| { | |
| "best_metric": 1.4968100786209106, | |
| "best_model_checkpoint": "./pippa-sharegpt-13b-qlora/checkpoint-150", | |
| "epoch": 1.58311345646438, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9209, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8722, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00012, | |
| "loss": 1.872, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9138, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8785, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8013, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019999332998034514, | |
| "loss": 1.7805, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019997332081116373, | |
| "loss": 1.7716, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019993997516168689, | |
| "loss": 1.7453, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019989329748023725, | |
| "loss": 1.7306, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019983329399363598, | |
| "loss": 1.7535, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001997599727063717, | |
| "loss": 1.7811, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000199673343399533, | |
| "loss": 1.7455, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.748, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001994602087264201, | |
| "loss": 1.723, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019933373179239502, | |
| "loss": 1.7539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000199194003699501, | |
| "loss": 1.7293, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001990410430875205, | |
| "loss": 1.6857, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001988748703614594, | |
| "loss": 1.7209, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019869550768882455, | |
| "loss": 1.7127, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001985029789966671, | |
| "loss": 1.7024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001982973099683902, | |
| "loss": 1.6927, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.6584, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001978466623980609, | |
| "loss": 1.7149, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019760174397257156, | |
| "loss": 1.6815, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001973438054360693, | |
| "loss": 1.7067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019707288119765623, | |
| "loss": 1.6799, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019678900739873226, | |
| "loss": 1.7206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001964922219081738, | |
| "loss": 1.6458, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019618256431728194, | |
| "loss": 1.6649, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019586007593450097, | |
| "loss": 1.6684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000195524799779908, | |
| "loss": 1.7411, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019517678057947384, | |
| "loss": 1.6678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001948160647590966, | |
| "loss": 1.6738, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019444270043840852, | |
| "loss": 1.6804, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019405673742435678, | |
| "loss": 1.6728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019365822720455916, | |
| "loss": 1.6941, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019324722294043558, | |
| "loss": 1.6861, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019282377946011652, | |
| "loss": 1.6751, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.7175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019193980245285966, | |
| "loss": 1.6454, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001914793868488021, | |
| "loss": 1.6934, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001910067678585786, | |
| "loss": 1.6534, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019052200852974819, | |
| "loss": 1.6797, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00019002517352939598, | |
| "loss": 1.6566, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018951632913550626, | |
| "loss": 1.657, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.653587818145752, | |
| "eval_runtime": 200.2473, | |
| "eval_samples_per_second": 6.672, | |
| "eval_steps_per_second": 0.21, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001889955432281212, | |
| "loss": 1.6736, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018846288528028555, | |
| "loss": 1.6696, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018791842634877898, | |
| "loss": 1.6429, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018736223906463696, | |
| "loss": 1.608, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018679439762346185, | |
| "loss": 1.6245, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018621497777552507, | |
| "loss": 1.6199, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018562405681566216, | |
| "loss": 1.7028, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018502171357296144, | |
| "loss": 1.6372, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018440802840024822, | |
| "loss": 1.6198, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018378308316336584, | |
| "loss": 1.6061, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.6051, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018249974745983023, | |
| "loss": 1.6257, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018184152819066435, | |
| "loss": 1.6295, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00018117239122946615, | |
| "loss": 1.6382, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001804924258393692, | |
| "loss": 1.6032, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000179801722728024, | |
| "loss": 1.652, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00017910037403549693, | |
| "loss": 1.6431, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00017838847332197938, | |
| "loss": 1.6482, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017766611555530636, | |
| "loss": 1.6276, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00017693339709828792, | |
| "loss": 1.611, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00017619041569585418, | |
| "loss": 1.6309, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001754372704620164, | |
| "loss": 1.6316, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017467406186664474, | |
| "loss": 1.5779, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00017390089172206592, | |
| "loss": 1.6015, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001731178631694811, | |
| "loss": 1.6133, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00017232508066520702, | |
| "loss": 1.6048, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00017152264996674136, | |
| "loss": 1.5792, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.5756, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00016988927343831095, | |
| "loss": 1.5497, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016905854550141716, | |
| "loss": 1.5604, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00016821860512740671, | |
| "loss": 1.5722, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00016736956436465573, | |
| "loss": 1.5943, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016651153647553567, | |
| "loss": 1.538, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00016564463592130428, | |
| "loss": 1.5875, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001647689783468362, | |
| "loss": 1.5835, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00016388468056519612, | |
| "loss": 1.5724, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00016299186054205577, | |
| "loss": 1.573, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00016209063737995715, | |
| "loss": 1.543, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016118113130242432, | |
| "loss": 1.5438, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00016026346363792567, | |
| "loss": 1.5711, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00015933775680368822, | |
| "loss": 1.5542, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015840413428936767, | |
| "loss": 1.5209, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0001574627206405744, | |
| "loss": 1.569, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001565136414422592, | |
| "loss": 1.5657, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.5248, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00015459299383291345, | |
| "loss": 1.5482, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.000153621681637029, | |
| "loss": 1.5186, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001526432162877356, | |
| "loss": 1.5363, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00015165772831269547, | |
| "loss": 1.5221, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00015066534917639195, | |
| "loss": 1.5071, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.541548728942871, | |
| "eval_runtime": 200.1636, | |
| "eval_samples_per_second": 6.675, | |
| "eval_steps_per_second": 0.21, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00014966621126259183, | |
| "loss": 1.5179, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014866044785668563, | |
| "loss": 1.4923, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00014764819312790707, | |
| "loss": 1.5733, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001466295821114348, | |
| "loss": 1.4586, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00014560475069037894, | |
| "loss": 1.5379, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00014457383557765386, | |
| "loss": 1.5059, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00014353697429774084, | |
| "loss": 1.512, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001424943051683422, | |
| "loss": 1.4908, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001414459672819297, | |
| "loss": 1.5067, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00014039210048718949, | |
| "loss": 1.4908, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00013933284537036625, | |
| "loss": 1.5299, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.4836, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00013719873609062077, | |
| "loss": 1.5285, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00013612416661871533, | |
| "loss": 1.5493, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001350447781687826, | |
| "loss": 1.4915, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013396071473166613, | |
| "loss": 1.5139, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00013287212092185464, | |
| "loss": 1.4589, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00013177914195819016, | |
| "loss": 1.4869, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00013068192364449618, | |
| "loss": 1.5081, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00012958061235012706, | |
| "loss": 1.5172, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001284753549904423, | |
| "loss": 1.5195, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001273662990072083, | |
| "loss": 1.4635, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00012625359234892907, | |
| "loss": 1.5036, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0001251373834511103, | |
| "loss": 1.5203, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00012401782121645766, | |
| "loss": 1.5047, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001228950549950134, | |
| "loss": 1.5047, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00012176923456423284, | |
| "loss": 1.4715, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00012064051010900397, | |
| "loss": 1.4884, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.4947, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00011837495178165706, | |
| "loss": 1.4665, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00011723842013591044, | |
| "loss": 1.4888, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00011609958887814129, | |
| "loss": 1.52, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00011495860992888712, | |
| "loss": 1.4305, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00011381563549518823, | |
| "loss": 1.4865, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00011267081805028339, | |
| "loss": 1.5155, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00011152431031326978, | |
| "loss": 1.4952, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00011037626522873019, | |
| "loss": 1.4765, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00010922683594633021, | |
| "loss": 1.4729, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00010807617580038796, | |
| "loss": 1.481, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00010692443828941918, | |
| "loss": 1.4877, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00010577177705566061, | |
| "loss": 1.4884, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00010461834586457398, | |
| "loss": 1.4786, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00010346429858433352, | |
| "loss": 1.4585, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00010230978916530012, | |
| "loss": 1.4867, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00010115497161948409, | |
| "loss": 1.487, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4693, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.884502838051595e-05, | |
| "loss": 1.4391, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.76902108346999e-05, | |
| "loss": 1.493, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.653570141566653e-05, | |
| "loss": 1.5152, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.538165413542607e-05, | |
| "loss": 1.4766, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.4968100786209106, | |
| "eval_runtime": 199.9343, | |
| "eval_samples_per_second": 6.682, | |
| "eval_steps_per_second": 0.21, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 282, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "total_flos": 1.546341313689944e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |