| { |
| "best_metric": 0.5050536394119263, |
| "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-600", |
| "epoch": 1.6842105263157894, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 0.7795, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 0.6789, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 0.6844, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 0.688, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 4.9999999999999996e-05, |
| "loss": 0.5958, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.6578, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 7e-05, |
| "loss": 0.6253, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 7.999999999999999e-05, |
| "loss": 0.6859, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.5348, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.596, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00010999999999999998, |
| "loss": 0.7, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.6234, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00013, |
| "loss": 0.555, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00014, |
| "loss": 0.5407, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00015, |
| "loss": 0.5553, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00015999999999999999, |
| "loss": 0.6885, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00016999999999999999, |
| "loss": 0.8918, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.684, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00018999999999999998, |
| "loss": 0.4785, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.5874, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 0.949, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00021999999999999995, |
| "loss": 0.8723, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00023, |
| "loss": 0.6717, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.6587, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00025, |
| "loss": 0.6596, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "eval_loss": 0.6079516410827637, |
| "eval_runtime": 26.3492, |
| "eval_samples_per_second": 7.59, |
| "eval_steps_per_second": 1.898, |
| "step": 25 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4494464054372671, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5370370370370371, |
| "dharma_eval_accuracy_ARC-Easy": 0.5740740740740741, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.45901639344262296, |
| "dharma_eval_accuracy_openbookqa": 0.35185185185185186, |
| "dharma_eval_accuracy_truthful_qa": 0.42592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.35185185185185186, |
| "dharma_loss": 2.3114946393966673, |
| "epoch": 0.07, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00026, |
| "loss": 0.5686, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00027, |
| "loss": 0.5699, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00028, |
| "loss": 0.4459, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00029, |
| "loss": 0.5475, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.0003, |
| "loss": 0.8182, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999992132854894, |
| "loss": 0.9174, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999968531502098, |
| "loss": 0.6544, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999929196189179, |
| "loss": 0.469, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00029998741273287477, |
| "loss": 0.6049, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0002999803325498448, |
| "loss": 0.6272, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0002999716791440959, |
| "loss": 0.6724, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00029996145260639806, |
| "loss": 0.7526, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.000299949653044023, |
| "loss": 0.5716, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00029993628058074245, |
| "loss": 0.4348, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00029992133535682725, |
| "loss": 0.7696, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00029990481752904563, |
| "loss": 0.7793, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002998867272706619, |
| "loss": 0.7342, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002998670647714343, |
| "loss": 0.5625, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00029984583023761317, |
| "loss": 0.5429, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029982302389193856, |
| "loss": 0.5458, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029979864597363845, |
| "loss": 0.4912, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.0002997726967384255, |
| "loss": 0.4761, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029974517645849503, |
| "loss": 0.6447, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002997160854225217, |
| "loss": 0.5931, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002996854239356567, |
| "loss": 0.5849, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_loss": 0.5564016699790955, |
| "eval_runtime": 26.3069, |
| "eval_samples_per_second": 7.603, |
| "eval_steps_per_second": 1.901, |
| "step": 50 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4336321131727263, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6111111111111112, |
| "dharma_eval_accuracy_ARC-Easy": 0.6666666666666666, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4262295081967213, |
| "dharma_eval_accuracy_openbookqa": 0.3333333333333333, |
| "dharma_eval_accuracy_truthful_qa": 0.48148148148148145, |
| "dharma_eval_accuracy_winogrande": 0.018518518518518517, |
| "dharma_loss": 2.094249272108078, |
| "epoch": 0.14, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00029965319231952455, |
| "loss": 0.6124, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002996193909122197, |
| "loss": 0.8966, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00029958402006830274, |
| "loss": 0.5725, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002995470801587973, |
| "loss": 0.622, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002995085715711854, |
| "loss": 0.5536, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002994684947094039, |
| "loss": 0.6182, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002994268499938403, |
| "loss": 0.6519, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00029938363786132774, |
| "loss": 0.5926, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029933885876514115, |
| "loss": 0.5578, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0002992925131749921, |
| "loss": 0.6589, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029924460157702376, |
| "loss": 0.5214, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029919512447380625, |
| "loss": 0.528, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0002991440823843309, |
| "loss": 0.6204, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0002990914758440051, |
| "loss": 0.6508, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00029903730540464666, |
| "loss": 0.512, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00029898157163447763, |
| "loss": 0.5887, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002989242751181191, |
| "loss": 0.6152, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002988654164565843, |
| "loss": 0.5389, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002988049962672728, |
| "loss": 0.4564, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029874301518396376, |
| "loss": 0.5451, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029867947385680936, |
| "loss": 0.6155, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0002986143729523282, |
| "loss": 0.5607, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029854771315339785, |
| "loss": 0.5281, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00029847949515924806, |
| "loss": 0.6095, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002984097196854534, |
| "loss": 0.5144, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 0.5410553216934204, |
| "eval_runtime": 26.3067, |
| "eval_samples_per_second": 7.603, |
| "eval_steps_per_second": 1.901, |
| "step": 75 |
| }, |
| { |
| "dharma_eval_accuracy": 0.45737899302160984, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6111111111111112, |
| "dharma_eval_accuracy_ARC-Easy": 0.6296296296296297, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.2037037037037037, |
| "dharma_eval_accuracy_truthful_qa": 0.37037037037037035, |
| "dharma_eval_accuracy_winogrande": 0.4074074074074074, |
| "dharma_loss": 2.42759256362915, |
| "epoch": 0.21, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002983383874639254, |
| "loss": 0.5234, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029826549924290557, |
| "loss": 0.6432, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029819105578695655, |
| "loss": 0.6061, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029811505787695524, |
| "loss": 0.5164, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029803750631008356, |
| "loss": 0.5481, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0002979584018998209, |
| "loss": 0.6353, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.000297877745475935, |
| "loss": 0.6274, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00029779553788447357, |
| "loss": 0.4919, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029771177998775536, |
| "loss": 0.5519, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0002976264726643611, |
| "loss": 0.5474, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029753961680912427, |
| "loss": 0.4565, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029745121333312163, |
| "loss": 0.5196, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002973612631636638, |
| "loss": 0.6924, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002972697672442856, |
| "loss": 0.552, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002971767265347358, |
| "loss": 0.7085, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00029708214201096755, |
| "loss": 0.637, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002969860146651276, |
| "loss": 0.785, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00029688834550554646, |
| "loss": 0.6269, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002967891355567273, |
| "loss": 0.6203, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00029668838585933556, |
| "loss": 0.5873, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0002965860974701879, |
| "loss": 0.593, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0002964822714622412, |
| "loss": 0.6257, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.000296376908924581, |
| "loss": 0.5547, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029627001096241057, |
| "loss": 0.548, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0002961615786970389, |
| "loss": 0.6886, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_loss": 0.5314058065414429, |
| "eval_runtime": 26.2979, |
| "eval_samples_per_second": 7.605, |
| "eval_steps_per_second": 1.901, |
| "step": 100 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3599742498201947, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6111111111111112, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.6851851851851852, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.2786885245901639, |
| "dharma_eval_accuracy_openbookqa": 0.1111111111111111, |
| "dharma_eval_accuracy_truthful_qa": 0.3148148148148148, |
| "dharma_eval_accuracy_winogrande": 0.037037037037037035, |
| "dharma_loss": 2.093293779850006, |
| "epoch": 0.28, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029605161326586916, |
| "loss": 0.5676, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002959401158223867, |
| "loss": 0.5588, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002958270875361469, |
| "loss": 0.7629, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002957125295927631, |
| "loss": 0.4804, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002955964431938939, |
| "loss": 0.6908, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0002954788295572305, |
| "loss": 0.7137, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029535968991648454, |
| "loss": 0.5269, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029523902552137433, |
| "loss": 0.5083, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0002951168376376124, |
| "loss": 0.7371, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0002949931275468917, |
| "loss": 0.4403, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00029486789654687253, |
| "loss": 0.5357, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00029474114595116896, |
| "loss": 0.6105, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00029461287708933473, |
| "loss": 0.587, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0002944830913068494, |
| "loss": 0.5673, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00029435178996510455, |
| "loss": 0.5928, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00029421897444138897, |
| "loss": 0.5244, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0002940846461288748, |
| "loss": 0.8121, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0002939488064366024, |
| "loss": 0.657, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00029381145678946584, |
| "loss": 0.6476, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00029367259862819804, |
| "loss": 0.7678, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002935322334093553, |
| "loss": 0.5754, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002933903626053024, |
| "loss": 0.3601, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00029324698770419685, |
| "loss": 0.5252, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002931021102099737, |
| "loss": 0.5425, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002929557316423291, |
| "loss": 0.7067, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 0.541481614112854, |
| "eval_runtime": 26.3113, |
| "eval_samples_per_second": 7.601, |
| "eval_steps_per_second": 1.9, |
| "step": 125 |
| }, |
| { |
| "dharma_eval_accuracy": 0.23540432470382144, |
| "dharma_eval_accuracy_ARC-Challenge": 0.3888888888888889, |
| "dharma_eval_accuracy_ARC-Easy": 0.4074074074074074, |
| "dharma_eval_accuracy_BoolQ": 0.0, |
| "dharma_eval_accuracy_MMLU": 0.3148148148148148, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.21311475409836064, |
| "dharma_eval_accuracy_openbookqa": 0.18518518518518517, |
| "dharma_eval_accuracy_truthful_qa": 0.37037037037037035, |
| "dharma_eval_accuracy_winogrande": 0.018518518518518517, |
| "dharma_loss": 2.240182936668396, |
| "epoch": 0.35, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00029280785353670514, |
| "loss": 0.583, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029265847744427303, |
| "loss": 0.8091, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029250760493191734, |
| "loss": 0.5991, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0002923552375822194, |
| "loss": 0.6537, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029220137699344055, |
| "loss": 0.7498, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00029204602477950556, |
| "loss": 0.694, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00029188918256998564, |
| "loss": 0.4471, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0002917308520100814, |
| "loss": 0.5525, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00029157103476060544, |
| "loss": 0.5435, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002914097324979651, |
| "loss": 0.4856, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002912469469141448, |
| "loss": 0.4508, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002910826797166882, |
| "loss": 0.6151, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00029091693262868067, |
| "loss": 0.7316, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002907497073887305, |
| "loss": 0.6147, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002905810057509515, |
| "loss": 0.7862, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029041082948494395, |
| "loss": 0.5832, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029023918037577635, |
| "loss": 0.5931, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029006606022396667, |
| "loss": 0.5275, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028989147084546333, |
| "loss": 0.747, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00028971541407162634, |
| "loss": 0.6066, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0002895378917492079, |
| "loss": 0.5402, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0002893589057403332, |
| "loss": 0.5637, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002891784579224808, |
| "loss": 1.1186, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00028899655018846295, |
| "loss": 0.5726, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002888131844464056, |
| "loss": 0.5567, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "eval_loss": 0.5340408086776733, |
| "eval_runtime": 26.3247, |
| "eval_samples_per_second": 7.597, |
| "eval_steps_per_second": 1.899, |
| "step": 150 |
| }, |
| { |
| "dharma_eval_accuracy": 0.36184662634911163, |
| "dharma_eval_accuracy_ARC-Challenge": 0.35185185185185186, |
| "dharma_eval_accuracy_ARC-Easy": 0.46296296296296297, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.2962962962962963, |
| "dharma_eval_accuracy_agieval": 0.1694915254237288, |
| "dharma_eval_accuracy_bigbench": 0.32786885245901637, |
| "dharma_eval_accuracy_openbookqa": 0.2222222222222222, |
| "dharma_eval_accuracy_truthful_qa": 0.5, |
| "dharma_eval_accuracy_winogrande": 0.2222222222222222, |
| "dharma_loss": 2.382638945579529, |
| "epoch": 0.42, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002886283626197287, |
| "loss": 0.6543, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00028844208664712575, |
| "loss": 0.5019, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0002882543584825435, |
| "loss": 0.4576, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00028806518009516155, |
| "loss": 0.7125, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002878745534693718, |
| "loss": 0.5933, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00028768248060475726, |
| "loss": 0.4112, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002874889635160714, |
| "loss": 0.5444, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002872940042332169, |
| "loss": 0.5717, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002870976048012244, |
| "loss": 0.5591, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.000286899767280231, |
| "loss": 0.6188, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002867004937454587, |
| "loss": 0.4811, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00028649978628719254, |
| "loss": 0.7187, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00028629764701075885, |
| "loss": 0.5985, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002860940780365029, |
| "loss": 0.3944, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.000285889081499767, |
| "loss": 0.6205, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00028568265955086774, |
| "loss": 0.6127, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002854748143550738, |
| "loss": 0.4686, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00028526554809258275, |
| "loss": 0.5284, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002850548629584988, |
| "loss": 0.6021, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028484276116280926, |
| "loss": 0.5461, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028462924493036164, |
| "loss": 0.5331, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028441431650084016, |
| "loss": 0.4928, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028419797812874237, |
| "loss": 0.444, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028398023208335533, |
| "loss": 0.4402, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028376108064873215, |
| "loss": 0.534, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "eval_loss": 0.5252656936645508, |
| "eval_runtime": 26.3152, |
| "eval_samples_per_second": 7.6, |
| "eval_steps_per_second": 1.9, |
| "step": 175 |
| }, |
| { |
| "dharma_eval_accuracy": 0.37138631329919036, |
| "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593, |
| "dharma_eval_accuracy_ARC-Easy": 0.5, |
| "dharma_eval_accuracy_BoolQ": 0.48148148148148145, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.288135593220339, |
| "dharma_eval_accuracy_bigbench": 0.29508196721311475, |
| "dharma_eval_accuracy_openbookqa": 0.14814814814814814, |
| "dharma_eval_accuracy_truthful_qa": 0.42592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.35185185185185186, |
| "dharma_loss": 2.167125677585602, |
| "epoch": 0.49, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028354052612366757, |
| "loss": 0.7301, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0002833185708216743, |
| "loss": 0.6828, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0002830952170709583, |
| "loss": 0.511, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00028287046721439484, |
| "loss": 0.5656, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00028264432360950353, |
| "loss": 0.6779, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002824167886284237, |
| "loss": 0.4952, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002821878646578898, |
| "loss": 0.7256, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002819575540992058, |
| "loss": 0.6188, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028172585936822055, |
| "loss": 0.6328, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028149278289530213, |
| "loss": 0.5524, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028125832712531246, |
| "loss": 0.6724, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002810224945175816, |
| "loss": 0.6166, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028078528754588205, |
| "loss": 0.5626, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028054670869840265, |
| "loss": 0.5691, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028030676047772265, |
| "loss": 0.4432, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00028006544540078534, |
| "loss": 0.7124, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0002798227659988717, |
| "loss": 0.7267, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00027957872481757374, |
| "loss": 0.6314, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00027933332441676807, |
| "loss": 0.5728, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0002790865673705888, |
| "loss": 0.4405, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00027883845626740044, |
| "loss": 0.5227, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0002785889937097712, |
| "loss": 0.4894, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027833818231444516, |
| "loss": 0.6226, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027808602471231524, |
| "loss": 0.5867, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002778325235483954, |
| "loss": 0.5393, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 0.5206255316734314, |
| "eval_runtime": 26.2955, |
| "eval_samples_per_second": 7.606, |
| "eval_steps_per_second": 1.901, |
| "step": 200 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4415195350331654, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5740740740740741, |
| "dharma_eval_accuracy_ARC-Easy": 0.48148148148148145, |
| "dharma_eval_accuracy_BoolQ": 0.7962962962962963, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.29508196721311475, |
| "dharma_eval_accuracy_openbookqa": 0.25925925925925924, |
| "dharma_eval_accuracy_truthful_qa": 0.5, |
| "dharma_eval_accuracy_winogrande": 0.37037037037037035, |
| "dharma_loss": 2.4329242930412294, |
| "epoch": 0.56, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027757768148179275, |
| "loss": 0.4509, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027732150118568017, |
| "loss": 0.562, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027706398534726757, |
| "loss": 0.4544, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027680513666777435, |
| "loss": 0.4827, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027654495786240066, |
| "loss": 0.4569, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027628345166029906, |
| "loss": 0.5267, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027602062080454577, |
| "loss": 0.6012, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.0002757564680521122, |
| "loss": 0.5415, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0002754909961738357, |
| "loss": 0.6135, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00027522420795439065, |
| "loss": 0.7098, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0002749561061922592, |
| "loss": 0.5442, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00027468669369970207, |
| "loss": 0.5521, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002744159733027287, |
| "loss": 0.6381, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002741439478410681, |
| "loss": 0.6088, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002738706201681384, |
| "loss": 0.6892, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00027359599315101787, |
| "loss": 0.5922, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00027332006967041366, |
| "loss": 0.618, |
| "step": 217 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002730428526206327, |
| "loss": 0.4905, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002727643449095507, |
| "loss": 0.7306, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002724845494585816, |
| "loss": 0.605, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002722034692026474, |
| "loss": 0.7353, |
| "step": 221 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00027192110709014697, |
| "loss": 0.5488, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002716374660829252, |
| "loss": 0.5709, |
| "step": 223 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002713525491562421, |
| "loss": 0.6261, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00027106635929874135, |
| "loss": 0.6109, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.63, |
| "eval_loss": 0.5185112357139587, |
| "eval_runtime": 26.3526, |
| "eval_samples_per_second": 7.589, |
| "eval_steps_per_second": 1.897, |
| "step": 225 |
| }, |
| { |
| "dharma_eval_accuracy": 0.43693206960781283, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.6296296296296297, |
| "dharma_eval_accuracy_BoolQ": 0.7592592592592593, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.32786885245901637, |
| "dharma_eval_accuracy_openbookqa": 0.1111111111111111, |
| "dharma_eval_accuracy_truthful_qa": 0.3888888888888889, |
| "dharma_eval_accuracy_winogrande": 0.4444444444444444, |
| "dharma_loss": 2.3577894673347473, |
| "epoch": 0.63, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002707788995124192, |
| "loss": 0.6372, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00027049017281259276, |
| "loss": 0.5911, |
| "step": 227 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.0002702001822278685, |
| "loss": 0.411, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00026990893080011035, |
| "loss": 0.5805, |
| "step": 229 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002696164215844081, |
| "loss": 0.5452, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00026932265764904493, |
| "loss": 0.5327, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002690276420754655, |
| "loss": 0.4257, |
| "step": 232 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002687313779582436, |
| "loss": 0.5536, |
| "step": 233 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.0002684338684050497, |
| "loss": 0.6901, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00026813511653661816, |
| "loss": 0.5755, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.0002678351254867147, |
| "loss": 0.5879, |
| "step": 236 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002675338984021035, |
| "loss": 0.2712, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00026723143844251416, |
| "loss": 0.6444, |
| "step": 238 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002669277487806085, |
| "loss": 0.4874, |
| "step": 239 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002666228326019474, |
| "loss": 0.5012, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002663166931049572, |
| "loss": 0.5705, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00026600933350089654, |
| "loss": 0.5436, |
| "step": 242 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00026570075701382213, |
| "loss": 0.7598, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002653909668805553, |
| "loss": 0.6408, |
| "step": 244 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00026507996635064787, |
| "loss": 0.5418, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0002647677586863484, |
| "loss": 0.612, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0002644543471625675, |
| "loss": 0.6403, |
| "step": 247 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00026413973506684364, |
| "loss": 0.5907, |
| "step": 248 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.000263823925699309, |
| "loss": 0.5865, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00026350692237265427, |
| "loss": 0.5661, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 0.5193732976913452, |
| "eval_runtime": 26.3567, |
| "eval_samples_per_second": 7.588, |
| "eval_steps_per_second": 1.897, |
| "step": 250 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3625658476234253, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5, |
| "dharma_eval_accuracy_ARC-Easy": 0.42592592592592593, |
| "dharma_eval_accuracy_BoolQ": 0.7777777777777778, |
| "dharma_eval_accuracy_MMLU": 0.46296296296296297, |
| "dharma_eval_accuracy_agieval": 0.23728813559322035, |
| "dharma_eval_accuracy_bigbench": 0.22950819672131148, |
| "dharma_eval_accuracy_openbookqa": 0.09259259259259259, |
| "dharma_eval_accuracy_truthful_qa": 0.48148148148148145, |
| "dharma_eval_accuracy_winogrande": 0.05555555555555555, |
| "dharma_loss": 2.5813710255622864, |
| "epoch": 0.7, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00026318872841209445, |
| "loss": 0.3614, |
| "step": 251 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.0002628693471553335, |
| "loss": 0.5204, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00026254878195252983, |
| "loss": 0.4298, |
| "step": 253 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00026222703616626055, |
| "loss": 0.4459, |
| "step": 254 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026190411317148686, |
| "loss": 0.5273, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026158001635551815, |
| "loss": 0.622, |
| "step": 256 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026125474911797657, |
| "loss": 0.6702, |
| "step": 257 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0002609283148707616, |
| "loss": 0.5812, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.000260600717038014, |
| "loss": 0.886, |
| "step": 259 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00026027195905608006, |
| "loss": 0.4844, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00025994204437347537, |
| "loss": 0.5818, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025961097645084885, |
| "loss": 0.629, |
| "step": 262 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0002592787587609465, |
| "loss": 0.423, |
| "step": 263 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025894539478857445, |
| "loss": 0.6513, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025861088803056325, |
| "loss": 0.4615, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0002582752419957303, |
| "loss": 0.4516, |
| "step": 266 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0002579384602048438, |
| "loss": 0.5692, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00025760054619058535, |
| "loss": 0.6714, |
| "step": 268 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00025726150349751305, |
| "loss": 0.533, |
| "step": 269 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002569213356820244, |
| "loss": 0.6656, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002565800463123187, |
| "loss": 0.6265, |
| "step": 271 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002562376389683599, |
| "loss": 0.5127, |
| "step": 272 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00025589411724183923, |
| "loss": 0.5243, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002555494847361369, |
| "loss": 0.5455, |
| "step": 274 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002552037450662849, |
| "loss": 0.5457, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.77, |
| "eval_loss": 0.5239390730857849, |
| "eval_runtime": 26.3626, |
| "eval_samples_per_second": 7.587, |
| "eval_steps_per_second": 1.897, |
| "step": 275 |
| }, |
| { |
| "dharma_eval_accuracy": 0.46902203058234054, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.5555555555555556, |
| "dharma_eval_accuracy_BoolQ": 0.7222222222222222, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.23728813559322035, |
| "dharma_eval_accuracy_bigbench": 0.4098360655737705, |
| "dharma_eval_accuracy_openbookqa": 0.25925925925925924, |
| "dharma_eval_accuracy_truthful_qa": 0.6481481481481481, |
| "dharma_eval_accuracy_winogrande": 0.3888888888888889, |
| "dharma_loss": 2.3993593831062316, |
| "epoch": 0.77, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002548569018589286, |
| "loss": 0.5044, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002545089587522893, |
| "loss": 0.672, |
| "step": 277 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002541599193961254, |
| "loss": 0.5391, |
| "step": 278 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002538097874516947, |
| "loss": 0.5886, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025345856659171563, |
| "loss": 0.4727, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0002531062605003287, |
| "loss": 0.4911, |
| "step": 281 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025275287287305814, |
| "loss": 0.4916, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025239840741677304, |
| "loss": 0.4675, |
| "step": 283 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025204286784964817, |
| "loss": 0.8109, |
| "step": 284 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025168625790112547, |
| "loss": 0.4635, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025132858131187444, |
| "loss": 0.549, |
| "step": 286 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00025096984183375334, |
| "loss": 0.5386, |
| "step": 287 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002506100432297695, |
| "loss": 0.5898, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00025024918927404004, |
| "loss": 0.6002, |
| "step": 289 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00024988728375175214, |
| "loss": 0.5995, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024952433045912354, |
| "loss": 0.4781, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024916033320336264, |
| "loss": 0.6746, |
| "step": 292 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024879529580262817, |
| "loss": 0.5565, |
| "step": 293 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00024842922208598994, |
| "loss": 0.6523, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.0002480621158933879, |
| "loss": 0.5657, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00024769398107559224, |
| "loss": 0.5042, |
| "step": 296 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.0002473248214941632, |
| "loss": 0.5771, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024695464102141, |
| "loss": 0.4739, |
| "step": 298 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0002465834435403506, |
| "loss": 0.4495, |
| "step": 299 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024621123294467096, |
| "loss": 0.5886, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_loss": 0.515432596206665, |
| "eval_runtime": 26.3157, |
| "eval_samples_per_second": 7.6, |
| "eval_steps_per_second": 1.9, |
| "step": 300 |
| }, |
| { |
| "dharma_eval_accuracy": 0.478252989799407, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.45901639344262296, |
| "dharma_eval_accuracy_openbookqa": 0.2777777777777778, |
| "dharma_eval_accuracy_truthful_qa": 0.5740740740740741, |
| "dharma_eval_accuracy_winogrande": 0.5, |
| "dharma_loss": 2.5394882402420045, |
| "epoch": 0.84, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024583801313868416, |
| "loss": 0.4195, |
| "step": 301 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0002454637880372892, |
| "loss": 0.4727, |
| "step": 302 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0002450885615659305, |
| "loss": 0.4463, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00024471233766055605, |
| "loss": 0.6394, |
| "step": 304 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024433512026757664, |
| "loss": 0.6439, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024395691334382427, |
| "loss": 0.5627, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024357772085651055, |
| "loss": 0.4879, |
| "step": 307 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024319754678318528, |
| "loss": 0.4786, |
| "step": 308 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00024281639511169456, |
| "loss": 0.393, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0002424342698401391, |
| "loss": 0.7039, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00024205117497683209, |
| "loss": 0.5914, |
| "step": 311 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002416671145402575, |
| "loss": 0.595, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002412820925590275, |
| "loss": 0.758, |
| "step": 313 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00024089611307184048, |
| "loss": 0.4295, |
| "step": 314 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002405091801274387, |
| "loss": 0.4564, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00024012129778456552, |
| "loss": 0.5362, |
| "step": 316 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00023973247011192325, |
| "loss": 0.6515, |
| "step": 317 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0002393427011881302, |
| "loss": 0.7295, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0002389519951016779, |
| "loss": 0.751, |
| "step": 319 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023856035595088839, |
| "loss": 0.895, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023816778784387094, |
| "loss": 0.6754, |
| "step": 321 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023777429489847934, |
| "loss": 0.6156, |
| "step": 322 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002373798812422683, |
| "loss": 0.4012, |
| "step": 323 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002369845510124505, |
| "loss": 0.3156, |
| "step": 324 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002365883083558529, |
| "loss": 0.5232, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.91, |
| "eval_loss": 0.5132270455360413, |
| "eval_runtime": 26.337, |
| "eval_samples_per_second": 7.594, |
| "eval_steps_per_second": 1.898, |
| "step": 325 |
| }, |
| { |
| "dharma_eval_accuracy": 0.38590223393100737, |
| "dharma_eval_accuracy_ARC-Challenge": 0.46296296296296297, |
| "dharma_eval_accuracy_ARC-Easy": 0.4444444444444444, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.3114754098360656, |
| "dharma_eval_accuracy_openbookqa": 0.2777777777777778, |
| "dharma_eval_accuracy_truthful_qa": 0.5555555555555556, |
| "dharma_eval_accuracy_winogrande": 0.037037037037037035, |
| "dharma_loss": 2.2708842940330505, |
| "epoch": 0.91, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023619115742887356, |
| "loss": 0.3488, |
| "step": 326 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023579310239743773, |
| "loss": 0.5628, |
| "step": 327 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023539414743695437, |
| "loss": 0.4697, |
| "step": 328 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023499429673227222, |
| "loss": 0.6077, |
| "step": 329 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00023459355447763596, |
| "loss": 0.5314, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00023419192487664217, |
| "loss": 0.5117, |
| "step": 331 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002337894121421954, |
| "loss": 0.4915, |
| "step": 332 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002333860204964637, |
| "loss": 0.5615, |
| "step": 333 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00023298175417083459, |
| "loss": 0.598, |
| "step": 334 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0002325766174058705, |
| "loss": 0.5588, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0002321706144512644, |
| "loss": 0.4396, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.0002317637495657952, |
| "loss": 0.4851, |
| "step": 337 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.000231356027017283, |
| "loss": 0.5265, |
| "step": 338 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00023094745108254435, |
| "loss": 0.5465, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00023053802604734757, |
| "loss": 0.5982, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00023012775620636746, |
| "loss": 0.5515, |
| "step": 341 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00022971664586314054, |
| "loss": 0.6549, |
| "step": 342 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00022930469933001975, |
| "loss": 0.5104, |
| "step": 343 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022889192092812938, |
| "loss": 0.4687, |
| "step": 344 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0002284783149873195, |
| "loss": 0.6088, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022806388584612066, |
| "loss": 0.6173, |
| "step": 346 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022764863785169854, |
| "loss": 0.5955, |
| "step": 347 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.000227232575359808, |
| "loss": 0.5085, |
| "step": 348 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.0002268157027347478, |
| "loss": 0.3806, |
| "step": 349 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00022639802434931444, |
| "loss": 0.6013, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.98, |
| "eval_loss": 0.511376678943634, |
| "eval_runtime": 26.3778, |
| "eval_samples_per_second": 7.582, |
| "eval_steps_per_second": 1.896, |
| "step": 350 |
| }, |
| { |
| "dharma_eval_accuracy": 0.45162236423697943, |
| "dharma_eval_accuracy_ARC-Challenge": 0.4444444444444444, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7592592592592593, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.3442622950819672, |
| "dharma_eval_accuracy_openbookqa": 0.37037037037037035, |
| "dharma_eval_accuracy_truthful_qa": 0.5370370370370371, |
| "dharma_eval_accuracy_winogrande": 0.48148148148148145, |
| "dharma_loss": 2.6632097277641296, |
| "epoch": 0.98, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.0002259795445847566, |
| "loss": 0.5341, |
| "step": 351 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022556026783072895, |
| "loss": 0.3715, |
| "step": 352 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022514019848524628, |
| "loss": 0.5229, |
| "step": 353 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022471934095463723, |
| "loss": 0.4048, |
| "step": 354 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022429769965349815, |
| "loss": 0.48, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022387527900464673, |
| "loss": 0.4543, |
| "step": 356 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022345208343907576, |
| "loss": 0.579, |
| "step": 357 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022302811739590642, |
| "loss": 0.488, |
| "step": 358 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022260338532234194, |
| "loss": 0.4045, |
| "step": 359 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022217789167362073, |
| "loss": 0.5919, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022175164091296987, |
| "loss": 0.6644, |
| "step": 361 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022132463751155812, |
| "loss": 0.6124, |
| "step": 362 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022089688594844915, |
| "loss": 0.5964, |
| "step": 363 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022046839071055435, |
| "loss": 0.3682, |
| "step": 364 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022003915629258605, |
| "loss": 0.4854, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021960918719701026, |
| "loss": 0.5045, |
| "step": 366 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021917848793399924, |
| "loss": 0.4382, |
| "step": 367 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021874706302138448, |
| "loss": 0.5718, |
| "step": 368 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021831491698460923, |
| "loss": 0.4179, |
| "step": 369 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021788205435668083, |
| "loss": 0.4178, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002174484796781235, |
| "loss": 0.4802, |
| "step": 371 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021701419749693034, |
| "loss": 0.4051, |
| "step": 372 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021657921236851603, |
| "loss": 0.3847, |
| "step": 373 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021614352885566872, |
| "loss": 0.5093, |
| "step": 374 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021570715152850232, |
| "loss": 0.4866, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.05, |
| "eval_loss": 0.5142313838005066, |
| "eval_runtime": 26.3986, |
| "eval_samples_per_second": 7.576, |
| "eval_steps_per_second": 1.894, |
| "step": 375 |
| }, |
| { |
| "dharma_eval_accuracy": 0.44273958129658786, |
| "dharma_eval_accuracy_ARC-Challenge": 0.25925925925925924, |
| "dharma_eval_accuracy_ARC-Easy": 0.35185185185185186, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.2222222222222222, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.37037037037037035, |
| "dharma_eval_accuracy_truthful_qa": 0.7777777777777778, |
| "dharma_eval_accuracy_winogrande": 0.5370370370370371, |
| "dharma_loss": 3.0705994338989258, |
| "epoch": 1.05, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021527008496440846, |
| "loss": 0.6129, |
| "step": 376 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021483233374800862, |
| "loss": 0.5435, |
| "step": 377 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021439390247110588, |
| "loss": 0.3336, |
| "step": 378 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021395479573263688, |
| "loss": 0.6667, |
| "step": 379 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021351501813862356, |
| "loss": 0.479, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021307457430212468, |
| "loss": 0.4249, |
| "step": 381 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021263346884318777, |
| "loss": 0.5989, |
| "step": 382 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021219170638880037, |
| "loss": 0.3444, |
| "step": 383 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021174929157284156, |
| "loss": 0.3373, |
| "step": 384 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021130622903603344, |
| "loss": 0.4317, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.0002108625234258923, |
| "loss": 0.4541, |
| "step": 386 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00021041817939668005, |
| "loss": 0.5544, |
| "step": 387 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020997320160935534, |
| "loss": 0.3578, |
| "step": 388 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020952759473152457, |
| "loss": 0.3263, |
| "step": 389 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020908136343739307, |
| "loss": 0.4524, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020863451240771592, |
| "loss": 0.4767, |
| "step": 391 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020818704632974896, |
| "loss": 0.4093, |
| "step": 392 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020773896989719965, |
| "loss": 0.4865, |
| "step": 393 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00020729028781017777, |
| "loss": 0.4853, |
| "step": 394 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.000206841004775146, |
| "loss": 0.3023, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00020639112550487084, |
| "loss": 0.5841, |
| "step": 396 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.000205940654718373, |
| "loss": 0.5222, |
| "step": 397 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002054895971408778, |
| "loss": 0.4549, |
| "step": 398 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002050379575037658, |
| "loss": 0.4911, |
| "step": 399 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00020458574054452313, |
| "loss": 0.4955, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_loss": 0.5140312910079956, |
| "eval_runtime": 26.3702, |
| "eval_samples_per_second": 7.584, |
| "eval_steps_per_second": 1.896, |
| "step": 400 |
| }, |
| { |
| "dharma_eval_accuracy": 0.42833628911551785, |
| "dharma_eval_accuracy_ARC-Challenge": 0.2777777777777778, |
| "dharma_eval_accuracy_ARC-Easy": 0.4074074074074074, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.24074074074074073, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.25925925925925924, |
| "dharma_eval_accuracy_truthful_qa": 0.6666666666666666, |
| "dharma_eval_accuracy_winogrande": 0.5370370370370371, |
| "dharma_loss": 2.6535617146492005, |
| "epoch": 1.12, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00020413295100669165, |
| "loss": 0.3082, |
| "step": 401 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00020367959363981936, |
| "loss": 0.5595, |
| "step": 402 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.0002032256731994106, |
| "loss": 0.618, |
| "step": 403 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00020277119444687584, |
| "loss": 0.4732, |
| "step": 404 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0002023161621494823, |
| "loss": 0.4542, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.00020186058108030342, |
| "loss": 0.4732, |
| "step": 406 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.00020140445601816897, |
| "loss": 0.4085, |
| "step": 407 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00020094779174761505, |
| "loss": 0.4966, |
| "step": 408 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00020049059305883379, |
| "loss": 0.4264, |
| "step": 409 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.0002000328647476231, |
| "loss": 0.6945, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00019957461161533628, |
| "loss": 0.3748, |
| "step": 411 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00019911583846883197, |
| "loss": 0.4211, |
| "step": 412 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00019865655012042335, |
| "loss": 0.421, |
| "step": 413 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00019819675138782784, |
| "loss": 0.3954, |
| "step": 414 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0001977364470941166, |
| "loss": 0.4557, |
| "step": 415 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.0001972756420676638, |
| "loss": 0.5205, |
| "step": 416 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00019681434114209614, |
| "loss": 0.6422, |
| "step": 417 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.0001963525491562421, |
| "loss": 0.3991, |
| "step": 418 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00019589027095408105, |
| "loss": 0.4185, |
| "step": 419 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.0001954275113846926, |
| "loss": 0.4448, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00019496427530220565, |
| "loss": 0.5212, |
| "step": 421 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.0001945005675657475, |
| "loss": 0.5918, |
| "step": 422 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0001940363930393929, |
| "loss": 0.3506, |
| "step": 423 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00019357175659211298, |
| "loss": 0.6174, |
| "step": 424 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00019310666309772424, |
| "loss": 0.3454, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.19, |
| "eval_loss": 0.5155076384544373, |
| "eval_runtime": 26.4029, |
| "eval_samples_per_second": 7.575, |
| "eval_steps_per_second": 1.894, |
| "step": 425 |
| }, |
| { |
| "dharma_eval_accuracy": 0.46314133898648113, |
| "dharma_eval_accuracy_ARC-Challenge": 0.4074074074074074, |
| "dharma_eval_accuracy_ARC-Easy": 0.5, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.2962962962962963, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.2777777777777778, |
| "dharma_eval_accuracy_truthful_qa": 0.6481481481481481, |
| "dharma_eval_accuracy_winogrande": 0.5555555555555556, |
| "dharma_loss": 2.406665512084961, |
| "epoch": 1.19, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.0001926411174348373, |
| "loss": 0.525, |
| "step": 426 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00019217512448680584, |
| "loss": 0.4988, |
| "step": 427 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.0001917086891416755, |
| "loss": 0.3246, |
| "step": 428 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00019124181629213226, |
| "loss": 0.6274, |
| "step": 429 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0001907745108354514, |
| "loss": 0.8056, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0001903067776734461, |
| "loss": 0.4925, |
| "step": 431 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.00018983862171241577, |
| "loss": 0.5953, |
| "step": 432 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.000189370047863095, |
| "loss": 0.5673, |
| "step": 433 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00018890106104060174, |
| "loss": 0.5765, |
| "step": 434 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0001884316661643858, |
| "loss": 0.453, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00018796186815817743, |
| "loss": 0.4503, |
| "step": 436 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.00018749167194993528, |
| "loss": 0.4895, |
| "step": 437 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0001870210824717951, |
| "loss": 0.432, |
| "step": 438 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0001865501046600179, |
| "loss": 0.3827, |
| "step": 439 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00018607874345493805, |
| "loss": 0.5148, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.0001856070038009115, |
| "loss": 0.5425, |
| "step": 441 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00018513489064626398, |
| "loss": 0.6838, |
| "step": 442 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00018466240894323918, |
| "loss": 0.4326, |
| "step": 443 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00018418956364794653, |
| "loss": 0.4965, |
| "step": 444 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00018371635972030942, |
| "loss": 0.4713, |
| "step": 445 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00018324280212401314, |
| "loss": 0.5163, |
| "step": 446 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00018276889582645277, |
| "loss": 0.3899, |
| "step": 447 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.00018229464579868121, |
| "loss": 0.3494, |
| "step": 448 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.00018182005701535678, |
| "loss": 0.4522, |
| "step": 449 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.00018134513445469127, |
| "loss": 0.4883, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.26, |
| "eval_loss": 0.5140238404273987, |
| "eval_runtime": 26.3956, |
| "eval_samples_per_second": 7.577, |
| "eval_steps_per_second": 1.894, |
| "step": 450 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4671948197773273, |
| "dharma_eval_accuracy_ARC-Challenge": 0.3888888888888889, |
| "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.3148148148148148, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.5245901639344263, |
| "dharma_eval_accuracy_openbookqa": 0.3148148148148148, |
| "dharma_eval_accuracy_truthful_qa": 0.7592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.752000973701477, |
| "epoch": 1.26, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00018086988309839753, |
| "loss": 0.5255, |
| "step": 451 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00018039430793163753, |
| "loss": 0.6, |
| "step": 452 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.0001799184139429696, |
| "loss": 0.214, |
| "step": 453 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00017944220612429662, |
| "loss": 0.4462, |
| "step": 454 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.0001789656894708132, |
| "loss": 0.3911, |
| "step": 455 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00017848886898095352, |
| "loss": 0.5309, |
| "step": 456 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00017801174965633893, |
| "loss": 0.3596, |
| "step": 457 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00017753433650172538, |
| "loss": 0.427, |
| "step": 458 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00017705663452495098, |
| "loss": 0.5063, |
| "step": 459 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00017657864873688343, |
| "loss": 0.5837, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00017610038415136734, |
| "loss": 0.5938, |
| "step": 461 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00017562184578517203, |
| "loss": 0.5135, |
| "step": 462 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00017514303865793848, |
| "loss": 0.3718, |
| "step": 463 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00017466396779212693, |
| "loss": 0.5354, |
| "step": 464 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00017418463821296395, |
| "loss": 0.4169, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00017370505494839012, |
| "loss": 0.383, |
| "step": 466 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00017322522302900696, |
| "loss": 0.6588, |
| "step": 467 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00017274514748802418, |
| "loss": 0.4773, |
| "step": 468 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00017226483336120707, |
| "loss": 0.4327, |
| "step": 469 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00017178428568682353, |
| "loss": 0.5411, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00017130350950559132, |
| "loss": 0.4514, |
| "step": 471 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00017082250986062502, |
| "loss": 0.4935, |
| "step": 472 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00017034129179738328, |
| "loss": 0.4042, |
| "step": 473 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00016985986036361598, |
| "loss": 0.3173, |
| "step": 474 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00016937822060931096, |
| "loss": 0.4456, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.33, |
| "eval_loss": 0.5098786354064941, |
| "eval_runtime": 26.3977, |
| "eval_samples_per_second": 7.576, |
| "eval_steps_per_second": 1.894, |
| "step": 475 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4939437909707429, |
| "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145, |
| "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.35185185185185186, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.5245901639344263, |
| "dharma_eval_accuracy_openbookqa": 0.3148148148148148, |
| "dharma_eval_accuracy_truthful_qa": 0.7407407407407407, |
| "dharma_eval_accuracy_winogrande": 0.5555555555555556, |
| "dharma_loss": 2.942282904624939, |
| "epoch": 1.33, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00016889637758664137, |
| "loss": 0.3904, |
| "step": 476 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.0001684143363499125, |
| "loss": 0.4446, |
| "step": 477 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00016793210195550882, |
| "loss": 0.4849, |
| "step": 478 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00016744967946184097, |
| "loss": 0.4961, |
| "step": 479 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00016696707392929266, |
| "loss": 0.5676, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.0001664842904201674, |
| "loss": 0.4996, |
| "step": 481 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00016600133399863594, |
| "loss": 0.2721, |
| "step": 482 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.00016551820973068255, |
| "loss": 0.3858, |
| "step": 483 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.00016503492268405215, |
| "loss": 0.4972, |
| "step": 484 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.0001645514779281972, |
| "loss": 0.5966, |
| "step": 485 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.00016406788053422445, |
| "loss": 0.3846, |
| "step": 486 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00016358413557484167, |
| "loss": 0.4582, |
| "step": 487 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00016310024812430458, |
| "loss": 0.5007, |
| "step": 488 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00016261622325836362, |
| "loss": 0.3344, |
| "step": 489 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00016213206605421063, |
| "loss": 0.483, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0001616477815904255, |
| "loss": 0.4295, |
| "step": 491 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0001611633749469231, |
| "loss": 0.4847, |
| "step": 492 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0001606788512048999, |
| "loss": 0.3394, |
| "step": 493 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.00016019421544678073, |
| "loss": 0.4139, |
| "step": 494 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.00015970947275616536, |
| "loss": 0.3148, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.00015922462821777524, |
| "loss": 0.4729, |
| "step": 496 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00015873968691740005, |
| "loss": 0.3881, |
| "step": 497 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00015825465394184472, |
| "loss": 0.4628, |
| "step": 498 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00015776953437887553, |
| "loss": 0.5961, |
| "step": 499 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00015728433331716724, |
| "loss": 0.6399, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_loss": 0.50834059715271, |
| "eval_runtime": 26.4232, |
| "eval_samples_per_second": 7.569, |
| "eval_steps_per_second": 1.892, |
| "step": 500 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4811876184170958, |
| "dharma_eval_accuracy_ARC-Challenge": 0.46296296296296297, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.5409836065573771, |
| "dharma_eval_accuracy_openbookqa": 0.2962962962962963, |
| "dharma_eval_accuracy_truthful_qa": 0.6851851851851852, |
| "dharma_eval_accuracy_winogrande": 0.46296296296296297, |
| "dharma_loss": 2.7791563968658446, |
| "epoch": 1.4, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.0001567990558462493, |
| "loss": 0.3633, |
| "step": 501 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.0001563137070564528, |
| "loss": 0.6472, |
| "step": 502 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00015582829203885688, |
| "loss": 0.3952, |
| "step": 503 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00015534281588523534, |
| "loss": 0.3335, |
| "step": 504 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0001548572836880034, |
| "loss": 0.6748, |
| "step": 505 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.00015437170054016395, |
| "loss": 0.5213, |
| "step": 506 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.00015388607153525452, |
| "loss": 0.5454, |
| "step": 507 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00015340040176729347, |
| "loss": 0.605, |
| "step": 508 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.000152914696330727, |
| "loss": 0.5786, |
| "step": 509 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00015242896032037522, |
| "loss": 0.5918, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00015194319883137905, |
| "loss": 0.7016, |
| "step": 511 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0001514574169591466, |
| "loss": 0.3418, |
| "step": 512 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0001509716197992999, |
| "loss": 0.4958, |
| "step": 513 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0001504858124476213, |
| "loss": 0.3953, |
| "step": 514 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00015, |
| "loss": 0.5772, |
| "step": 515 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.0001495141875523787, |
| "loss": 0.4234, |
| "step": 516 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00014902838020070008, |
| "loss": 0.2827, |
| "step": 517 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.0001485425830408534, |
| "loss": 0.4302, |
| "step": 518 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00014805680116862095, |
| "loss": 0.4149, |
| "step": 519 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00014757103967962475, |
| "loss": 0.4118, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00014708530366927297, |
| "loss": 0.3965, |
| "step": 521 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.0001465995982327065, |
| "loss": 0.5043, |
| "step": 522 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.0001461139284647455, |
| "loss": 0.4457, |
| "step": 523 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.00014562829945983607, |
| "loss": 0.5667, |
| "step": 524 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.00014514271631199663, |
| "loss": 0.4982, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.47, |
| "eval_loss": 0.5073952674865723, |
| "eval_runtime": 26.2985, |
| "eval_samples_per_second": 7.605, |
| "eval_steps_per_second": 1.901, |
| "step": 525 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4803106029681313, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.45901639344262296, |
| "dharma_eval_accuracy_openbookqa": 0.3148148148148148, |
| "dharma_eval_accuracy_truthful_qa": 0.5925925925925926, |
| "dharma_eval_accuracy_winogrande": 0.5, |
| "dharma_loss": 2.697408908367157, |
| "epoch": 1.47, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00014465718411476463, |
| "loss": 0.3422, |
| "step": 526 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00014417170796114312, |
| "loss": 0.3436, |
| "step": 527 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0001436862929435472, |
| "loss": 0.3001, |
| "step": 528 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00014320094415375072, |
| "loss": 0.4839, |
| "step": 529 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.0001427156666828328, |
| "loss": 0.3702, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00014223046562112442, |
| "loss": 0.5617, |
| "step": 531 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00014174534605815525, |
| "loss": 0.5076, |
| "step": 532 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00014126031308259992, |
| "loss": 0.5191, |
| "step": 533 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.0001407753717822248, |
| "loss": 0.6035, |
| "step": 534 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00014029052724383464, |
| "loss": 0.4406, |
| "step": 535 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00013980578455321922, |
| "loss": 0.4745, |
| "step": 536 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00013932114879510005, |
| "loss": 0.4057, |
| "step": 537 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.0001388366250530769, |
| "loss": 0.5748, |
| "step": 538 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.0001383522184095745, |
| "loss": 0.6466, |
| "step": 539 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00013786793394578937, |
| "loss": 0.4808, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00013738377674163635, |
| "loss": 0.4348, |
| "step": 541 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.0001368997518756954, |
| "loss": 0.3255, |
| "step": 542 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00013641586442515833, |
| "loss": 0.3578, |
| "step": 543 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00013593211946577555, |
| "loss": 0.4295, |
| "step": 544 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.0001354485220718028, |
| "loss": 0.4566, |
| "step": 545 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00013496507731594783, |
| "loss": 0.5032, |
| "step": 546 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00013448179026931745, |
| "loss": 0.5479, |
| "step": 547 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00013399866600136403, |
| "loss": 0.4946, |
| "step": 548 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00013351570957983257, |
| "loss": 0.5054, |
| "step": 549 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00013303292607070737, |
| "loss": 0.2585, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.54, |
| "eval_loss": 0.5078052282333374, |
| "eval_runtime": 26.3852, |
| "eval_samples_per_second": 7.58, |
| "eval_steps_per_second": 1.895, |
| "step": 550 |
| }, |
| { |
| "dharma_eval_accuracy": 0.46749268486788176, |
| "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.2777777777777778, |
| "dharma_eval_accuracy_truthful_qa": 0.5370370370370371, |
| "dharma_eval_accuracy_winogrande": 0.48148148148148145, |
| "dharma_loss": 2.9045387988090514, |
| "epoch": 1.54, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.000132550320538159, |
| "loss": 0.5333, |
| "step": 551 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.00013206789804449116, |
| "loss": 0.3957, |
| "step": 552 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.0001315856636500875, |
| "loss": 0.5521, |
| "step": 553 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00013110362241335865, |
| "loss": 0.5326, |
| "step": 554 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00013062177939068907, |
| "loss": 0.5668, |
| "step": 555 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00013014013963638408, |
| "loss": 0.3726, |
| "step": 556 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.0001296587082026167, |
| "loss": 0.3974, |
| "step": 557 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.000129177490139375, |
| "loss": 0.3974, |
| "step": 558 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.0001286964904944087, |
| "loss": 0.4792, |
| "step": 559 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.00012821571431317647, |
| "loss": 0.4565, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.0001277351666387929, |
| "loss": 0.3991, |
| "step": 561 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.0001272548525119758, |
| "loss": 0.3742, |
| "step": 562 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.000126774776970993, |
| "loss": 0.3932, |
| "step": 563 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.00012629494505160982, |
| "loss": 0.5469, |
| "step": 564 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00012581536178703603, |
| "loss": 0.2917, |
| "step": 565 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.0001253360322078731, |
| "loss": 0.5076, |
| "step": 566 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00012485696134206147, |
| "loss": 0.4549, |
| "step": 567 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.0001243781542148279, |
| "loss": 0.4924, |
| "step": 568 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.00012389961584863263, |
| "loss": 0.4153, |
| "step": 569 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.0001234213512631166, |
| "loss": 0.5995, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.000122943365475049, |
| "loss": 0.38, |
| "step": 571 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0001224656634982746, |
| "loss": 0.5892, |
| "step": 572 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.00012198825034366104, |
| "loss": 0.3141, |
| "step": 573 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.00012151113101904645, |
| "loss": 0.4494, |
| "step": 574 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0001210343105291868, |
| "loss": 0.4938, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.61, |
| "eval_loss": 0.504688560962677, |
| "eval_runtime": 26.3824, |
| "eval_samples_per_second": 7.581, |
| "eval_steps_per_second": 1.895, |
| "step": 575 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4820703510463012, |
| "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.2962962962962963, |
| "dharma_eval_accuracy_truthful_qa": 0.6481481481481481, |
| "dharma_eval_accuracy_winogrande": 0.5, |
| "dharma_loss": 2.8464001512527464, |
| "epoch": 1.61, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00012055779387570338, |
| "loss": 0.4101, |
| "step": 576 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00012008158605703037, |
| "loss": 0.4743, |
| "step": 577 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00011960569206836249, |
| "loss": 0.5178, |
| "step": 578 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011913011690160246, |
| "loss": 0.5462, |
| "step": 579 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011865486554530873, |
| "loss": 0.3295, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011817994298464319, |
| "loss": 0.4082, |
| "step": 581 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011770535420131876, |
| "loss": 0.495, |
| "step": 582 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011723110417354719, |
| "loss": 0.5554, |
| "step": 583 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011675719787598688, |
| "loss": 0.4386, |
| "step": 584 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011628364027969062, |
| "loss": 0.4684, |
| "step": 585 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00011581043635205352, |
| "loss": 0.3877, |
| "step": 586 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.00011533759105676082, |
| "loss": 0.6039, |
| "step": 587 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.000114865109353736, |
| "loss": 0.4679, |
| "step": 588 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.00011439299619908854, |
| "loss": 0.5623, |
| "step": 589 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00011392125654506198, |
| "loss": 0.4549, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00011344989533998204, |
| "loss": 0.4881, |
| "step": 591 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00011297891752820484, |
| "loss": 0.483, |
| "step": 592 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.0001125083280500647, |
| "loss": 0.6766, |
| "step": 593 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011203813184182255, |
| "loss": 0.4011, |
| "step": 594 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011156833383561413, |
| "loss": 0.5004, |
| "step": 595 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011109893895939823, |
| "loss": 0.4021, |
| "step": 596 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00011062995213690494, |
| "loss": 0.6189, |
| "step": 597 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00011016137828758422, |
| "loss": 0.5078, |
| "step": 598 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.0001096932223265539, |
| "loss": 0.637, |
| "step": 599 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00010922548916454855, |
| "loss": 0.5294, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.68, |
| "eval_loss": 0.5050536394119263, |
| "eval_runtime": 26.3547, |
| "eval_samples_per_second": 7.589, |
| "eval_steps_per_second": 1.897, |
| "step": 600 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4757231375427789, |
| "dharma_eval_accuracy_ARC-Challenge": 0.46296296296296297, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.2962962962962963, |
| "dharma_eval_accuracy_truthful_qa": 0.6111111111111112, |
| "dharma_eval_accuracy_winogrande": 0.48148148148148145, |
| "dharma_loss": 2.8082506337165833, |
| "epoch": 1.68, |
| "step": 600 |
| } |
| ], |
| "max_steps": 1000, |
| "num_train_epochs": 3, |
| "total_flos": 1.9307426648459674e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
