| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.8192771084337345, | |
| "eval_steps": 150, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.4026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.8531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.3763, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00015, | |
| "loss": 0.961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.2005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.1054, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0114, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00027, | |
| "loss": 1.1386, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00029990862405286433, | |
| "loss": 0.7562, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002996346075389736, | |
| "loss": 1.0498, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00029917828430524096, | |
| "loss": 1.2559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002985402103112355, | |
| "loss": 1.0074, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002977211629518312, | |
| "loss": 1.0239, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 1.3441, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002955443589413994, | |
| "loss": 1.1692, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002941892543907478, | |
| "loss": 1.3764, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.9064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002909538931178862, | |
| "loss": 1.4608, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002890775781850181, | |
| "loss": 1.0947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 1.113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.000284819106944875, | |
| "loss": 0.9546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.000282442138928839, | |
| "loss": 1.1469, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002799038105676658, | |
| "loss": 1.3102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00027720721442346387, | |
| "loss": 1.4763, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002743556358832562, | |
| "loss": 1.0281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.0988, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00026820161304100823, | |
| "loss": 1.1848, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00026490666646784665, | |
| "loss": 0.9901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00026147172382160914, | |
| "loss": 0.8676, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00025790097005079764, | |
| "loss": 1.0521, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002541987555688496, | |
| "loss": 1.0436, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 0.9511, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002464181414529809, | |
| "loss": 1.2208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002423492212988487, | |
| "loss": 1.1128, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 1.114, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00023387893552061199, | |
| "loss": 0.9318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002294878896349807, | |
| "loss": 1.6424, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.000225, | |
| "loss": 0.7759, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00022042073441788358, | |
| "loss": 0.8061, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002157556720183616, | |
| "loss": 1.2972, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00021101049646137003, | |
| "loss": 0.9694, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002061909890123868, | |
| "loss": 0.7951, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00020130302149885031, | |
| "loss": 0.8049, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.7308, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00019134560337254986, | |
| "loss": 1.4495, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00018628828433995013, | |
| "loss": 0.8338, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00018118675362266385, | |
| "loss": 0.8706, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00017604722665003956, | |
| "loss": 1.3767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0001708759651440098, | |
| "loss": 1.5032, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.000165679269490148, | |
| "loss": 1.3356, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.00016046347106161876, | |
| "loss": 1.0869, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00015523492450537517, | |
| "loss": 0.8374, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9144, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0001447650754946249, | |
| "loss": 0.7246, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00013953652893838119, | |
| "loss": 1.0432, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.000134320730509852, | |
| "loss": 0.9271, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0001291240348559902, | |
| "loss": 0.7968, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00012395277334996044, | |
| "loss": 0.9131, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00011881324637733611, | |
| "loss": 0.937, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00011371171566004985, | |
| "loss": 0.8228, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00010865439662745013, | |
| "loss": 1.0797, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.8893, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.869697850114969e-05, | |
| "loss": 0.5448, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 9.380901098761319e-05, | |
| "loss": 0.6197, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 8.898950353862998e-05, | |
| "loss": 0.6925, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 8.424432798163836e-05, | |
| "loss": 0.6065, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.957926558211642e-05, | |
| "loss": 0.9739, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 0.8073, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.051211036501928e-05, | |
| "loss": 1.5069, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.612106447938799e-05, | |
| "loss": 0.5149, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.8116, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.765077870115125e-05, | |
| "loss": 0.5185, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.358185854701909e-05, | |
| "loss": 0.8031, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 4.963040904617131e-05, | |
| "loss": 0.5611, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 4.5801244431150394e-05, | |
| "loss": 0.7082, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.209902994920235e-05, | |
| "loss": 0.8057, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.852827617839084e-05, | |
| "loss": 1.8981, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.509333353215331e-05, | |
| "loss": 0.8772, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.1798386958991714e-05, | |
| "loss": 1.1716, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.949, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.5644364116743755e-05, | |
| "loss": 0.901, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 2.2792785576536105e-05, | |
| "loss": 1.0778, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.009618943233419e-05, | |
| "loss": 1.0495, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1.755786107116095e-05, | |
| "loss": 1.1405, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.5180893055124977e-05, | |
| "loss": 0.6457, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.2968181353609852e-05, | |
| "loss": 0.7194, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.0922421814981901e-05, | |
| "loss": 0.768, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 9.046106882113751e-06, | |
| "loss": 0.7015, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 0.9132, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 5.810745609252165e-06, | |
| "loss": 0.703, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.455641058600528e-06, | |
| "loss": 0.8964, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.2778598899291465e-06, | |
| "loss": 0.9267, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.2788370481687965e-06, | |
| "loss": 0.7872, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.4597896887644456e-06, | |
| "loss": 0.7648, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 8.217156947590064e-07, | |
| "loss": 0.5883, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 3.653924610263703e-07, | |
| "loss": 0.6093, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 9.137594713563568e-08, | |
| "loss": 0.8796, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.5744, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.55142096011264e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |