| { |
| "best_metric": 0.5143458843231201, |
| "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-400", |
| "epoch": 1.1228070175438596, |
| "global_step": 400, |
| "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": 0.6847, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 0.6878, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 4.9999999999999996e-05, |
| "loss": 0.5962, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.6581, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 7e-05, |
| "loss": 0.6256, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 7.999999999999999e-05, |
| "loss": 0.6868, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.5345, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.5959, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00010999999999999998, |
| "loss": 0.7002, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.623, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00013, |
| "loss": 0.5554, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00014, |
| "loss": 0.5401, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00015, |
| "loss": 0.5547, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.00015999999999999999, |
| "loss": 0.6882, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00016999999999999999, |
| "loss": 0.8901, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.6838, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00018999999999999998, |
| "loss": 0.4786, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.587, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 0.9494, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00021999999999999995, |
| "loss": 0.8728, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00023, |
| "loss": 0.6719, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.6586, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00025, |
| "loss": 0.6593, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "eval_loss": 0.607403576374054, |
| "eval_runtime": 26.394, |
| "eval_samples_per_second": 7.577, |
| "eval_steps_per_second": 1.894, |
| "step": 25 |
| }, |
| { |
| "dharma_eval_accuracy": 0.45308939268681175, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5370370370370371, |
| "dharma_eval_accuracy_ARC-Easy": 0.5555555555555556, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.3333333333333333, |
| "dharma_eval_accuracy_truthful_qa": 0.42592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.35185185185185186, |
| "dharma_loss": 2.316238456726074, |
| "epoch": 0.07, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00026, |
| "loss": 0.5658, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00027, |
| "loss": 0.5688, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00028, |
| "loss": 0.4466, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00029, |
| "loss": 0.5476, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.0003, |
| "loss": 0.8189, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999992132854894, |
| "loss": 0.9189, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999968531502098, |
| "loss": 0.6546, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.0002999929196189179, |
| "loss": 0.4689, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00029998741273287477, |
| "loss": 0.604, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0002999803325498448, |
| "loss": 0.6302, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0002999716791440959, |
| "loss": 0.6739, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00029996145260639806, |
| "loss": 0.7528, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.000299949653044023, |
| "loss": 0.5713, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00029993628058074245, |
| "loss": 0.4324, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00029992133535682725, |
| "loss": 0.7712, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00029990481752904563, |
| "loss": 0.7824, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002998867272706619, |
| "loss": 0.7353, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002998670647714343, |
| "loss": 0.5625, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00029984583023761317, |
| "loss": 0.5424, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029982302389193856, |
| "loss": 0.5455, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029979864597363845, |
| "loss": 0.4901, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.0002997726967384255, |
| "loss": 0.4773, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00029974517645849503, |
| "loss": 0.6435, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002997160854225217, |
| "loss": 0.5929, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.0002996854239356567, |
| "loss": 0.5866, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_loss": 0.5568216443061829, |
| "eval_runtime": 26.2645, |
| "eval_samples_per_second": 7.615, |
| "eval_steps_per_second": 1.904, |
| "step": 50 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4336321131727263, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5925925925925926, |
| "dharma_eval_accuracy_ARC-Easy": 0.6666666666666666, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4262295081967213, |
| "dharma_eval_accuracy_openbookqa": 0.2777777777777778, |
| "dharma_eval_accuracy_truthful_qa": 0.46296296296296297, |
| "dharma_eval_accuracy_winogrande": 0.07407407407407407, |
| "dharma_loss": 2.1247796120643616, |
| "epoch": 0.14, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00029965319231952455, |
| "loss": 0.6123, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002996193909122197, |
| "loss": 0.8919, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00029958402006830274, |
| "loss": 0.5756, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002995470801587973, |
| "loss": 0.6228, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0002995085715711854, |
| "loss": 0.5568, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002994684947094039, |
| "loss": 0.6196, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002994268499938403, |
| "loss": 0.6517, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00029938363786132774, |
| "loss": 0.5935, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029933885876514115, |
| "loss": 0.5591, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0002992925131749921, |
| "loss": 0.6607, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029924460157702376, |
| "loss": 0.5215, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00029919512447380625, |
| "loss": 0.5303, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0002991440823843309, |
| "loss": 0.6202, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0002990914758440051, |
| "loss": 0.652, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00029903730540464666, |
| "loss": 0.513, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00029898157163447763, |
| "loss": 0.5911, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002989242751181191, |
| "loss": 0.6151, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002988654164565843, |
| "loss": 0.5382, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0002988049962672728, |
| "loss": 0.4576, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029874301518396376, |
| "loss": 0.5454, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029867947385680936, |
| "loss": 0.6165, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0002986143729523282, |
| "loss": 0.5668, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00029854771315339785, |
| "loss": 0.529, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00029847949515924806, |
| "loss": 0.607, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002984097196854534, |
| "loss": 0.5148, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 0.5403281450271606, |
| "eval_runtime": 26.2629, |
| "eval_samples_per_second": 7.615, |
| "eval_steps_per_second": 1.904, |
| "step": 75 |
| }, |
| { |
| "dharma_eval_accuracy": 0.44914854034671264, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5925925925925926, |
| "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.48148148148148145, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4918032786885246, |
| "dharma_eval_accuracy_openbookqa": 0.14814814814814814, |
| "dharma_eval_accuracy_truthful_qa": 0.37037037037037035, |
| "dharma_eval_accuracy_winogrande": 0.3888888888888889, |
| "dharma_loss": 2.383504674911499, |
| "epoch": 0.21, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0002983383874639254, |
| "loss": 0.5237, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029826549924290557, |
| "loss": 0.6427, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029819105578695655, |
| "loss": 0.599, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029811505787695524, |
| "loss": 0.5157, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00029803750631008356, |
| "loss": 0.549, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0002979584018998209, |
| "loss": 0.6365, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.000297877745475935, |
| "loss": 0.6266, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00029779553788447357, |
| "loss": 0.4927, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029771177998775536, |
| "loss": 0.5505, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.0002976264726643611, |
| "loss": 0.5477, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029753961680912427, |
| "loss": 0.4543, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029745121333312163, |
| "loss": 0.5124, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002973612631636638, |
| "loss": 0.6943, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002972697672442856, |
| "loss": 0.5516, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0002971767265347358, |
| "loss": 0.7085, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00029708214201096755, |
| "loss": 0.6372, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002969860146651276, |
| "loss": 0.7821, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00029688834550554646, |
| "loss": 0.6261, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002967891355567273, |
| "loss": 0.6183, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00029668838585933556, |
| "loss": 0.5842, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0002965860974701879, |
| "loss": 0.5885, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0002964822714622412, |
| "loss": 0.6271, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.000296376908924581, |
| "loss": 0.5535, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029627001096241057, |
| "loss": 0.5465, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0002961615786970389, |
| "loss": 0.6853, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_loss": 0.5313628315925598, |
| "eval_runtime": 26.2771, |
| "eval_samples_per_second": 7.611, |
| "eval_steps_per_second": 1.903, |
| "step": 100 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3661470893263675, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.6851851851851852, |
| "dharma_eval_accuracy_MMLU": 0.46296296296296297, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.2786885245901639, |
| "dharma_eval_accuracy_openbookqa": 0.1111111111111111, |
| "dharma_eval_accuracy_truthful_qa": 0.3333333333333333, |
| "dharma_eval_accuracy_winogrande": 0.037037037037037035, |
| "dharma_loss": 2.1082235522270203, |
| "epoch": 0.28, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029605161326586916, |
| "loss": 0.5665, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002959401158223867, |
| "loss": 0.553, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002958270875361469, |
| "loss": 0.753, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002957125295927631, |
| "loss": 0.4767, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.0002955964431938939, |
| "loss": 0.6908, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0002954788295572305, |
| "loss": 0.7143, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029535968991648454, |
| "loss": 0.5282, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029523902552137433, |
| "loss": 0.511, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0002951168376376124, |
| "loss": 0.735, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.0002949931275468917, |
| "loss": 0.4398, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00029486789654687253, |
| "loss": 0.5353, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00029474114595116896, |
| "loss": 0.6276, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00029461287708933473, |
| "loss": 0.5891, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0002944830913068494, |
| "loss": 0.5658, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00029435178996510455, |
| "loss": 0.5942, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00029421897444138897, |
| "loss": 0.5236, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0002940846461288748, |
| "loss": 0.81, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0002939488064366024, |
| "loss": 0.6618, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00029381145678946584, |
| "loss": 0.6485, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00029367259862819804, |
| "loss": 0.812, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002935322334093553, |
| "loss": 0.5752, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002933903626053024, |
| "loss": 0.362, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00029324698770419685, |
| "loss": 0.525, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002931021102099737, |
| "loss": 0.5478, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002929557316423291, |
| "loss": 0.7068, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 0.5387007594108582, |
| "eval_runtime": 26.2871, |
| "eval_samples_per_second": 7.608, |
| "eval_steps_per_second": 1.902, |
| "step": 125 |
| }, |
| { |
| "dharma_eval_accuracy": 0.28195932340602153, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5, |
| "dharma_eval_accuracy_ARC-Easy": 0.42592592592592593, |
| "dharma_eval_accuracy_BoolQ": 0.14814814814814814, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.2033898305084746, |
| "dharma_eval_accuracy_bigbench": 0.2786885245901639, |
| "dharma_eval_accuracy_openbookqa": 0.16666666666666666, |
| "dharma_eval_accuracy_truthful_qa": 0.4074074074074074, |
| "dharma_eval_accuracy_winogrande": 0.037037037037037035, |
| "dharma_loss": 2.1986728873252868, |
| "epoch": 0.35, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00029280785353670514, |
| "loss": 0.5792, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029265847744427303, |
| "loss": 0.8044, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029250760493191734, |
| "loss": 0.6001, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0002923552375822194, |
| "loss": 0.6472, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00029220137699344055, |
| "loss": 0.7501, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00029204602477950556, |
| "loss": 0.6902, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00029188918256998564, |
| "loss": 0.4407, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0002917308520100814, |
| "loss": 0.5332, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00029157103476060544, |
| "loss": 0.5386, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002914097324979651, |
| "loss": 0.4817, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002912469469141448, |
| "loss": 0.4525, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.0002910826797166882, |
| "loss": 0.612, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00029091693262868067, |
| "loss": 0.7156, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002907497073887305, |
| "loss": 0.5885, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002905810057509515, |
| "loss": 0.7867, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029041082948494395, |
| "loss": 0.5811, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029023918037577635, |
| "loss": 0.5932, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00029006606022396667, |
| "loss": 0.5278, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028989147084546333, |
| "loss": 0.7287, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00028971541407162634, |
| "loss": 0.6057, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0002895378917492079, |
| "loss": 0.5389, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0002893589057403332, |
| "loss": 0.5675, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002891784579224808, |
| "loss": 1.1157, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00028899655018846295, |
| "loss": 0.5764, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002888131844464056, |
| "loss": 0.5569, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "eval_loss": 0.5351170301437378, |
| "eval_runtime": 26.2901, |
| "eval_samples_per_second": 7.607, |
| "eval_steps_per_second": 1.902, |
| "step": 150 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3671984787726814, |
| "dharma_eval_accuracy_ARC-Challenge": 0.4074074074074074, |
| "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185, |
| "dharma_eval_accuracy_BoolQ": 0.5925925925925926, |
| "dharma_eval_accuracy_MMLU": 0.2777777777777778, |
| "dharma_eval_accuracy_agieval": 0.2033898305084746, |
| "dharma_eval_accuracy_bigbench": 0.36065573770491804, |
| "dharma_eval_accuracy_openbookqa": 0.12962962962962962, |
| "dharma_eval_accuracy_truthful_qa": 0.46296296296296297, |
| "dharma_eval_accuracy_winogrande": 0.35185185185185186, |
| "dharma_loss": 2.2095200095176697, |
| "epoch": 0.42, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002886283626197287, |
| "loss": 0.6519, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00028844208664712575, |
| "loss": 0.5034, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0002882543584825435, |
| "loss": 0.458, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00028806518009516155, |
| "loss": 0.7111, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002878745534693718, |
| "loss": 0.5929, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00028768248060475726, |
| "loss": 0.4101, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002874889635160714, |
| "loss": 0.5451, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002872940042332169, |
| "loss": 0.5704, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002870976048012244, |
| "loss": 0.561, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.000286899767280231, |
| "loss": 0.6202, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002867004937454587, |
| "loss": 0.482, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00028649978628719254, |
| "loss": 0.7186, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00028629764701075885, |
| "loss": 0.6017, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002860940780365029, |
| "loss": 0.3942, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.000285889081499767, |
| "loss": 0.6209, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00028568265955086774, |
| "loss": 0.6066, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002854748143550738, |
| "loss": 0.4569, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00028526554809258275, |
| "loss": 0.5281, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002850548629584988, |
| "loss": 0.6024, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028484276116280926, |
| "loss": 0.5511, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028462924493036164, |
| "loss": 0.5352, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00028441431650084016, |
| "loss": 0.4939, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028419797812874237, |
| "loss": 0.4447, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028398023208335533, |
| "loss": 0.4381, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028376108064873215, |
| "loss": 0.5307, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "eval_loss": 0.5249650478363037, |
| "eval_runtime": 26.2562, |
| "eval_samples_per_second": 7.617, |
| "eval_steps_per_second": 1.904, |
| "step": 175 |
| }, |
| { |
| "dharma_eval_accuracy": 0.37955502042748507, |
| "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145, |
| "dharma_eval_accuracy_ARC-Easy": 0.46296296296296297, |
| "dharma_eval_accuracy_BoolQ": 0.5185185185185185, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.3114754098360656, |
| "dharma_eval_accuracy_openbookqa": 0.18518518518518517, |
| "dharma_eval_accuracy_truthful_qa": 0.3888888888888889, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.0181055121421814, |
| "epoch": 0.49, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00028354052612366757, |
| "loss": 0.728, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0002833185708216743, |
| "loss": 0.6826, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0002830952170709583, |
| "loss": 0.5093, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00028287046721439484, |
| "loss": 0.5606, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00028264432360950353, |
| "loss": 0.6572, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002824167886284237, |
| "loss": 0.4859, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002821878646578898, |
| "loss": 0.7205, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002819575540992058, |
| "loss": 0.6155, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028172585936822055, |
| "loss": 0.6296, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028149278289530213, |
| "loss": 0.5541, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00028125832712531246, |
| "loss": 0.6688, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002810224945175816, |
| "loss": 0.6164, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028078528754588205, |
| "loss": 0.5584, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028054670869840265, |
| "loss": 0.5675, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00028030676047772265, |
| "loss": 0.439, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00028006544540078534, |
| "loss": 0.7137, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0002798227659988717, |
| "loss": 0.7236, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00027957872481757374, |
| "loss": 0.6347, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00027933332441676807, |
| "loss": 0.572, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0002790865673705888, |
| "loss": 0.4412, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00027883845626740044, |
| "loss": 0.5219, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0002785889937097712, |
| "loss": 0.4882, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027833818231444516, |
| "loss": 0.6258, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027808602471231524, |
| "loss": 0.585, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002778325235483954, |
| "loss": 0.5413, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 0.5214321613311768, |
| "eval_runtime": 26.2712, |
| "eval_samples_per_second": 7.613, |
| "eval_steps_per_second": 1.903, |
| "step": 200 |
| }, |
| { |
| "dharma_eval_accuracy": 0.46479417579414495, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112, |
| "dharma_eval_accuracy_BoolQ": 0.7592592592592593, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.39344262295081966, |
| "dharma_eval_accuracy_openbookqa": 0.2222222222222222, |
| "dharma_eval_accuracy_truthful_qa": 0.48148148148148145, |
| "dharma_eval_accuracy_winogrande": 0.46296296296296297, |
| "dharma_loss": 2.4899120001792907, |
| "epoch": 0.56, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00027757768148179275, |
| "loss": 0.4495, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027732150118568017, |
| "loss": 0.5601, |
| "step": 202 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027706398534726757, |
| "loss": 0.4523, |
| "step": 203 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00027680513666777435, |
| "loss": 0.4744, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027654495786240066, |
| "loss": 0.4629, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027628345166029906, |
| "loss": 0.526, |
| "step": 206 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00027602062080454577, |
| "loss": 0.6021, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.0002757564680521122, |
| "loss": 0.5399, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0002754909961738357, |
| "loss": 0.6118, |
| "step": 209 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00027522420795439065, |
| "loss": 0.7085, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0002749561061922592, |
| "loss": 0.5468, |
| "step": 211 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00027468669369970207, |
| "loss": 0.5486, |
| "step": 212 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002744159733027287, |
| "loss": 0.635, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002741439478410681, |
| "loss": 0.6096, |
| "step": 214 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002738706201681384, |
| "loss": 0.6964, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00027359599315101787, |
| "loss": 0.5901, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00027332006967041366, |
| "loss": 0.6118, |
| "step": 217 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002730428526206327, |
| "loss": 0.5126, |
| "step": 218 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0002727643449095507, |
| "loss": 0.7313, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002724845494585816, |
| "loss": 0.6084, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002722034692026474, |
| "loss": 0.7394, |
| "step": 221 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00027192110709014697, |
| "loss": 0.5481, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002716374660829252, |
| "loss": 0.562, |
| "step": 223 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002713525491562421, |
| "loss": 0.6225, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00027106635929874135, |
| "loss": 0.6103, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.63, |
| "eval_loss": 0.5194589495658875, |
| "eval_runtime": 26.3678, |
| "eval_samples_per_second": 7.585, |
| "eval_steps_per_second": 1.896, |
| "step": 225 |
| }, |
| { |
| "dharma_eval_accuracy": 0.43951795023080253, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.6666666666666666, |
| "dharma_eval_accuracy_BoolQ": 0.7407407407407407, |
| "dharma_eval_accuracy_MMLU": 0.48148148148148145, |
| "dharma_eval_accuracy_agieval": 0.3050847457627119, |
| "dharma_eval_accuracy_bigbench": 0.4098360655737705, |
| "dharma_eval_accuracy_openbookqa": 0.07407407407407407, |
| "dharma_eval_accuracy_truthful_qa": 0.2962962962962963, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.398480008125305, |
| "epoch": 0.63, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.0002707788995124192, |
| "loss": 0.6396, |
| "step": 226 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00027049017281259276, |
| "loss": 0.5941, |
| "step": 227 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.0002702001822278685, |
| "loss": 0.4124, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00026990893080011035, |
| "loss": 0.5808, |
| "step": 229 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002696164215844081, |
| "loss": 0.5505, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00026932265764904493, |
| "loss": 0.5346, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002690276420754655, |
| "loss": 0.4269, |
| "step": 232 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002687313779582436, |
| "loss": 0.5643, |
| "step": 233 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.0002684338684050497, |
| "loss": 0.6967, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00026813511653661816, |
| "loss": 0.5752, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.0002678351254867147, |
| "loss": 0.5876, |
| "step": 236 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002675338984021035, |
| "loss": 0.2724, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00026723143844251416, |
| "loss": 0.6353, |
| "step": 238 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002669277487806085, |
| "loss": 0.4909, |
| "step": 239 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002666228326019474, |
| "loss": 0.5022, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002663166931049572, |
| "loss": 0.5741, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00026600933350089654, |
| "loss": 0.5531, |
| "step": 242 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00026570075701382213, |
| "loss": 0.7589, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0002653909668805553, |
| "loss": 0.6368, |
| "step": 244 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00026507996635064787, |
| "loss": 0.5444, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0002647677586863484, |
| "loss": 0.6092, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.0002644543471625675, |
| "loss": 0.642, |
| "step": 247 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00026413973506684364, |
| "loss": 0.5914, |
| "step": 248 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.000263823925699309, |
| "loss": 0.5741, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00026350692237265427, |
| "loss": 0.5625, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 0.5171582102775574, |
| "eval_runtime": 26.3289, |
| "eval_samples_per_second": 7.596, |
| "eval_steps_per_second": 1.899, |
| "step": 250 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3371152480627335, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556, |
| "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371, |
| "dharma_eval_accuracy_BoolQ": 0.7222222222222222, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.288135593220339, |
| "dharma_eval_accuracy_bigbench": 0.2459016393442623, |
| "dharma_eval_accuracy_openbookqa": 0.037037037037037035, |
| "dharma_eval_accuracy_truthful_qa": 0.2037037037037037, |
| "dharma_eval_accuracy_winogrande": 0.07407407407407407, |
| "dharma_loss": 2.435349561214447, |
| "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": 0.5217, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00026254878195252983, |
| "loss": 0.4295, |
| "step": 253 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00026222703616626055, |
| "loss": 0.4418, |
| "step": 254 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026190411317148686, |
| "loss": 0.5318, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026158001635551815, |
| "loss": 0.6201, |
| "step": 256 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00026125474911797657, |
| "loss": 0.668, |
| "step": 257 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0002609283148707616, |
| "loss": 0.5815, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.000260600717038014, |
| "loss": 0.8842, |
| "step": 259 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00026027195905608006, |
| "loss": 0.4842, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00025994204437347537, |
| "loss": 0.5761, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025961097645084885, |
| "loss": 0.6292, |
| "step": 262 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0002592787587609465, |
| "loss": 0.4136, |
| "step": 263 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025894539478857445, |
| "loss": 0.651, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00025861088803056325, |
| "loss": 0.4619, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0002582752419957303, |
| "loss": 0.4523, |
| "step": 266 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0002579384602048438, |
| "loss": 0.5598, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00025760054619058535, |
| "loss": 0.674, |
| "step": 268 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00025726150349751305, |
| "loss": 0.5375, |
| "step": 269 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002569213356820244, |
| "loss": 0.6697, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002565800463123187, |
| "loss": 0.6273, |
| "step": 271 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002562376389683599, |
| "loss": 0.5117, |
| "step": 272 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00025589411724183923, |
| "loss": 0.5244, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002555494847361369, |
| "loss": 0.5547, |
| "step": 274 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002552037450662849, |
| "loss": 0.5421, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.77, |
| "eval_loss": 0.5214882493019104, |
| "eval_runtime": 26.2939, |
| "eval_samples_per_second": 7.606, |
| "eval_steps_per_second": 1.902, |
| "step": 275 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4302195282868927, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5185185185185185, |
| "dharma_eval_accuracy_ARC-Easy": 0.5740740740740741, |
| "dharma_eval_accuracy_BoolQ": 0.7222222222222222, |
| "dharma_eval_accuracy_MMLU": 0.3888888888888889, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.16666666666666666, |
| "dharma_eval_accuracy_truthful_qa": 0.3333333333333333, |
| "dharma_eval_accuracy_winogrande": 0.3888888888888889, |
| "dharma_loss": 2.8160859088897707, |
| "epoch": 0.77, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0002548569018589286, |
| "loss": 0.4993, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002545089587522893, |
| "loss": 0.6713, |
| "step": 277 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002541599193961254, |
| "loss": 0.5358, |
| "step": 278 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0002538097874516947, |
| "loss": 0.5865, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025345856659171563, |
| "loss": 0.4745, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0002531062605003287, |
| "loss": 0.4952, |
| "step": 281 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025275287287305814, |
| "loss": 0.4839, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00025239840741677304, |
| "loss": 0.4663, |
| "step": 283 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025204286784964817, |
| "loss": 0.8068, |
| "step": 284 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025168625790112547, |
| "loss": 0.4626, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00025132858131187444, |
| "loss": 0.5517, |
| "step": 286 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00025096984183375334, |
| "loss": 0.5414, |
| "step": 287 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002506100432297695, |
| "loss": 0.5891, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00025024918927404004, |
| "loss": 0.5998, |
| "step": 289 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00024988728375175214, |
| "loss": 0.5972, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024952433045912354, |
| "loss": 0.4774, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024916033320336264, |
| "loss": 0.6492, |
| "step": 292 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00024879529580262817, |
| "loss": 0.5421, |
| "step": 293 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00024842922208598994, |
| "loss": 0.6527, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.0002480621158933879, |
| "loss": 0.5661, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00024769398107559224, |
| "loss": 0.4992, |
| "step": 296 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.0002473248214941632, |
| "loss": 0.5778, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024695464102141, |
| "loss": 0.4747, |
| "step": 298 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0002465834435403506, |
| "loss": 0.45, |
| "step": 299 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024621123294467096, |
| "loss": 0.5855, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_loss": 0.5145771503448486, |
| "eval_runtime": 26.2935, |
| "eval_samples_per_second": 7.606, |
| "eval_steps_per_second": 1.902, |
| "step": 300 |
| }, |
| { |
| "dharma_eval_accuracy": 0.44867630125880875, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5, |
| "dharma_eval_accuracy_ARC-Easy": 0.5555555555555556, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.3888888888888889, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.5245901639344263, |
| "dharma_eval_accuracy_openbookqa": 0.2037037037037037, |
| "dharma_eval_accuracy_truthful_qa": 0.48148148148148145, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.7657925186157226, |
| "epoch": 0.84, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00024583801313868416, |
| "loss": 0.421, |
| "step": 301 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0002454637880372892, |
| "loss": 0.4721, |
| "step": 302 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0002450885615659305, |
| "loss": 0.4455, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00024471233766055605, |
| "loss": 0.6375, |
| "step": 304 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024433512026757664, |
| "loss": 0.643, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024395691334382427, |
| "loss": 0.5644, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024357772085651055, |
| "loss": 0.4863, |
| "step": 307 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00024319754678318528, |
| "loss": 0.4783, |
| "step": 308 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00024281639511169456, |
| "loss": 0.392, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0002424342698401391, |
| "loss": 0.6975, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00024205117497683209, |
| "loss": 0.5923, |
| "step": 311 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002416671145402575, |
| "loss": 0.5953, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002412820925590275, |
| "loss": 0.7582, |
| "step": 313 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00024089611307184048, |
| "loss": 0.4313, |
| "step": 314 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002405091801274387, |
| "loss": 0.4586, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00024012129778456552, |
| "loss": 0.5375, |
| "step": 316 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00023973247011192325, |
| "loss": 0.6677, |
| "step": 317 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0002393427011881302, |
| "loss": 0.7285, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0002389519951016779, |
| "loss": 0.7538, |
| "step": 319 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023856035595088839, |
| "loss": 0.8908, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023816778784387094, |
| "loss": 0.676, |
| "step": 321 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00023777429489847934, |
| "loss": 0.622, |
| "step": 322 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002373798812422683, |
| "loss": 0.4019, |
| "step": 323 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002369845510124505, |
| "loss": 0.3107, |
| "step": 324 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0002365883083558529, |
| "loss": 0.5211, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.91, |
| "eval_loss": 0.5113330483436584, |
| "eval_runtime": 26.3892, |
| "eval_samples_per_second": 7.579, |
| "eval_steps_per_second": 1.895, |
| "step": 325 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3877854731023821, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5370370370370371, |
| "dharma_eval_accuracy_ARC-Easy": 0.5, |
| "dharma_eval_accuracy_BoolQ": 0.7222222222222222, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.3114754098360656, |
| "dharma_eval_accuracy_openbookqa": 0.1111111111111111, |
| "dharma_eval_accuracy_truthful_qa": 0.42592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.2037037037037037, |
| "dharma_loss": 2.4642191791534422, |
| "epoch": 0.91, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023619115742887356, |
| "loss": 0.3429, |
| "step": 326 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023579310239743773, |
| "loss": 0.5627, |
| "step": 327 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023539414743695437, |
| "loss": 0.4695, |
| "step": 328 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00023499429673227222, |
| "loss": 0.6067, |
| "step": 329 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00023459355447763596, |
| "loss": 0.5316, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00023419192487664217, |
| "loss": 0.513, |
| "step": 331 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002337894121421954, |
| "loss": 0.4925, |
| "step": 332 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002333860204964637, |
| "loss": 0.563, |
| "step": 333 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00023298175417083459, |
| "loss": 0.5984, |
| "step": 334 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0002325766174058705, |
| "loss": 0.5588, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0002321706144512644, |
| "loss": 0.4404, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.0002317637495657952, |
| "loss": 0.4732, |
| "step": 337 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.000231356027017283, |
| "loss": 0.5246, |
| "step": 338 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00023094745108254435, |
| "loss": 0.5532, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00023053802604734757, |
| "loss": 0.5995, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00023012775620636746, |
| "loss": 0.5497, |
| "step": 341 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00022971664586314054, |
| "loss": 0.6566, |
| "step": 342 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00022930469933001975, |
| "loss": 0.5113, |
| "step": 343 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022889192092812938, |
| "loss": 0.4709, |
| "step": 344 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0002284783149873195, |
| "loss": 0.6061, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022806388584612066, |
| "loss": 0.6152, |
| "step": 346 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00022764863785169854, |
| "loss": 0.5941, |
| "step": 347 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.000227232575359808, |
| "loss": 0.5065, |
| "step": 348 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.0002268157027347478, |
| "loss": 0.3712, |
| "step": 349 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00022639802434931444, |
| "loss": 0.6014, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.98, |
| "eval_loss": 0.5098372101783752, |
| "eval_runtime": 26.3063, |
| "eval_samples_per_second": 7.603, |
| "eval_steps_per_second": 1.901, |
| "step": 350 |
| }, |
| { |
| "dharma_eval_accuracy": 0.43539186125089613, |
| "dharma_eval_accuracy_ARC-Challenge": 0.4444444444444444, |
| "dharma_eval_accuracy_ARC-Easy": 0.5925925925925926, |
| "dharma_eval_accuracy_BoolQ": 0.7407407407407407, |
| "dharma_eval_accuracy_MMLU": 0.2962962962962963, |
| "dharma_eval_accuracy_agieval": 0.23728813559322035, |
| "dharma_eval_accuracy_bigbench": 0.45901639344262296, |
| "dharma_eval_accuracy_openbookqa": 0.25925925925925924, |
| "dharma_eval_accuracy_truthful_qa": 0.46296296296296297, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.812399542808533, |
| "epoch": 0.98, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.0002259795445847566, |
| "loss": 0.5326, |
| "step": 351 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022556026783072895, |
| "loss": 0.3734, |
| "step": 352 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022514019848524628, |
| "loss": 0.5185, |
| "step": 353 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00022471934095463723, |
| "loss": 0.4014, |
| "step": 354 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022429769965349815, |
| "loss": 0.4812, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022387527900464673, |
| "loss": 0.4543, |
| "step": 356 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022345208343907576, |
| "loss": 0.6986, |
| "step": 357 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00022302811739590642, |
| "loss": 0.4894, |
| "step": 358 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022260338532234194, |
| "loss": 0.4049, |
| "step": 359 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022217789167362073, |
| "loss": 0.5939, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00022175164091296987, |
| "loss": 0.6627, |
| "step": 361 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022132463751155812, |
| "loss": 0.6113, |
| "step": 362 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022089688594844915, |
| "loss": 0.5954, |
| "step": 363 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022046839071055435, |
| "loss": 0.365, |
| "step": 364 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00022003915629258605, |
| "loss": 0.483, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021960918719701026, |
| "loss": 0.5085, |
| "step": 366 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021917848793399924, |
| "loss": 0.4389, |
| "step": 367 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00021874706302138448, |
| "loss": 0.5703, |
| "step": 368 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021831491698460923, |
| "loss": 0.4179, |
| "step": 369 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021788205435668083, |
| "loss": 0.4141, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002174484796781235, |
| "loss": 0.4796, |
| "step": 371 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00021701419749693034, |
| "loss": 0.4063, |
| "step": 372 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021657921236851603, |
| "loss": 0.3794, |
| "step": 373 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021614352885566872, |
| "loss": 0.5091, |
| "step": 374 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.00021570715152850232, |
| "loss": 0.4805, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.05, |
| "eval_loss": 0.5130083560943604, |
| "eval_runtime": 26.3643, |
| "eval_samples_per_second": 7.586, |
| "eval_steps_per_second": 1.897, |
| "step": 375 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4202802104379703, |
| "dharma_eval_accuracy_ARC-Challenge": 0.2962962962962963, |
| "dharma_eval_accuracy_ARC-Easy": 0.3333333333333333, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.2222222222222222, |
| "dharma_eval_accuracy_agieval": 0.23728813559322035, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.2962962962962963, |
| "dharma_eval_accuracy_truthful_qa": 0.6481481481481481, |
| "dharma_eval_accuracy_winogrande": 0.5370370370370371, |
| "dharma_loss": 2.9995801568031313, |
| "epoch": 1.05, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021527008496440846, |
| "loss": 0.6046, |
| "step": 376 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021483233374800862, |
| "loss": 0.545, |
| "step": 377 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021439390247110588, |
| "loss": 0.3296, |
| "step": 378 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00021395479573263688, |
| "loss": 0.6645, |
| "step": 379 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021351501813862356, |
| "loss": 0.4805, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021307457430212468, |
| "loss": 0.4243, |
| "step": 381 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021263346884318777, |
| "loss": 0.5985, |
| "step": 382 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021219170638880037, |
| "loss": 0.3354, |
| "step": 383 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021174929157284156, |
| "loss": 0.3357, |
| "step": 384 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00021130622903603344, |
| "loss": 0.4297, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.0002108625234258923, |
| "loss": 0.4413, |
| "step": 386 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00021041817939668005, |
| "loss": 0.5532, |
| "step": 387 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020997320160935534, |
| "loss": 0.3623, |
| "step": 388 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020952759473152457, |
| "loss": 0.3285, |
| "step": 389 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020908136343739307, |
| "loss": 0.4629, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020863451240771592, |
| "loss": 0.4902, |
| "step": 391 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020818704632974896, |
| "loss": 0.4195, |
| "step": 392 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.00020773896989719965, |
| "loss": 0.4876, |
| "step": 393 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00020729028781017777, |
| "loss": 0.4855, |
| "step": 394 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.000206841004775146, |
| "loss": 0.3135, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00020639112550487084, |
| "loss": 0.5793, |
| "step": 396 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.000205940654718373, |
| "loss": 0.5195, |
| "step": 397 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002054895971408778, |
| "loss": 0.4541, |
| "step": 398 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002050379575037658, |
| "loss": 0.4901, |
| "step": 399 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00020458574054452313, |
| "loss": 0.4943, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_loss": 0.5143458843231201, |
| "eval_runtime": 26.3523, |
| "eval_samples_per_second": 7.589, |
| "eval_steps_per_second": 1.897, |
| "step": 400 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4058769182569003, |
| "dharma_eval_accuracy_ARC-Challenge": 0.3148148148148148, |
| "dharma_eval_accuracy_ARC-Easy": 0.4074074074074074, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.25925925925925924, |
| "dharma_eval_accuracy_agieval": 0.23728813559322035, |
| "dharma_eval_accuracy_bigbench": 0.5081967213114754, |
| "dharma_eval_accuracy_openbookqa": 0.16666666666666666, |
| "dharma_eval_accuracy_truthful_qa": 0.5555555555555556, |
| "dharma_eval_accuracy_winogrande": 0.5, |
| "dharma_loss": 2.6459020280838015, |
| "epoch": 1.12, |
| "step": 400 |
| } |
| ], |
| "max_steps": 1000, |
| "num_train_epochs": 3, |
| "total_flos": 1.2906498742913434e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
