{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9932885906040269, "eval_steps": 500, "global_step": 111, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008948545861297539, "grad_norm": Infinity, "learning_rate": 4e-05, "loss": 2.5209, "step": 1 }, { "epoch": 0.017897091722595078, "grad_norm": Infinity, "learning_rate": 8e-05, "loss": 2.3763, "step": 2 }, { "epoch": 0.026845637583892617, "grad_norm": Infinity, "learning_rate": 0.00012, "loss": 2.4052, "step": 3 }, { "epoch": 0.035794183445190156, "grad_norm": Infinity, "learning_rate": 0.00016, "loss": 2.3638, "step": 4 }, { "epoch": 0.0447427293064877, "grad_norm": Infinity, "learning_rate": 0.0002, "loss": 2.4036, "step": 5 }, { "epoch": 0.053691275167785234, "grad_norm": Infinity, "learning_rate": 0.00019995608365087946, "loss": 2.356, "step": 6 }, { "epoch": 0.06263982102908278, "grad_norm": Infinity, "learning_rate": 0.00019982437317643217, "loss": 2.3205, "step": 7 }, { "epoch": 0.07158836689038031, "grad_norm": Infinity, "learning_rate": 0.0001996049842615217, "loss": 2.3699, "step": 8 }, { "epoch": 0.08053691275167785, "grad_norm": Infinity, "learning_rate": 0.00019929810960135172, "loss": 2.3722, "step": 9 }, { "epoch": 0.0894854586129754, "grad_norm": Infinity, "learning_rate": 0.0001989040187322164, "loss": 2.4075, "step": 10 }, { "epoch": 0.09843400447427293, "grad_norm": Infinity, "learning_rate": 0.00019842305779475968, "loss": 2.3877, "step": 11 }, { "epoch": 0.10738255033557047, "grad_norm": Infinity, "learning_rate": 0.0001978556492299504, "loss": 2.3471, "step": 12 }, { "epoch": 0.116331096196868, "grad_norm": Infinity, "learning_rate": 0.0001972022914080411, "loss": 2.3465, "step": 13 }, { "epoch": 0.12527964205816555, "grad_norm": Infinity, "learning_rate": 0.00019646355819083589, "loss": 2.3472, "step": 14 }, { "epoch": 0.1342281879194631, "grad_norm": Infinity, "learning_rate": 0.00019564009842765225, "loss": 2.3, "step": 15 }, { "epoch": 0.14317673378076062, "grad_norm": Infinity, "learning_rate": 0.00019473263538541914, "loss": 2.3641, "step": 16 }, { "epoch": 0.15212527964205816, "grad_norm": Infinity, "learning_rate": 0.0001937419661134121, "loss": 2.2752, "step": 17 }, { "epoch": 0.1610738255033557, "grad_norm": Infinity, "learning_rate": 0.00019266896074318334, "loss": 2.3554, "step": 18 }, { "epoch": 0.17002237136465326, "grad_norm": Infinity, "learning_rate": 0.00019151456172430183, "loss": 2.3903, "step": 19 }, { "epoch": 0.1789709172259508, "grad_norm": Infinity, "learning_rate": 0.00019027978299657436, "loss": 2.3386, "step": 20 }, { "epoch": 0.18791946308724833, "grad_norm": Infinity, "learning_rate": 0.00018896570909947475, "loss": 2.2683, "step": 21 }, { "epoch": 0.19686800894854586, "grad_norm": Infinity, "learning_rate": 0.0001875734942195637, "loss": 2.3581, "step": 22 }, { "epoch": 0.2058165548098434, "grad_norm": Infinity, "learning_rate": 0.00018610436117673555, "loss": 2.4238, "step": 23 }, { "epoch": 0.21476510067114093, "grad_norm": Infinity, "learning_rate": 0.0001845596003501826, "loss": 2.3498, "step": 24 }, { "epoch": 0.22371364653243847, "grad_norm": Infinity, "learning_rate": 0.0001829405685450202, "loss": 2.3951, "step": 25 }, { "epoch": 0.232662192393736, "grad_norm": Infinity, "learning_rate": 0.00018124868780056814, "loss": 2.3998, "step": 26 }, { "epoch": 0.24161073825503357, "grad_norm": Infinity, "learning_rate": 0.00017948544414133534, "loss": 2.3576, "step": 27 }, { "epoch": 0.2505592841163311, "grad_norm": Infinity, "learning_rate": 0.00017765238627180424, "loss": 2.4546, "step": 28 }, { "epoch": 0.2595078299776286, "grad_norm": Infinity, "learning_rate": 0.00017575112421616202, "loss": 2.4187, "step": 29 }, { "epoch": 0.2684563758389262, "grad_norm": Infinity, "learning_rate": 0.00017378332790417273, "loss": 2.3181, "step": 30 }, { "epoch": 0.27740492170022374, "grad_norm": Infinity, "learning_rate": 0.00017175072570443312, "loss": 2.2427, "step": 31 }, { "epoch": 0.28635346756152125, "grad_norm": Infinity, "learning_rate": 0.00016965510290629972, "loss": 2.2389, "step": 32 }, { "epoch": 0.2953020134228188, "grad_norm": Infinity, "learning_rate": 0.00016749830015182107, "loss": 2.2622, "step": 33 }, { "epoch": 0.3042505592841163, "grad_norm": Infinity, "learning_rate": 0.00016528221181905217, "loss": 2.3253, "step": 34 }, { "epoch": 0.3131991051454139, "grad_norm": Infinity, "learning_rate": 0.00016300878435817113, "loss": 2.3176, "step": 35 }, { "epoch": 0.3221476510067114, "grad_norm": Infinity, "learning_rate": 0.00016068001458185936, "loss": 2.3296, "step": 36 }, { "epoch": 0.33109619686800895, "grad_norm": Infinity, "learning_rate": 0.0001582979479114472, "loss": 2.3007, "step": 37 }, { "epoch": 0.3400447427293065, "grad_norm": Infinity, "learning_rate": 0.00015586467658036524, "loss": 2.3147, "step": 38 }, { "epoch": 0.348993288590604, "grad_norm": Infinity, "learning_rate": 0.0001533823377964791, "loss": 2.4518, "step": 39 }, { "epoch": 0.3579418344519016, "grad_norm": Infinity, "learning_rate": 0.00015085311186492206, "loss": 2.3307, "step": 40 }, { "epoch": 0.3668903803131991, "grad_norm": Infinity, "learning_rate": 0.00014827922027307451, "loss": 2.3834, "step": 41 }, { "epoch": 0.37583892617449666, "grad_norm": Infinity, "learning_rate": 0.0001456629237393713, "loss": 2.4204, "step": 42 }, { "epoch": 0.38478747203579416, "grad_norm": Infinity, "learning_rate": 0.00014300652022765207, "loss": 2.3773, "step": 43 }, { "epoch": 0.39373601789709173, "grad_norm": Infinity, "learning_rate": 0.00014031234292879725, "loss": 2.4166, "step": 44 }, { "epoch": 0.40268456375838924, "grad_norm": Infinity, "learning_rate": 0.00013758275821142382, "loss": 2.2125, "step": 45 }, { "epoch": 0.4116331096196868, "grad_norm": Infinity, "learning_rate": 0.0001348201635434399, "loss": 2.54, "step": 46 }, { "epoch": 0.42058165548098436, "grad_norm": Infinity, "learning_rate": 0.00013202698538628376, "loss": 2.2798, "step": 47 }, { "epoch": 0.42953020134228187, "grad_norm": Infinity, "learning_rate": 0.00012920567706369758, "loss": 2.4098, "step": 48 }, { "epoch": 0.43847874720357943, "grad_norm": Infinity, "learning_rate": 0.00012635871660690676, "loss": 2.291, "step": 49 }, { "epoch": 0.44742729306487694, "grad_norm": Infinity, "learning_rate": 0.00012348860457809838, "loss": 2.4545, "step": 50 }, { "epoch": 0.4563758389261745, "grad_norm": Infinity, "learning_rate": 0.00012059786187410984, "loss": 2.2959, "step": 51 }, { "epoch": 0.465324384787472, "grad_norm": Infinity, "learning_rate": 0.0001176890275122573, "loss": 2.3574, "step": 52 }, { "epoch": 0.4742729306487696, "grad_norm": Infinity, "learning_rate": 0.00011476465640024814, "loss": 2.406, "step": 53 }, { "epoch": 0.48322147651006714, "grad_norm": Infinity, "learning_rate": 0.00011182731709213659, "loss": 2.4389, "step": 54 }, { "epoch": 0.49217002237136465, "grad_norm": Infinity, "learning_rate": 0.00010887958953229349, "loss": 2.3658, "step": 55 }, { "epoch": 0.5011185682326622, "grad_norm": Infinity, "learning_rate": 0.00010592406278937144, "loss": 2.3528, "step": 56 }, { "epoch": 0.5100671140939598, "grad_norm": Infinity, "learning_rate": 0.00010296333278225599, "loss": 2.4212, "step": 57 }, { "epoch": 0.5190156599552572, "grad_norm": Infinity, "learning_rate": 0.0001, "loss": 2.3734, "step": 58 }, { "epoch": 0.5279642058165548, "grad_norm": Infinity, "learning_rate": 9.703666721774402e-05, "loss": 2.4072, "step": 59 }, { "epoch": 0.5369127516778524, "grad_norm": Infinity, "learning_rate": 9.407593721062859e-05, "loss": 2.284, "step": 60 }, { "epoch": 0.5458612975391499, "grad_norm": Infinity, "learning_rate": 9.112041046770653e-05, "loss": 2.3904, "step": 61 }, { "epoch": 0.5548098434004475, "grad_norm": Infinity, "learning_rate": 8.817268290786343e-05, "loss": 2.3897, "step": 62 }, { "epoch": 0.5637583892617449, "grad_norm": Infinity, "learning_rate": 8.523534359975189e-05, "loss": 2.3225, "step": 63 }, { "epoch": 0.5727069351230425, "grad_norm": Infinity, "learning_rate": 8.231097248774274e-05, "loss": 2.2408, "step": 64 }, { "epoch": 0.5816554809843401, "grad_norm": Infinity, "learning_rate": 7.940213812589018e-05, "loss": 2.282, "step": 65 }, { "epoch": 0.5906040268456376, "grad_norm": Infinity, "learning_rate": 7.651139542190164e-05, "loss": 2.3552, "step": 66 }, { "epoch": 0.5995525727069351, "grad_norm": Infinity, "learning_rate": 7.364128339309326e-05, "loss": 2.3491, "step": 67 }, { "epoch": 0.6085011185682326, "grad_norm": Infinity, "learning_rate": 7.079432293630244e-05, "loss": 2.3222, "step": 68 }, { "epoch": 0.6174496644295302, "grad_norm": Infinity, "learning_rate": 6.797301461371625e-05, "loss": 2.3866, "step": 69 }, { "epoch": 0.6263982102908278, "grad_norm": Infinity, "learning_rate": 6.517983645656014e-05, "loss": 2.3404, "step": 70 }, { "epoch": 0.6353467561521253, "grad_norm": Infinity, "learning_rate": 6.24172417885762e-05, "loss": 2.3076, "step": 71 }, { "epoch": 0.6442953020134228, "grad_norm": Infinity, "learning_rate": 5.96876570712028e-05, "loss": 2.2991, "step": 72 }, { "epoch": 0.6532438478747203, "grad_norm": Infinity, "learning_rate": 5.699347977234799e-05, "loss": 2.3487, "step": 73 }, { "epoch": 0.6621923937360179, "grad_norm": Infinity, "learning_rate": 5.43370762606287e-05, "loss": 2.3273, "step": 74 }, { "epoch": 0.6711409395973155, "grad_norm": Infinity, "learning_rate": 5.172077972692553e-05, "loss": 2.3829, "step": 75 }, { "epoch": 0.680089485458613, "grad_norm": Infinity, "learning_rate": 4.914688813507797e-05, "loss": 2.3727, "step": 76 }, { "epoch": 0.6890380313199105, "grad_norm": Infinity, "learning_rate": 4.661766220352097e-05, "loss": 2.3296, "step": 77 }, { "epoch": 0.697986577181208, "grad_norm": Infinity, "learning_rate": 4.4135323419634766e-05, "loss": 2.3478, "step": 78 }, { "epoch": 0.7069351230425056, "grad_norm": Infinity, "learning_rate": 4.170205208855281e-05, "loss": 2.228, "step": 79 }, { "epoch": 0.7158836689038032, "grad_norm": Infinity, "learning_rate": 3.931998541814069e-05, "loss": 2.3218, "step": 80 }, { "epoch": 0.7248322147651006, "grad_norm": Infinity, "learning_rate": 3.69912156418289e-05, "loss": 2.302, "step": 81 }, { "epoch": 0.7337807606263982, "grad_norm": Infinity, "learning_rate": 3.471778818094785e-05, "loss": 2.4534, "step": 82 }, { "epoch": 0.7427293064876958, "grad_norm": Infinity, "learning_rate": 3.250169984817897e-05, "loss": 2.4143, "step": 83 }, { "epoch": 0.7516778523489933, "grad_norm": Infinity, "learning_rate": 3.034489709370033e-05, "loss": 2.4148, "step": 84 }, { "epoch": 0.7606263982102909, "grad_norm": Infinity, "learning_rate": 2.8249274295566864e-05, "loss": 2.3943, "step": 85 }, { "epoch": 0.7695749440715883, "grad_norm": Infinity, "learning_rate": 2.6216672095827266e-05, "loss": 2.3216, "step": 86 }, { "epoch": 0.7785234899328859, "grad_norm": Infinity, "learning_rate": 2.4248875783837987e-05, "loss": 2.3203, "step": 87 }, { "epoch": 0.7874720357941835, "grad_norm": Infinity, "learning_rate": 2.234761372819577e-05, "loss": 2.243, "step": 88 }, { "epoch": 0.796420581655481, "grad_norm": Infinity, "learning_rate": 2.0514555858664663e-05, "loss": 2.393, "step": 89 }, { "epoch": 0.8053691275167785, "grad_norm": Infinity, "learning_rate": 1.875131219943187e-05, "loss": 2.3419, "step": 90 }, { "epoch": 0.814317673378076, "grad_norm": Infinity, "learning_rate": 1.7059431454979824e-05, "loss": 2.4027, "step": 91 }, { "epoch": 0.8232662192393736, "grad_norm": Infinity, "learning_rate": 1.5440399649817385e-05, "loss": 2.2473, "step": 92 }, { "epoch": 0.8322147651006712, "grad_norm": Infinity, "learning_rate": 1.3895638823264446e-05, "loss": 2.4251, "step": 93 }, { "epoch": 0.8411633109619687, "grad_norm": Infinity, "learning_rate": 1.2426505780436326e-05, "loss": 2.2876, "step": 94 }, { "epoch": 0.8501118568232662, "grad_norm": Infinity, "learning_rate": 1.103429090052528e-05, "loss": 2.2836, "step": 95 }, { "epoch": 0.8590604026845637, "grad_norm": Infinity, "learning_rate": 9.720217003425647e-06, "loss": 2.4119, "step": 96 }, { "epoch": 0.8680089485458613, "grad_norm": Infinity, "learning_rate": 8.485438275698154e-06, "loss": 2.3938, "step": 97 }, { "epoch": 0.8769574944071589, "grad_norm": Infinity, "learning_rate": 7.331039256816663e-06, "loss": 2.315, "step": 98 }, { "epoch": 0.8859060402684564, "grad_norm": Infinity, "learning_rate": 6.258033886587911e-06, "loss": 2.3633, "step": 99 }, { "epoch": 0.8948545861297539, "grad_norm": Infinity, "learning_rate": 5.267364614580861e-06, "loss": 2.4346, "step": 100 }, { "epoch": 0.9038031319910514, "grad_norm": Infinity, "learning_rate": 4.359901572347758e-06, "loss": 2.3044, "step": 101 }, { "epoch": 0.912751677852349, "grad_norm": Infinity, "learning_rate": 3.5364418091641373e-06, "loss": 2.3033, "step": 102 }, { "epoch": 0.9217002237136466, "grad_norm": Infinity, "learning_rate": 2.7977085919589254e-06, "loss": 2.4251, "step": 103 }, { "epoch": 0.930648769574944, "grad_norm": Infinity, "learning_rate": 2.144350770049597e-06, "loss": 2.3084, "step": 104 }, { "epoch": 0.9395973154362416, "grad_norm": Infinity, "learning_rate": 1.576942205240317e-06, "loss": 2.4026, "step": 105 }, { "epoch": 0.9485458612975392, "grad_norm": Infinity, "learning_rate": 1.0959812677835968e-06, "loss": 2.3017, "step": 106 }, { "epoch": 0.9574944071588367, "grad_norm": Infinity, "learning_rate": 7.018903986483083e-07, "loss": 2.3852, "step": 107 }, { "epoch": 0.9664429530201343, "grad_norm": Infinity, "learning_rate": 3.950157384783104e-07, "loss": 2.3078, "step": 108 }, { "epoch": 0.9753914988814317, "grad_norm": Infinity, "learning_rate": 1.7562682356786487e-07, "loss": 2.3399, "step": 109 }, { "epoch": 0.9843400447427293, "grad_norm": Infinity, "learning_rate": 4.391634912056519e-08, "loss": 2.295, "step": 110 }, { "epoch": 0.9932885906040269, "grad_norm": Infinity, "learning_rate": 0.0, "loss": 2.4105, "step": 111 }, { "epoch": 0.9932885906040269, "eval_loss": 2.663038492202759, "eval_runtime": 443.7515, "eval_samples_per_second": 23.493, "eval_steps_per_second": 2.939, "step": 111 } ], "logging_steps": 1, "max_steps": 111, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.250921952103629e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }