| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0334928229665072, |
| "eval_steps": 500, |
| "global_step": 108, |
| "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": 2.3634, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 4e-05, |
| "loss": 2.4605, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 6e-05, |
| "loss": 2.3783, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 8e-05, |
| "loss": 2.5611, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0001, |
| "loss": 2.525, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00012, |
| "loss": 2.4104, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00014, |
| "loss": 2.3589, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00016, |
| "loss": 2.4133, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00018, |
| "loss": 2.1582, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.0002, |
| "loss": 2.1394, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019998741276738754, |
| "loss": 2.1466, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019994965423831854, |
| "loss": 2.0672, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0001998867339183008, |
| "loss": 2.1323, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019979866764718843, |
| "loss": 2.0887, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00019968547759519425, |
| "loss": 2.1057, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019954719225730847, |
| "loss": 2.0863, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00019938384644612543, |
| "loss": 2.09, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00019919548128307954, |
| "loss": 2.0731, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0001989821441880933, |
| "loss": 2.1503, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00019874388886763944, |
| "loss": 1.9755, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00019848077530122083, |
| "loss": 2.117, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00019819286972627066, |
| "loss": 1.9935, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00019788024462147788, |
| "loss": 2.0685, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00019754297868854073, |
| "loss": 2.0086, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00019718115683235417, |
| "loss": 2.0013, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00019679487013963564, |
| "loss": 2.0066, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00019638421585599423, |
| "loss": 1.9823, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00019594929736144976, |
| "loss": 2.0394, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0001954902241444074, |
| "loss": 2.0804, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00019500711177409454, |
| "loss": 1.997, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00019450008187146684, |
| "loss": 2.0794, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00019396926207859084, |
| "loss": 1.9769, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00019341478602651069, |
| "loss": 1.9643, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00019283679330160726, |
| "loss": 2.041, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00019223542941045817, |
| "loss": 1.9873, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00019161084574320696, |
| "loss": 2.0358, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00019096319953545185, |
| "loss": 2.021, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00019029265382866214, |
| "loss": 2.0764, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00018959937742913359, |
| "loss": 2.1639, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00018888354486549237, |
| "loss": 2.0892, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00018814533634475822, |
| "loss": 1.9749, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00018738493770697852, |
| "loss": 2.0521, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 2.0751, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00018579834132349772, |
| "loss": 2.0852, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00018497254299495146, |
| "loss": 1.9871, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00018412535328311814, |
| "loss": 1.9199, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00018325698546347715, |
| "loss": 1.9627, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0001823676581429833, |
| "loss": 2.0465, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00018145759520503358, |
| "loss": 2.0033, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00018052702575310588, |
| "loss": 1.8835, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00017957618405308324, |
| "loss": 1.9823, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00017860530947427875, |
| "loss": 2.0887, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0001776146464291757, |
| "loss": 2.0936, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0001766044443118978, |
| "loss": 2.0576, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00017557495743542585, |
| "loss": 1.8788, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0001745264449675755, |
| "loss": 2.0452, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00017345917086575332, |
| "loss": 2.0411, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00017237340381050703, |
| "loss": 2.0834, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00017126941713788632, |
| "loss": 2.113, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00017014748877063214, |
| "loss": 2.0797, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00016900790114821122, |
| "loss": 2.0783, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00016785094115571322, |
| "loss": 1.9576, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00016667690005162916, |
| "loss": 1.9651, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00016548607339452853, |
| "loss": 1.9927, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00016427876096865394, |
| "loss": 2.0967, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00016305526670845226, |
| "loss": 2.0661, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00016181589862206052, |
| "loss": 1.9413, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00016056096871376667, |
| "loss": 1.8223, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.00015929079290546408, |
| "loss": 2.0162, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00015800569095711982, |
| "loss": 1.9682, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00015670598638627706, |
| "loss": 1.8836, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00015539200638661104, |
| "loss": 1.9973, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.00015406408174555976, |
| "loss": 2.1492, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00015272254676105025, |
| "loss": 1.9856, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00015136773915734066, |
| "loss": 1.9407, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 2.0559, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.00014861967361004687, |
| "loss": 1.9553, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.0001472271074772683, |
| "loss": 1.996, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00014582265217274104, |
| "loss": 2.2306, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00014440666126057744, |
| "loss": 2.0002, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.00014297949120891718, |
| "loss": 2.068, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.00014154150130018866, |
| "loss": 2.0615, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00014009305354066137, |
| "loss": 2.0083, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00013863451256931287, |
| "loss": 1.9979, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00013716624556603274, |
| "loss": 1.8525, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00013568862215918717, |
| "loss": 2.045, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.00013420201433256689, |
| "loss": 1.9144, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00013270679633174218, |
| "loss": 1.9353, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.0001312033445698487, |
| "loss": 2.1257, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.0001296920375328275, |
| "loss": 1.906, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00012817325568414297, |
| "loss": 1.9963, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00012664738136900348, |
| "loss": 2.0734, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0001251147987181079, |
| "loss": 2.0182, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00012357589355094275, |
| "loss": 1.9574, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.00012203105327865407, |
| "loss": 2.1562, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00012048066680651908, |
| "loss": 2.082, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00011892512443604102, |
| "loss": 1.9546, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00011736481776669306, |
| "loss": 2.0957, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.000115800139597335, |
| "loss": 1.9348, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.00011423148382732853, |
| "loss": 2.0772, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.00011265924535737493, |
| "loss": 2.0298, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00011108381999010111, |
| "loss": 2.0272, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00010950560433041826, |
| "loss": 2.0293, |
| "step": 103 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00010792499568567884, |
| "loss": 1.8576, |
| "step": 104 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00010634239196565646, |
| "loss": 1.9792, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00010475819158237425, |
| "loss": 1.8629, |
| "step": 106 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00010317279334980678, |
| "loss": 2.0062, |
| "step": 107 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00010158659638348081, |
| "loss": 1.937, |
| "step": 108 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 208, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 4.245474393540526e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
