927, |
| "mean_token_accuracy": 0.7881185412406921, |
| "step": 146 |
| }, |
| { |
| "epoch": 1.2352941176470589, |
| "grad_norm": 1.7762583026108316, |
| "learning_rate": 7.634624780351715e-06, |
| "loss": 0.7979, |
| "mean_token_accuracy": 0.8104432821273804, |
| "step": 147 |
| }, |
| { |
| "epoch": 1.2436974789915967, |
| "grad_norm": 1.8444818695347533, |
| "learning_rate": 7.595752522744287e-06, |
| "loss": 0.685, |
| "mean_token_accuracy": 0.8296918869018555, |
| "step": 148 |
| }, |
| { |
| "epoch": 1.2521008403361344, |
| "grad_norm": 1.6589733125236013, |
| "learning_rate": 7.556679528699692e-06, |
| "loss": 0.7998, |
| "mean_token_accuracy": 0.8100078701972961, |
| "step": 149 |
| }, |
| { |
| "epoch": 1.2605042016806722, |
| "grad_norm": 1.8160364471890191, |
| "learning_rate": 7.5174095407273765e-06, |
| "loss": 0.6939, |
| "mean_token_accuracy": 0.8351863622665405, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.26890756302521, |
| "grad_norm": 1.8158422888302235, |
| "learning_rate": 7.477946320205358e-06, |
| "loss": 0.7705, |
| "mean_token_accuracy": 0.8159504532814026, |
| "step": 151 |
| }, |
| { |
| "epoch": 1.2773109243697478, |
| "grad_norm": 1.88868521231513, |
| "learning_rate": 7.438293647019958e-06, |
| "loss": 0.786, |
| "mean_token_accuracy": 0.817752480506897, |
| "step": 152 |
| }, |
| { |
| "epoch": 1.2857142857142856, |
| "grad_norm": 1.669440069435849, |
| "learning_rate": 7.398455319203741e-06, |
| "loss": 0.7114, |
| "mean_token_accuracy": 0.8334900736808777, |
| "step": 153 |
| }, |
| { |
| "epoch": 1.2941176470588236, |
| "grad_norm": 1.8859412020788646, |
| "learning_rate": 7.358435152571749e-06, |
| "loss": 0.7507, |
| "mean_token_accuracy": 0.820056140422821, |
| "step": 154 |
| }, |
| { |
| "epoch": 1.3025210084033614, |
| "grad_norm": 1.8440185592893792, |
| "learning_rate": 7.318236980355993e-06, |
| "loss": 0.7795, |
| "mean_token_accuracy": 0.8169759511947632, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.3109243697478992, |
| "grad_norm": 1.7904168122577475, |
| "learning_rate": 7.2778646528383105e-06, |
| "loss": 0.7735, |
| "mean_token_accuracy": 0.8180586099624634, |
| "step": 156 |
| }, |
| { |
| "epoch": 1.319327731092437, |
| "grad_norm": 1.765680038172988, |
| "learning_rate": 7.237322036981568e-06, |
| "loss": 0.834, |
| "mean_token_accuracy": 0.8086110949516296, |
| "step": 157 |
| }, |
| { |
| "epoch": 1.3277310924369747, |
| "grad_norm": 1.8167654523320387, |
| "learning_rate": 7.196613016059281e-06, |
| "loss": 0.7641, |
| "mean_token_accuracy": 0.8251628875732422, |
| "step": 158 |
| }, |
| { |
| "epoch": 1.3361344537815127, |
| "grad_norm": 1.7892540373408776, |
| "learning_rate": 7.155741489283653e-06, |
| "loss": 0.7715, |
| "mean_token_accuracy": 0.815371036529541, |
| "step": 159 |
| }, |
| { |
| "epoch": 1.3445378151260505, |
| "grad_norm": 2.0679437530612765, |
| "learning_rate": 7.114711371432113e-06, |
| "loss": 0.892, |
| "mean_token_accuracy": 0.7930935621261597, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.3529411764705883, |
| "grad_norm": 1.9245059782180325, |
| "learning_rate": 7.073526592472337e-06, |
| "loss": 0.8448, |
| "mean_token_accuracy": 0.8044028282165527, |
| "step": 161 |
| }, |
| { |
| "epoch": 1.361344537815126, |
| "grad_norm": 1.9104553151840824, |
| "learning_rate": 7.032191097185832e-06, |
| "loss": 0.7271, |
| "mean_token_accuracy": 0.8310403227806091, |
| "step": 162 |
| }, |
| { |
| "epoch": 1.3697478991596639, |
| "grad_norm": 1.798136465856472, |
| "learning_rate": 6.990708844790093e-06, |
| "loss": 0.8835, |
| "mean_token_accuracy": 0.7889003753662109, |
| "step": 163 |
| }, |
| { |
| "epoch": 1.3781512605042017, |
| "grad_norm": 1.7234505675114578, |
| "learning_rate": 6.949083808559378e-06, |
| "loss": 0.8402, |
| "mean_token_accuracy": 0.8051289319992065, |
| "step": 164 |
| }, |
| { |
| "epoch": 1.3865546218487395, |
| "grad_norm": 1.7897230878472068, |
| "learning_rate": 6.90731997544414e-06, |
| "loss": 0.8286, |
| "mean_token_accuracy": 0.8056466579437256, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.3949579831932772, |
| "grad_norm": 1.849230508051203, |
| "learning_rate": 6.865421345689147e-06, |
| "loss": 0.8297, |
| "mean_token_accuracy": 0.8059335947036743, |
| "step": 166 |
| }, |
| { |
| "epoch": 1.403361344537815, |
| "grad_norm": 1.7845120726376866, |
| "learning_rate": 6.8233919324503265e-06, |
| "loss": 0.8854, |
| "mean_token_accuracy": 0.7944253087043762, |
| "step": 167 |
| }, |
| { |
| "epoch": 1.4117647058823528, |
| "grad_norm": 1.8294086172402824, |
| "learning_rate": 6.781235761410374e-06, |
| "loss": 0.8595, |
| "mean_token_accuracy": 0.8054335117340088, |
| "step": 168 |
| }, |
| { |
| "epoch": 1.4201680672268908, |
| "grad_norm": 1.8052234917818033, |
| "learning_rate": 6.73895687039317e-06, |
| "loss": 0.8036, |
| "mean_token_accuracy": 0.8146604299545288, |
| "step": 169 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 1.7998277689388709, |
| "learning_rate": 6.696559308977021e-06, |
| "loss": 0.735, |
| "mean_token_accuracy": 0.8271728754043579, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.4369747899159664, |
| "grad_norm": 1.7330715976428295, |
| "learning_rate": 6.6540471381067785e-06, |
| "loss": 0.8224, |
| "mean_token_accuracy": 0.80235755443573, |
| "step": 171 |
| }, |
| { |
| "epoch": 1.4453781512605042, |
| "grad_norm": 1.876207322246444, |
| "learning_rate": 6.611424429704879e-06, |
| "loss": 0.8064, |
| "mean_token_accuracy": 0.8060723543167114, |
| "step": 172 |
| }, |
| { |
| "epoch": 1.453781512605042, |
| "grad_norm": 1.826777321537923, |
| "learning_rate": 6.5686952662813215e-06, |
| "loss": 0.7626, |
| "mean_token_accuracy": 0.8241952657699585, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.46218487394958, |
| "grad_norm": 1.9309690813658709, |
| "learning_rate": 6.525863740542633e-06, |
| "loss": 0.8768, |
| "mean_token_accuracy": 0.7913132905960083, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.4705882352941178, |
| "grad_norm": 1.9363389825762378, |
| "learning_rate": 6.482933954999858e-06, |
| "loss": 0.742, |
| "mean_token_accuracy": 0.8222526907920837, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.4789915966386555, |
| "grad_norm": 1.7340115535262608, |
| "learning_rate": 6.439910021575617e-06, |
| "loss": 0.8238, |
| "mean_token_accuracy": 0.8056747913360596, |
| "step": 176 |
| }, |
| { |
| "epoch": 1.4873949579831933, |
| "grad_norm": 1.7607961684480655, |
| "learning_rate": 6.396796061210245e-06, |
| "loss": 0.8639, |
| "mean_token_accuracy": 0.7974097728729248, |
| "step": 177 |
| }, |
| { |
| "epoch": 1.495798319327731, |
| "grad_norm": 1.912300447750382, |
| "learning_rate": 6.353596203467085e-06, |
| "loss": 0.8516, |
| "mean_token_accuracy": 0.7965307235717773, |
| "step": 178 |
| }, |
| { |
| "epoch": 1.504201680672269, |
| "grad_norm": 1.9148975976568732, |
| "learning_rate": 6.3103145861369505e-06, |
| "loss": 0.8007, |
| "mean_token_accuracy": 0.8129093050956726, |
| "step": 179 |
| }, |
| { |
| "epoch": 1.5126050420168067, |
| "grad_norm": 1.8491807086301022, |
| "learning_rate": 6.266955354841788e-06, |
| "loss": 0.7817, |
| "mean_token_accuracy": 0.8149424195289612, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.5210084033613445, |
| "grad_norm": 1.8115593786268498, |
| "learning_rate": 6.2235226626376075e-06, |
| "loss": 0.7714, |
| "mean_token_accuracy": 0.8186544179916382, |
| "step": 181 |
| }, |
| { |
| "epoch": 1.5294117647058822, |
| "grad_norm": 1.8341527270888607, |
| "learning_rate": 6.180020669616689e-06, |
| "loss": 0.791, |
| "mean_token_accuracy": 0.8164339661598206, |
| "step": 182 |
| }, |
| { |
| "epoch": 1.53781512605042, |
| "grad_norm": 1.7479348310610867, |
| "learning_rate": 6.1364535425091175e-06, |
| "loss": 0.8119, |
| "mean_token_accuracy": 0.8093591332435608, |
| "step": 183 |
| }, |
| { |
| "epoch": 1.5462184873949578, |
| "grad_norm": 1.748030323352481, |
| "learning_rate": 6.0928254542836855e-06, |
| "loss": 0.7798, |
| "mean_token_accuracy": 0.8146873712539673, |
| "step": 184 |
| }, |
| { |
| "epoch": 1.5546218487394958, |
| "grad_norm": 1.7171481257834251, |
| "learning_rate": 6.049140583748193e-06, |
| "loss": 0.7612, |
| "mean_token_accuracy": 0.8190532326698303, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.5630252100840336, |
| "grad_norm": 1.8479808075500652, |
| "learning_rate": 6.005403115149194e-06, |
| "loss": 0.6937, |
| "mean_token_accuracy": 0.838882565498352, |
| "step": 186 |
| }, |
| { |
| "epoch": 1.5714285714285714, |
| "grad_norm": 2.117162630613232, |
| "learning_rate": 5.961617237771217e-06, |
| "loss": 0.9241, |
| "mean_token_accuracy": 0.7848495244979858, |
| "step": 187 |
| }, |
| { |
| "epoch": 1.5798319327731094, |
| "grad_norm": 1.750486932166757, |
| "learning_rate": 5.917787145535502e-06, |
| "loss": 0.7778, |
| "mean_token_accuracy": 0.8146782517433167, |
| "step": 188 |
| }, |
| { |
| "epoch": 1.5882352941176472, |
| "grad_norm": 1.8908131914774162, |
| "learning_rate": 5.873917036598301e-06, |
| "loss": 0.8392, |
| "mean_token_accuracy": 0.7985531687736511, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.596638655462185, |
| "grad_norm": 1.8273639504026071, |
| "learning_rate": 5.830011112948768e-06, |
| "loss": 0.7724, |
| "mean_token_accuracy": 0.81374192237854, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.6050420168067228, |
| "grad_norm": 1.828941646368098, |
| "learning_rate": 5.786073580006478e-06, |
| "loss": 0.785, |
| "mean_token_accuracy": 0.8174896240234375, |
| "step": 191 |
| }, |
| { |
| "epoch": 1.6134453781512605, |
| "grad_norm": 1.7330730222271304, |
| "learning_rate": 5.742108646218622e-06, |
| "loss": 0.8689, |
| "mean_token_accuracy": 0.7993961572647095, |
| "step": 192 |
| }, |
| { |
| "epoch": 1.6218487394957983, |
| "grad_norm": 1.7144231122228817, |
| "learning_rate": 5.698120522656916e-06, |
| "loss": 0.7063, |
| "mean_token_accuracy": 0.830324649810791, |
| "step": 193 |
| }, |
| { |
| "epoch": 1.6302521008403361, |
| "grad_norm": 1.9817707355442309, |
| "learning_rate": 5.654113422614249e-06, |
| "loss": 0.9405, |
| "mean_token_accuracy": 0.779734194278717, |
| "step": 194 |
| }, |
| { |
| "epoch": 1.638655462184874, |
| "grad_norm": 1.8152467597722433, |
| "learning_rate": 5.610091561201123e-06, |
| "loss": 0.8376, |
| "mean_token_accuracy": 0.8002806305885315, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.6470588235294117, |
| "grad_norm": 1.7562031104736542, |
| "learning_rate": 5.566059154941925e-06, |
| "loss": 0.8001, |
| "mean_token_accuracy": 0.8095415234565735, |
| "step": 196 |
| }, |
| { |
| "epoch": 1.6554621848739495, |
| "grad_norm": 1.7465382260554791, |
| "learning_rate": 5.522020421371053e-06, |
| "loss": 0.7886, |
| "mean_token_accuracy": 0.8145126104354858, |
| "step": 197 |
| }, |
| { |
| "epoch": 1.6638655462184873, |
| "grad_norm": 1.8000228189517324, |
| "learning_rate": 5.477979578628949e-06, |
| "loss": 0.8073, |
| "mean_token_accuracy": 0.8087124228477478, |
| "step": 198 |
| }, |
| { |
| "epoch": 1.6722689075630253, |
| "grad_norm": 1.7127026839600348, |
| "learning_rate": 5.433940845058076e-06, |
| "loss": 0.7923, |
| "mean_token_accuracy": 0.8146789073944092, |
| "step": 199 |
| }, |
| { |
| "epoch": 1.680672268907563, |
| "grad_norm": 1.7481710683580405, |
| "learning_rate": 5.38990843879888e-06, |
| "loss": 0.7628, |
| "mean_token_accuracy": 0.8225399255752563, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6890756302521008, |
| "grad_norm": 1.7370632838141555, |
| "learning_rate": 5.345886577385754e-06, |
| "loss": 0.7968, |
| "mean_token_accuracy": 0.8118207454681396, |
| "step": 201 |
| }, |
| { |
| "epoch": 1.6974789915966386, |
| "grad_norm": 1.788668828544874, |
| "learning_rate": 5.301879477343086e-06, |
| "loss": 0.9275, |
| "mean_token_accuracy": 0.7842003703117371, |
| "step": 202 |
| }, |
| { |
| "epoch": 1.7058823529411766, |
| "grad_norm": 1.7557341503386812, |
| "learning_rate": 5.257891353781381e-06, |
| "loss": 0.8115, |
| "mean_token_accuracy": 0.8065828680992126, |
| "step": 203 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 1.8266761935083635, |
| "learning_rate": 5.213926419993524e-06, |
| "loss": 0.8503, |
| "mean_token_accuracy": 0.8006482720375061, |
| "step": 204 |
| }, |
| { |
| "epoch": 1.7226890756302522, |
| "grad_norm": 1.8318814439021893, |
| "learning_rate": 5.169988887051234e-06, |
| "loss": 0.8397, |
| "mean_token_accuracy": 0.800042450428009, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.73109243697479, |
| "grad_norm": 1.7950366268900575, |
| "learning_rate": 5.1260829634017e-06, |
| "loss": 0.8816, |
| "mean_token_accuracy": 0.7939304709434509, |
| "step": 206 |
| }, |
| { |
| "epoch": 1.7394957983193278, |
| "grad_norm": 1.7097851307871237, |
| "learning_rate": 5.0822128544645015e-06, |
| "loss": 0.7794, |
| "mean_token_accuracy": 0.8178083300590515, |
| "step": 207 |
| }, |
| { |
| "epoch": 1.7478991596638656, |
| "grad_norm": 1.7248899218784792, |
| "learning_rate": 5.038382762228786e-06, |
| "loss": 0.8302, |
| "mean_token_accuracy": 0.8006280660629272, |
| "step": 208 |
| }, |
| { |
| "epoch": 1.7563025210084033, |
| "grad_norm": 1.7624161921422554, |
| "learning_rate": 4.994596884850809e-06, |
| "loss": 0.8145, |
| "mean_token_accuracy": 0.8077849745750427, |
| "step": 209 |
| }, |
| { |
| "epoch": 1.7647058823529411, |
| "grad_norm": 1.772558161317811, |
| "learning_rate": 4.95085941625181e-06, |
| "loss": 0.7222, |
| "mean_token_accuracy": 0.8232572078704834, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.773109243697479, |
| "grad_norm": 1.7357919073002692, |
| "learning_rate": 4.907174545716317e-06, |
| "loss": 0.7584, |
| "mean_token_accuracy": 0.8207970857620239, |
| "step": 211 |
| }, |
| { |
| "epoch": 1.7815126050420167, |
| "grad_norm": 1.7737912355330372, |
| "learning_rate": 4.863546457490886e-06, |
| "loss": 0.8097, |
| "mean_token_accuracy": 0.8093906044960022, |
| "step": 212 |
| }, |
| { |
| "epoch": 1.7899159663865545, |
| "grad_norm": 1.7882219588273116, |
| "learning_rate": 4.8199793303833135e-06, |
| "loss": 0.8145, |
| "mean_token_accuracy": 0.807731568813324, |
| "step": 213 |
| }, |
| { |
| "epoch": 1.7983193277310925, |
| "grad_norm": 1.8477432032889956, |
| "learning_rate": 4.776477337362394e-06, |
| "loss": 0.801, |
| "mean_token_accuracy": 0.8072378635406494, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.8067226890756303, |
| "grad_norm": 1.7882807024631573, |
| "learning_rate": 4.733044645158214e-06, |
| "loss": 0.8694, |
| "mean_token_accuracy": 0.7961673736572266, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.815126050420168, |
| "grad_norm": 1.7813429615618168, |
| "learning_rate": 4.689685413863052e-06, |
| "loss": 0.7709, |
| "mean_token_accuracy": 0.8158525228500366, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.8235294117647058, |
| "grad_norm": 1.7685865694472525, |
| "learning_rate": 4.646403796532916e-06, |
| "loss": 0.8273, |
| "mean_token_accuracy": 0.8055749535560608, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.8319327731092439, |
| "grad_norm": 1.765292271683428, |
| "learning_rate": 4.603203938789757e-06, |
| "loss": 0.6773, |
| "mean_token_accuracy": 0.8375442624092102, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.8403361344537816, |
| "grad_norm": 1.8827516407913738, |
| "learning_rate": 4.560089978424384e-06, |
| "loss": 0.685, |
| "mean_token_accuracy": 0.8397190570831299, |
| "step": 219 |
| }, |
| { |
| "epoch": 1.8487394957983194, |
| "grad_norm": 1.894159185774351, |
| "learning_rate": 4.517066045000142e-06, |
| "loss": 0.7897, |
| "mean_token_accuracy": 0.8115262389183044, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.8571428571428572, |
| "grad_norm": 1.8084889223361214, |
| "learning_rate": 4.4741362594573686e-06, |
| "loss": 0.7753, |
| "mean_token_accuracy": 0.8194411993026733, |
| "step": 221 |
| }, |
| { |
| "epoch": 1.865546218487395, |
| "grad_norm": 1.7599399933691897, |
| "learning_rate": 4.43130473371868e-06, |
| "loss": 0.7357, |
| "mean_token_accuracy": 0.8300382494926453, |
| "step": 222 |
| }, |
| { |
| "epoch": 1.8739495798319328, |
| "grad_norm": 1.9796797707154894, |
| "learning_rate": 4.388575570295123e-06, |
| "loss": 0.9223, |
| "mean_token_accuracy": 0.7812479734420776, |
| "step": 223 |
| }, |
| { |
| "epoch": 1.8823529411764706, |
| "grad_norm": 1.6759722598102358, |
| "learning_rate": 4.345952861893225e-06, |
| "loss": 0.7815, |
| "mean_token_accuracy": 0.8141289353370667, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.8907563025210083, |
| "grad_norm": 1.9173489384782079, |
| "learning_rate": 4.303440691022982e-06, |
| "loss": 0.7538, |
| "mean_token_accuracy": 0.8243086338043213, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.8991596638655461, |
| "grad_norm": 1.8207386221911352, |
| "learning_rate": 4.261043129606832e-06, |
| "loss": 0.8646, |
| "mean_token_accuracy": 0.7935149073600769, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.907563025210084, |
| "grad_norm": 1.7872281900341995, |
| "learning_rate": 4.218764238589629e-06, |
| "loss": 0.7669, |
| "mean_token_accuracy": 0.8217418193817139, |
| "step": 227 |
| }, |
| { |
| "epoch": 1.9159663865546217, |
| "grad_norm": 1.788744931311787, |
| "learning_rate": 4.176608067549677e-06, |
| "loss": 0.8866, |
| "mean_token_accuracy": 0.7902339696884155, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.9243697478991597, |
| "grad_norm": 1.8110709612539386, |
| "learning_rate": 4.134578654310854e-06, |
| "loss": 0.7914, |
| "mean_token_accuracy": 0.8136367201805115, |
| "step": 229 |
| }, |
| { |
| "epoch": 1.9327731092436975, |
| "grad_norm": 1.8112670191684481, |
| "learning_rate": 4.092680024555862e-06, |
| "loss": 0.8218, |
| "mean_token_accuracy": 0.8051120638847351, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.9411764705882353, |
| "grad_norm": 1.7458590334496111, |
| "learning_rate": 4.0509161914406244e-06, |
| "loss": 0.8198, |
| "mean_token_accuracy": 0.8071305155754089, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.949579831932773, |
| "grad_norm": 1.8175887274370786, |
| "learning_rate": 4.009291155209909e-06, |
| "loss": 0.7585, |
| "mean_token_accuracy": 0.8226490616798401, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.957983193277311, |
| "grad_norm": 1.8094467781021035, |
| "learning_rate": 3.9678089028141704e-06, |
| "loss": 0.7939, |
| "mean_token_accuracy": 0.817867636680603, |
| "step": 233 |
| }, |
| { |
| "epoch": 1.9663865546218489, |
| "grad_norm": 1.7690996396224505, |
| "learning_rate": 3.926473407527665e-06, |
| "loss": 0.7872, |
| "mean_token_accuracy": 0.8126543760299683, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.9747899159663866, |
| "grad_norm": 1.7966623405063749, |
| "learning_rate": 3.8852886285678896e-06, |
| "loss": 0.73, |
| "mean_token_accuracy": 0.8237267732620239, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.9831932773109244, |
| "grad_norm": 1.8277505004778425, |
| "learning_rate": 3.8442585107163496e-06, |
| "loss": 0.814, |
| "mean_token_accuracy": 0.8057609796524048, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.9915966386554622, |
| "grad_norm": 1.8613824843405602, |
| "learning_rate": 3.803386983940722e-06, |
| "loss": 0.8278, |
| "mean_token_accuracy": 0.8035258650779724, |
| "step": 237 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.9832090535001756, |
| "learning_rate": 3.762677963018433e-06, |
| "loss": 0.6424, |
| "mean_token_accuracy": 0.8467904329299927, |
| "step": 238 |
| }, |
| { |
| "epoch": 2.008403361344538, |
| "grad_norm": 3.3844194174357805, |
| "learning_rate": 3.722135347161693e-06, |
| "loss": 0.5364, |
| "mean_token_accuracy": 0.8735464215278625, |
| "step": 239 |
| }, |
| { |
| "epoch": 2.0168067226890756, |
| "grad_norm": 2.960796922058979, |
| "learning_rate": 3.681763019644009e-06, |
| "loss": 0.5647, |
| "mean_token_accuracy": 0.8627821803092957, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.0252100840336134, |
| "grad_norm": 2.73404749939346, |
| "learning_rate": 3.641564847428254e-06, |
| "loss": 0.4946, |
| "mean_token_accuracy": 0.8812078237533569, |
| "step": 241 |
| }, |
| { |
| "epoch": 2.033613445378151, |
| "grad_norm": 2.276716264454592, |
| "learning_rate": 3.6015446807962597e-06, |
| "loss": 0.4616, |
| "mean_token_accuracy": 0.8877162337303162, |
| "step": 242 |
| }, |
| { |
| "epoch": 2.042016806722689, |
| "grad_norm": 1.8253957145676258, |
| "learning_rate": 3.5617063529800467e-06, |
| "loss": 0.496, |
| "mean_token_accuracy": 0.8811616897583008, |
| "step": 243 |
| }, |
| { |
| "epoch": 2.0504201680672267, |
| "grad_norm": 1.7915842293074373, |
| "learning_rate": 3.5220536797946447e-06, |
| "loss": 0.4918, |
| "mean_token_accuracy": 0.8797276616096497, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0588235294117645, |
| "grad_norm": 2.546532003908193, |
| "learning_rate": 3.4825904592726266e-06, |
| "loss": 0.4841, |
| "mean_token_accuracy": 0.8803112506866455, |
| "step": 245 |
| }, |
| { |
| "epoch": 2.0672268907563027, |
| "grad_norm": 3.478981600558786, |
| "learning_rate": 3.44332047130031e-06, |
| "loss": 0.5142, |
| "mean_token_accuracy": 0.8750914335250854, |
| "step": 246 |
| }, |
| { |
| "epoch": 2.0756302521008405, |
| "grad_norm": 2.5707840642456103, |
| "learning_rate": 3.4042474772557143e-06, |
| "loss": 0.4965, |
| "mean_token_accuracy": 0.876130998134613, |
| "step": 247 |
| }, |
| { |
| "epoch": 2.0840336134453783, |
| "grad_norm": 3.1381820065412027, |
| "learning_rate": 3.3653752196482864e-06, |
| "loss": 0.5625, |
| "mean_token_accuracy": 0.8635848760604858, |
| "step": 248 |
| }, |
| { |
| "epoch": 2.092436974789916, |
| "grad_norm": 2.599264595056195, |
| "learning_rate": 3.3267074217604344e-06, |
| "loss": 0.4363, |
| "mean_token_accuracy": 0.8929134011268616, |
| "step": 249 |
| }, |
| { |
| "epoch": 2.100840336134454, |
| "grad_norm": 2.6170150441013, |
| "learning_rate": 3.2882477872908965e-06, |
| "loss": 0.4978, |
| "mean_token_accuracy": 0.8795924186706543, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.1092436974789917, |
| "grad_norm": 4.701829999902318, |
| "learning_rate": 3.2500000000000015e-06, |
| "loss": 0.4867, |
| "mean_token_accuracy": 0.8780362606048584, |
| "step": 251 |
| }, |
| { |
| "epoch": 2.1176470588235294, |
| "grad_norm": 2.3010791433576583, |
| "learning_rate": 3.2119677233568213e-06, |
| "loss": 0.4875, |
| "mean_token_accuracy": 0.8787326812744141, |
| "step": 252 |
| }, |
| { |
| "epoch": 2.1260504201680672, |
| "grad_norm": 2.988123689093377, |
| "learning_rate": 3.1741546001882773e-06, |
| "loss": 0.4386, |
| "mean_token_accuracy": 0.8922126889228821, |
| "step": 253 |
| }, |
| { |
| "epoch": 2.134453781512605, |
| "grad_norm": 1.8808088041609694, |
| "learning_rate": 3.1365642523302214e-06, |
| "loss": 0.4819, |
| "mean_token_accuracy": 0.881823718547821, |
| "step": 254 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 1.8516453219973752, |
| "learning_rate": 3.099200280280529e-06, |
| "loss": 0.532, |
| "mean_token_accuracy": 0.8674002885818481, |
| "step": 255 |
| }, |
| { |
| "epoch": 2.1512605042016806, |
| "grad_norm": 1.8121229898589075, |
| "learning_rate": 3.0620662628542256e-06, |
| "loss": 0.5078, |
| "mean_token_accuracy": 0.8735317587852478, |
| "step": 256 |
| }, |
| { |
| "epoch": 2.1596638655462184, |
| "grad_norm": 2.0979951074315366, |
| "learning_rate": 3.0251657568407134e-06, |
| "loss": 0.5357, |
| "mean_token_accuracy": 0.867943286895752, |
| "step": 257 |
| }, |
| { |
| "epoch": 2.168067226890756, |
| "grad_norm": 1.7941659597404156, |
| "learning_rate": 2.9885022966630812e-06, |
| "loss": 0.535, |
| "mean_token_accuracy": 0.8686414361000061, |
| "step": 258 |
| }, |
| { |
| "epoch": 2.176470588235294, |
| "grad_norm": 1.8274634030738992, |
| "learning_rate": 2.9520793940395735e-06, |
| "loss": 0.4964, |
| "mean_token_accuracy": 0.8770714402198792, |
| "step": 259 |
| }, |
| { |
| "epoch": 2.184873949579832, |
| "grad_norm": 1.7677515796991008, |
| "learning_rate": 2.9159005376472294e-06, |
| "loss": 0.4821, |
| "mean_token_accuracy": 0.8821917772293091, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.19327731092437, |
| "grad_norm": 1.7394663644514425, |
| "learning_rate": 2.879969192787727e-06, |
| "loss": 0.5063, |
| "mean_token_accuracy": 0.8776208758354187, |
| "step": 261 |
| }, |
| { |
| "epoch": 2.2016806722689077, |
| "grad_norm": 1.7434272641018915, |
| "learning_rate": 2.8442888010554658e-06, |
| "loss": 0.4933, |
| "mean_token_accuracy": 0.8733060359954834, |
| "step": 262 |
| }, |
| { |
| "epoch": 2.2100840336134455, |
| "grad_norm": 1.8237732843940058, |
| "learning_rate": 2.8088627800079282e-06, |
| "loss": 0.5022, |
| "mean_token_accuracy": 0.8763316869735718, |
| "step": 263 |
| }, |
| { |
| "epoch": 2.2184873949579833, |
| "grad_norm": 1.7684491855815565, |
| "learning_rate": 2.773694522838333e-06, |
| "loss": 0.5956, |
| "mean_token_accuracy": 0.8532027006149292, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.226890756302521, |
| "grad_norm": 1.698245931367799, |
| "learning_rate": 2.7387873980506286e-06, |
| "loss": 0.5113, |
| "mean_token_accuracy": 0.8779188394546509, |
| "step": 265 |
| }, |
| { |
| "epoch": 2.235294117647059, |
| "grad_norm": 1.7603718021061416, |
| "learning_rate": 2.7041447491368455e-06, |
| "loss": 0.4722, |
| "mean_token_accuracy": 0.8837765455245972, |
| "step": 266 |
| }, |
| { |
| "epoch": 2.2436974789915967, |
| "grad_norm": 1.7942983338768146, |
| "learning_rate": 2.6697698942568552e-06, |
| "loss": 0.5117, |
| "mean_token_accuracy": 0.8737485408782959, |
| "step": 267 |
| }, |
| { |
| "epoch": 2.2521008403361344, |
| "grad_norm": 1.7621204272017936, |
| "learning_rate": 2.6356661259205396e-06, |
| "loss": 0.495, |
| "mean_token_accuracy": 0.8756034970283508, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.2605042016806722, |
| "grad_norm": 1.7768174505264556, |
| "learning_rate": 2.601836710672435e-06, |
| "loss": 0.4538, |
| "mean_token_accuracy": 0.8886755108833313, |
| "step": 269 |
| }, |
| { |
| "epoch": 2.26890756302521, |
| "grad_norm": 1.8376489221725794, |
| "learning_rate": 2.568284888778849e-06, |
| "loss": 0.5373, |
| "mean_token_accuracy": 0.8677133321762085, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.277310924369748, |
| "grad_norm": 1.7356483601315353, |
| "learning_rate": 2.535013873917501e-06, |
| "loss": 0.4766, |
| "mean_token_accuracy": 0.8781722187995911, |
| "step": 271 |
| }, |
| { |
| "epoch": 2.2857142857142856, |
| "grad_norm": 1.8378248814183524, |
| "learning_rate": 2.5020268528697067e-06, |
| "loss": 0.5831, |
| "mean_token_accuracy": 0.8570009469985962, |
| "step": 272 |
| }, |
| { |
| "epoch": 2.2941176470588234, |
| "grad_norm": 1.7493303613971574, |
| "learning_rate": 2.469326985215146e-06, |
| "loss": 0.5094, |
| "mean_token_accuracy": 0.8769955635070801, |
| "step": 273 |
| }, |
| { |
| "epoch": 2.302521008403361, |
| "grad_norm": 1.7748047104815001, |
| "learning_rate": 2.436917403029219e-06, |
| "loss": 0.5089, |
| "mean_token_accuracy": 0.8757727742195129, |
| "step": 274 |
| }, |
| { |
| "epoch": 2.310924369747899, |
| "grad_norm": 1.7897596864764491, |
| "learning_rate": 2.404801210583059e-06, |
| "loss": 0.5097, |
| "mean_token_accuracy": 0.8774615526199341, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.3193277310924367, |
| "grad_norm": 1.7651576671680917, |
| "learning_rate": 2.3729814840461944e-06, |
| "loss": 0.494, |
| "mean_token_accuracy": 0.8773323893547058, |
| "step": 276 |
| }, |
| { |
| "epoch": 2.327731092436975, |
| "grad_norm": 1.740295851487235, |
| "learning_rate": 2.341461271191903e-06, |
| "loss": 0.4865, |
| "mean_token_accuracy": 0.8756646513938904, |
| "step": 277 |
| }, |
| { |
| "epoch": 2.3361344537815127, |
| "grad_norm": 1.8654150960642903, |
| "learning_rate": 2.3102435911052915e-06, |
| "loss": 0.5036, |
| "mean_token_accuracy": 0.8760148286819458, |
| "step": 278 |
| }, |
| { |
| "epoch": 2.3445378151260505, |
| "grad_norm": 1.7800155124407253, |
| "learning_rate": 2.279331433894118e-06, |
| "loss": 0.546, |
| "mean_token_accuracy": 0.8608104586601257, |
| "step": 279 |
| }, |
| { |
| "epoch": 2.3529411764705883, |
| "grad_norm": 1.768664170523609, |
| "learning_rate": 2.248727760402391e-06, |
| "loss": 0.4948, |
| "mean_token_accuracy": 0.8780577182769775, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.361344537815126, |
| "grad_norm": 1.770469552181129, |
| "learning_rate": 2.2184355019267766e-06, |
| "loss": 0.4778, |
| "mean_token_accuracy": 0.8816194534301758, |
| "step": 281 |
| }, |
| { |
| "epoch": 2.369747899159664, |
| "grad_norm": 1.6852781922022526, |
| "learning_rate": 2.1884575599358276e-06, |
| "loss": 0.4861, |
| "mean_token_accuracy": 0.8807989358901978, |
| "step": 282 |
| }, |
| { |
| "epoch": 2.3781512605042017, |
| "grad_norm": 1.744755572820875, |
| "learning_rate": 2.158796805792076e-06, |
| "loss": 0.4576, |
| "mean_token_accuracy": 0.887958288192749, |
| "step": 283 |
| }, |
| { |
| "epoch": 2.3865546218487395, |
| "grad_norm": 1.7018336172367803, |
| "learning_rate": 2.1294560804770066e-06, |
| "loss": 0.5494, |
| "mean_token_accuracy": 0.8622578978538513, |
| "step": 284 |
| }, |
| { |
| "epoch": 2.3949579831932772, |
| "grad_norm": 1.7837096796158942, |
| "learning_rate": 2.1004381943189347e-06, |
| "loss": 0.4585, |
| "mean_token_accuracy": 0.8856400847434998, |
| "step": 285 |
| }, |
| { |
| "epoch": 2.403361344537815, |
| "grad_norm": 1.8096225018522962, |
| "learning_rate": 2.071745926723836e-06, |
| "loss": 0.4728, |
| "mean_token_accuracy": 0.8849493861198425, |
| "step": 286 |
| }, |
| { |
| "epoch": 2.411764705882353, |
| "grad_norm": 1.7226922737142318, |
| "learning_rate": 2.043382025909121e-06, |
| "loss": 0.4401, |
| "mean_token_accuracy": 0.8929994702339172, |
| "step": 287 |
| }, |
| { |
| "epoch": 2.4201680672268906, |
| "grad_norm": 1.7381932608091253, |
| "learning_rate": 2.015349208640406e-06, |
| "loss": 0.4559, |
| "mean_token_accuracy": 0.8868588805198669, |
| "step": 288 |
| }, |
| { |
| "epoch": 2.4285714285714284, |
| "grad_norm": 1.785216301732934, |
| "learning_rate": 1.9876501599712933e-06, |
| "loss": 0.537, |
| "mean_token_accuracy": 0.8654530048370361, |
| "step": 289 |
| }, |
| { |
| "epoch": 2.4369747899159666, |
| "grad_norm": 1.676413871744692, |
| "learning_rate": 1.9602875329861943e-06, |
| "loss": 0.4562, |
| "mean_token_accuracy": 0.8863703012466431, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.4453781512605044, |
| "grad_norm": 1.7379682976536965, |
| "learning_rate": 1.9332639485462006e-06, |
| "loss": 0.4977, |
| "mean_token_accuracy": 0.8756354451179504, |
| "step": 291 |
| }, |
| { |
| "epoch": 2.453781512605042, |
| "grad_norm": 1.789857023158383, |
| "learning_rate": 1.9065819950380634e-06, |
| "loss": 0.4762, |
| "mean_token_accuracy": 0.8814483284950256, |
| "step": 292 |
| }, |
| { |
| "epoch": 2.46218487394958, |
| "grad_norm": 1.6577735082283171, |
| "learning_rate": 1.880244228126264e-06, |
| "loss": 0.4476, |
| "mean_token_accuracy": 0.8910816311836243, |
| "step": 293 |
| }, |
| { |
| "epoch": 2.4705882352941178, |
| "grad_norm": 1.6927936102476582, |
| "learning_rate": 1.8542531705082275e-06, |
| "loss": 0.4893, |
| "mean_token_accuracy": 0.8814150094985962, |
| "step": 294 |
| }, |
| { |
| "epoch": 2.4789915966386555, |
| "grad_norm": 1.8054159398941678, |
| "learning_rate": 1.8286113116726928e-06, |
| "loss": 0.5264, |
| "mean_token_accuracy": 0.8734607100486755, |
| "step": 295 |
| }, |
| { |
| "epoch": 2.4873949579831933, |
| "grad_norm": 1.8000374925757012, |
| "learning_rate": 1.803321107661264e-06, |
| "loss": 0.5714, |
| "mean_token_accuracy": 0.8573963046073914, |
| "step": 296 |
| }, |
| { |
| "epoch": 2.495798319327731, |
| "grad_norm": 1.749129571326899, |
| "learning_rate": 1.7783849808331585e-06, |
| "loss": 0.488, |
| "mean_token_accuracy": 0.882330060005188, |
| "step": 297 |
| }, |
| { |
| "epoch": 2.504201680672269, |
| "grad_norm": 1.7434863893866612, |
| "learning_rate": 1.7538053196331988e-06, |
| "loss": 0.4528, |
| "mean_token_accuracy": 0.8885789513587952, |
| "step": 298 |
| }, |
| { |
| "epoch": 2.5126050420168067, |
| "grad_norm": 1.8268657961411574, |
| "learning_rate": 1.729584478363031e-06, |
| "loss": 0.5059, |
| "mean_token_accuracy": 0.8760490417480469, |
| "step": 299 |
| }, |
| { |
| "epoch": 2.5210084033613445, |
| "grad_norm": 1.7966988339135452, |
| "learning_rate": 1.705724776955629e-06, |
| "loss": 0.5497, |
| "mean_token_accuracy": 0.8659508228302002, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.5294117647058822, |
| "grad_norm": 1.6853755248345623, |
| "learning_rate": 1.682228500753083e-06, |
| "loss": 0.4493, |
| "mean_token_accuracy": 0.8905779719352722, |
| "step": 301 |
| }, |
| { |
| "epoch": 2.53781512605042, |
| "grad_norm": 1.7040165346823453, |
| "learning_rate": 1.6590979002877076e-06, |
| "loss": 0.4613, |
| "mean_token_accuracy": 0.8883019089698792, |
| "step": 302 |
| }, |
| { |
| "epoch": 2.546218487394958, |
| "grad_norm": 1.6968001110057345, |
| "learning_rate": 1.636335191066473e-06, |
| "loss": 0.4533, |
| "mean_token_accuracy": 0.8894676566123962, |
| "step": 303 |
| }, |
| { |
| "epoch": 2.5546218487394956, |
| "grad_norm": 1.8088482407470852, |
| "learning_rate": 1.6139425533588055e-06, |
| "loss": 0.4755, |
| "mean_token_accuracy": 0.8818231821060181, |
| "step": 304 |
| }, |
| { |
| "epoch": 2.5630252100840334, |
| "grad_norm": 1.8080423623957333, |
| "learning_rate": 1.591922131987753e-06, |
| "loss": 0.5279, |
| "mean_token_accuracy": 0.8711415529251099, |
| "step": 305 |
| }, |
| { |
| "epoch": 2.571428571428571, |
| "grad_norm": 1.6807675642589819, |
| "learning_rate": 1.5702760361245472e-06, |
| "loss": 0.5431, |
| "mean_token_accuracy": 0.8634845614433289, |
| "step": 306 |
| }, |
| { |
| "epoch": 2.5798319327731094, |
| "grad_norm": 1.7843878630443717, |
| "learning_rate": 1.5490063390865845e-06, |
| "loss": 0.5302, |
| "mean_token_accuracy": 0.87076336145401, |
| "step": 307 |
| }, |
| { |
| "epoch": 2.588235294117647, |
| "grad_norm": 1.8299228807610584, |
| "learning_rate": 1.5281150781388362e-06, |
| "loss": 0.4958, |
| "mean_token_accuracy": 0.879771888256073, |
| "step": 308 |
| }, |
| { |
| "epoch": 2.596638655462185, |
| "grad_norm": 1.7345499313976294, |
| "learning_rate": 1.507604254298714e-06, |
| "loss": 0.4688, |
| "mean_token_accuracy": 0.8848387002944946, |
| "step": 309 |
| }, |
| { |
| "epoch": 2.6050420168067228, |
| "grad_norm": 1.7440085831923724, |
| "learning_rate": 1.4874758321444091e-06, |
| "loss": 0.5557, |
| "mean_token_accuracy": 0.8678417205810547, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.6134453781512605, |
| "grad_norm": 1.7622118867050525, |
| "learning_rate": 1.467731739626721e-06, |
| "loss": 0.4711, |
| "mean_token_accuracy": 0.8795005679130554, |
| "step": 311 |
| }, |
| { |
| "epoch": 2.6218487394957983, |
| "grad_norm": 1.7408285994608907, |
| "learning_rate": 1.44837386788439e-06, |
| "loss": 0.4393, |
| "mean_token_accuracy": 0.89531010389328, |
| "step": 312 |
| }, |
| { |
| "epoch": 2.630252100840336, |
| "grad_norm": 1.6936183271117475, |
| "learning_rate": 1.4294040710629617e-06, |
| "loss": 0.5008, |
| "mean_token_accuracy": 0.8742570877075195, |
| "step": 313 |
| }, |
| { |
| "epoch": 2.638655462184874, |
| "grad_norm": 1.7686735948043326, |
| "learning_rate": 1.410824166137193e-06, |
| "loss": 0.5115, |
| "mean_token_accuracy": 0.8729111552238464, |
| "step": 314 |
| }, |
| { |
| "epoch": 2.6470588235294117, |
| "grad_norm": 1.6467546945232723, |
| "learning_rate": 1.392635932737012e-06, |
| "loss": 0.4889, |
| "mean_token_accuracy": 0.876711368560791, |
| "step": 315 |
| }, |
| { |
| "epoch": 2.6554621848739495, |
| "grad_norm": 1.732864583611146, |
| "learning_rate": 1.3748411129770703e-06, |
| "loss": 0.5009, |
| "mean_token_accuracy": 0.8752124905586243, |
| "step": 316 |
| }, |
| { |
| "epoch": 2.6638655462184873, |
| "grad_norm": 1.7439183506320681, |
| "learning_rate": 1.3574414112898707e-06, |
| "loss": 0.4682, |
| "mean_token_accuracy": 0.8827528953552246, |
| "step": 317 |
| }, |
| { |
| "epoch": 2.6722689075630255, |
| "grad_norm": 1.8227721928870744, |
| "learning_rate": 1.3404384942625152e-06, |
| "loss": 0.5204, |
| "mean_token_accuracy": 0.8724432587623596, |
| "step": 318 |
| }, |
| { |
| "epoch": 2.6806722689075633, |
| "grad_norm": 1.7373528828791687, |
| "learning_rate": 1.323833990477076e-06, |
| "loss": 0.4701, |
| "mean_token_accuracy": 0.8856019973754883, |
| "step": 319 |
| }, |
| { |
| "epoch": 2.689075630252101, |
| "grad_norm": 1.7468852153995695, |
| "learning_rate": 1.3076294903546057e-06, |
| "loss": 0.5016, |
| "mean_token_accuracy": 0.8778213858604431, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.697478991596639, |
| "grad_norm": 1.817280481287246, |
| "learning_rate": 1.2918265460027988e-06, |
| "loss": 0.4422, |
| "mean_token_accuracy": 0.893291711807251, |
| "step": 321 |
| }, |
| { |
| "epoch": 2.7058823529411766, |
| "grad_norm": 1.6954515135011916, |
| "learning_rate": 1.2764266710673335e-06, |
| "loss": 0.4258, |
| "mean_token_accuracy": 0.8955129981040955, |
| "step": 322 |
| }, |
| { |
| "epoch": 2.7142857142857144, |
| "grad_norm": 1.7738375580958614, |
| "learning_rate": 1.261431340586886e-06, |
| "loss": 0.536, |
| "mean_token_accuracy": 0.866767942905426, |
| "step": 323 |
| }, |
| { |
| "epoch": 2.722689075630252, |
| "grad_norm": 1.7778545981105411, |
| "learning_rate": 1.2468419908518489e-06, |
| "loss": 0.5557, |
| "mean_token_accuracy": 0.863368809223175, |
| "step": 324 |
| }, |
| { |
| "epoch": 2.73109243697479, |
| "grad_norm": 1.7511974755151039, |
| "learning_rate": 1.2326600192667612e-06, |
| "loss": 0.569, |
| "mean_token_accuracy": 0.8578982949256897, |
| "step": 325 |
| }, |
| { |
| "epoch": 2.7394957983193278, |
| "grad_norm": 1.7650614934750701, |
| "learning_rate": 1.2188867842164597e-06, |
| "loss": 0.4642, |
| "mean_token_accuracy": 0.8880206346511841, |
| "step": 326 |
| }, |
| { |
| "epoch": 2.7478991596638656, |
| "grad_norm": 1.7295018909117994, |
| "learning_rate": 1.2055236049359689e-06, |
| "loss": 0.4866, |
| "mean_token_accuracy": 0.8756598830223083, |
| "step": 327 |
| }, |
| { |
| "epoch": 2.7563025210084033, |
| "grad_norm": 1.715068147392596, |
| "learning_rate": 1.1925717613841432e-06, |
| "loss": 0.5014, |
| "mean_token_accuracy": 0.8752623200416565, |
| "step": 328 |
| }, |
| { |
| "epoch": 2.764705882352941, |
| "grad_norm": 1.7238361196149397, |
| "learning_rate": 1.1800324941210686e-06, |
| "loss": 0.4965, |
| "mean_token_accuracy": 0.8757110834121704, |
| "step": 329 |
| }, |
| { |
| "epoch": 2.773109243697479, |
| "grad_norm": 1.833231298436174, |
| "learning_rate": 1.1679070041892387e-06, |
| "loss": 0.4842, |
| "mean_token_accuracy": 0.8799470067024231, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.7815126050420167, |
| "grad_norm": 1.740678169112491, |
| "learning_rate": 1.1561964529985143e-06, |
| "loss": 0.4907, |
| "mean_token_accuracy": 0.8828567266464233, |
| "step": 331 |
| }, |
| { |
| "epoch": 2.7899159663865545, |
| "grad_norm": 1.8309652165832162, |
| "learning_rate": 1.1449019622148842e-06, |
| "loss": 0.5389, |
| "mean_token_accuracy": 0.869530975818634, |
| "step": 332 |
| }, |
| { |
| "epoch": 2.7983193277310923, |
| "grad_norm": 1.894304195634988, |
| "learning_rate": 1.134024613653025e-06, |
| "loss": 0.566, |
| "mean_token_accuracy": 0.8650041818618774, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.80672268907563, |
| "grad_norm": 1.761316482336543, |
| "learning_rate": 1.1235654491726853e-06, |
| "loss": 0.529, |
| "mean_token_accuracy": 0.868781566619873, |
| "step": 334 |
| }, |
| { |
| "epoch": 2.815126050420168, |
| "grad_norm": 1.8000544542443722, |
| "learning_rate": 1.1135254705788933e-06, |
| "loss": 0.5494, |
| "mean_token_accuracy": 0.8643285036087036, |
| "step": 335 |
| }, |
| { |
| "epoch": 2.8235294117647056, |
| "grad_norm": 1.7905406066253629, |
| "learning_rate": 1.1039056395259991e-06, |
| "loss": 0.5052, |
| "mean_token_accuracy": 0.8782471418380737, |
| "step": 336 |
| }, |
| { |
| "epoch": 2.831932773109244, |
| "grad_norm": 1.7722042771606428, |
| "learning_rate": 1.0947068774255675e-06, |
| "loss": 0.4977, |
| "mean_token_accuracy": 0.875531017780304, |
| "step": 337 |
| }, |
| { |
| "epoch": 2.8403361344537816, |
| "grad_norm": 1.9973830902031495, |
| "learning_rate": 1.085930065358124e-06, |
| "loss": 0.4324, |
| "mean_token_accuracy": 0.8934433460235596, |
| "step": 338 |
| }, |
| { |
| "epoch": 2.8487394957983194, |
| "grad_norm": 1.6896484708992687, |
| "learning_rate": 1.0775760439887567e-06, |
| "loss": 0.4953, |
| "mean_token_accuracy": 0.8801694512367249, |
| "step": 339 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 1.7595624086770811, |
| "learning_rate": 1.0696456134866027e-06, |
| "loss": 0.5703, |
| "mean_token_accuracy": 0.8666946291923523, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.865546218487395, |
| "grad_norm": 1.7324834152474125, |
| "learning_rate": 1.0621395334482023e-06, |
| "loss": 0.501, |
| "mean_token_accuracy": 0.8782939910888672, |
| "step": 341 |
| }, |
| { |
| "epoch": 2.8739495798319328, |
| "grad_norm": 1.7494633234405406, |
| "learning_rate": 1.055058522824742e-06, |
| "loss": 0.5414, |
| "mean_token_accuracy": 0.867946207523346, |
| "step": 342 |
| }, |
| { |
| "epoch": 2.8823529411764706, |
| "grad_norm": 1.7043979501327688, |
| "learning_rate": 1.0484032598531933e-06, |
| "loss": 0.4072, |
| "mean_token_accuracy": 0.9014019966125488, |
| "step": 343 |
| }, |
| { |
| "epoch": 2.8907563025210083, |
| "grad_norm": 1.7718012344425826, |
| "learning_rate": 1.042174381991349e-06, |
| "loss": 0.4649, |
| "mean_token_accuracy": 0.8876906037330627, |
| "step": 344 |
| }, |
| { |
| "epoch": 2.899159663865546, |
| "grad_norm": 1.8014581956296338, |
| "learning_rate": 1.0363724858567655e-06, |
| "loss": 0.5118, |
| "mean_token_accuracy": 0.8747749924659729, |
| "step": 345 |
| }, |
| { |
| "epoch": 2.907563025210084, |
| "grad_norm": 1.7277581616143525, |
| "learning_rate": 1.0309981271696186e-06, |
| "loss": 0.497, |
| "mean_token_accuracy": 0.8768202066421509, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.9159663865546217, |
| "grad_norm": 1.6173184552284654, |
| "learning_rate": 1.0260518206994732e-06, |
| "loss": 0.5029, |
| "mean_token_accuracy": 0.8765256404876709, |
| "step": 347 |
| }, |
| { |
| "epoch": 2.92436974789916, |
| "grad_norm": 1.8049758496648165, |
| "learning_rate": 1.021534040215978e-06, |
| "loss": 0.5257, |
| "mean_token_accuracy": 0.8693103790283203, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.9327731092436977, |
| "grad_norm": 1.7473323800131928, |
| "learning_rate": 1.0174452184434888e-06, |
| "loss": 0.4879, |
| "mean_token_accuracy": 0.8786296844482422, |
| "step": 349 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 1.744414604472958, |
| "learning_rate": 1.0137857470196177e-06, |
| "loss": 0.4312, |
| "mean_token_accuracy": 0.8908872008323669, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.9495798319327733, |
| "grad_norm": 1.7551567310461849, |
| "learning_rate": 1.0105559764577236e-06, |
| "loss": 0.462, |
| "mean_token_accuracy": 0.8851808309555054, |
| "step": 351 |
| }, |
| { |
| "epoch": 2.957983193277311, |
| "grad_norm": 1.696209846178712, |
| "learning_rate": 1.0077562161133376e-06, |
| "loss": 0.4247, |
| "mean_token_accuracy": 0.896420955657959, |
| "step": 352 |
| }, |
| { |
| "epoch": 2.966386554621849, |
| "grad_norm": 1.7889797242427938, |
| "learning_rate": 1.005386734154534e-06, |
| "loss": 0.4947, |
| "mean_token_accuracy": 0.8767175078392029, |
| "step": 353 |
| }, |
| { |
| "epoch": 2.9747899159663866, |
| "grad_norm": 1.7759605744443523, |
| "learning_rate": 1.0034477575362412e-06, |
| "loss": 0.455, |
| "mean_token_accuracy": 0.8875412344932556, |
| "step": 354 |
| }, |
| { |
| "epoch": 2.9831932773109244, |
| "grad_norm": 1.7992397002954914, |
| "learning_rate": 1.0019394719785073e-06, |
| "loss": 0.4586, |
| "mean_token_accuracy": 0.8864205479621887, |
| "step": 355 |
| }, |
| { |
| "epoch": 2.991596638655462, |
| "grad_norm": 1.7245167657524767, |
| "learning_rate": 1.000862021948709e-06, |
| "loss": 0.4852, |
| "mean_token_accuracy": 0.8800389766693115, |
| "step": 356 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.5906696719690108, |
| "learning_rate": 1.0002155106477152e-06, |
| "loss": 0.4201, |
| "mean_token_accuracy": 0.8944628834724426, |
| "step": 357 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 357, |
| "total_flos": 21584411688960.0, |
| "train_loss": 0.9353465321017247, |
| "train_runtime": 6466.1821, |
| "train_samples_per_second": 7.014, |
| "train_steps_per_second": 0.055 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 357, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 21584411688960.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
