| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5078125, | |
| "eval_steps": 39, | |
| "global_step": 195, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026041666666666665, | |
| "grad_norm": 0.3952034496250024, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026041666666666665, | |
| "eval_loss": 2.554558753967285, | |
| "eval_runtime": 65.1161, | |
| "eval_samples_per_second": 1.229, | |
| "eval_steps_per_second": 0.154, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005208333333333333, | |
| "grad_norm": 0.3885918424668888, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4825, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0078125, | |
| "grad_norm": 0.3847099050493279, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.5035, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010416666666666666, | |
| "grad_norm": 0.4235545463515579, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5577, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013020833333333334, | |
| "grad_norm": 0.3801745772810421, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.5297, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "grad_norm": 0.3512277500716236, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018229166666666668, | |
| "grad_norm": 0.28888015786994375, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.4556, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 0.25350975750236143, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5022, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0234375, | |
| "grad_norm": 0.22691977505165736, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.4143, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "grad_norm": 0.20864896327745933, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028645833333333332, | |
| "grad_norm": 0.20008113121425344, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.4939, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 0.24785418789288546, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3184, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.033854166666666664, | |
| "grad_norm": 0.2153715911656377, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 2.4738, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036458333333333336, | |
| "grad_norm": 0.22249287774026938, | |
| "learning_rate": 7e-05, | |
| "loss": 2.4814, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 0.2076426443768558, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3529, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 0.2246776060857838, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2371, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.044270833333333336, | |
| "grad_norm": 0.18383862266336323, | |
| "learning_rate": 8.5e-05, | |
| "loss": 2.4787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 0.20631688287583885, | |
| "learning_rate": 9e-05, | |
| "loss": 2.6178, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.049479166666666664, | |
| "grad_norm": 0.18016643348558348, | |
| "learning_rate": 9.5e-05, | |
| "loss": 2.4891, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.052083333333333336, | |
| "grad_norm": 0.14534618682097772, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4522, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0546875, | |
| "grad_norm": 0.15428537805246717, | |
| "learning_rate": 9.999832398924833e-05, | |
| "loss": 2.4111, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057291666666666664, | |
| "grad_norm": 0.1631103718894274, | |
| "learning_rate": 9.999329608183822e-05, | |
| "loss": 2.387, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.059895833333333336, | |
| "grad_norm": 0.1552602669275131, | |
| "learning_rate": 9.998491665229539e-05, | |
| "loss": 2.3648, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.1704183704935776, | |
| "learning_rate": 9.997318632479817e-05, | |
| "loss": 2.4997, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06510416666666667, | |
| "grad_norm": 0.1585395745370806, | |
| "learning_rate": 9.995810597313128e-05, | |
| "loss": 2.5326, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06770833333333333, | |
| "grad_norm": 0.1344528253347993, | |
| "learning_rate": 9.993967672062052e-05, | |
| "loss": 2.5174, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0703125, | |
| "grad_norm": 0.14705487245235002, | |
| "learning_rate": 9.991789994004929e-05, | |
| "loss": 2.3446, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07291666666666667, | |
| "grad_norm": 0.1461054029585455, | |
| "learning_rate": 9.989277725355615e-05, | |
| "loss": 2.4945, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07552083333333333, | |
| "grad_norm": 0.14508526627249885, | |
| "learning_rate": 9.986431053251411e-05, | |
| "loss": 2.3801, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "grad_norm": 0.14473824067661442, | |
| "learning_rate": 9.983250189739119e-05, | |
| "loss": 2.4877, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08072916666666667, | |
| "grad_norm": 0.18945595196350265, | |
| "learning_rate": 9.97973537175925e-05, | |
| "loss": 2.5833, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.1541697712272958, | |
| "learning_rate": 9.975886861128368e-05, | |
| "loss": 2.4619, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0859375, | |
| "grad_norm": 0.16052736172586615, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 2.5037, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08854166666666667, | |
| "grad_norm": 0.15543243937875972, | |
| "learning_rate": 9.967189933441243e-05, | |
| "loss": 2.4374, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09114583333333333, | |
| "grad_norm": 0.16705335802827087, | |
| "learning_rate": 9.962342164213639e-05, | |
| "loss": 2.5955, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 0.14789348505066385, | |
| "learning_rate": 9.957161997944034e-05, | |
| "loss": 2.4322, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09635416666666667, | |
| "grad_norm": 0.15495422007897772, | |
| "learning_rate": 9.95164982049974e-05, | |
| "loss": 2.4307, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09895833333333333, | |
| "grad_norm": 0.15049524925558916, | |
| "learning_rate": 9.94580604247936e-05, | |
| "loss": 2.3423, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1015625, | |
| "grad_norm": 0.1444251980172912, | |
| "learning_rate": 9.939631099182219e-05, | |
| "loss": 2.2882, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1015625, | |
| "eval_loss": 2.4301750659942627, | |
| "eval_runtime": 65.3323, | |
| "eval_samples_per_second": 1.225, | |
| "eval_steps_per_second": 0.153, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 0.1475367612200888, | |
| "learning_rate": 9.933125450575932e-05, | |
| "loss": 2.4509, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10677083333333333, | |
| "grad_norm": 0.16356380426266176, | |
| "learning_rate": 9.926289581262147e-05, | |
| "loss": 2.5307, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.109375, | |
| "grad_norm": 0.166302003601292, | |
| "learning_rate": 9.919124000440438e-05, | |
| "loss": 2.526, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11197916666666667, | |
| "grad_norm": 0.14645402434215465, | |
| "learning_rate": 9.91162924187038e-05, | |
| "loss": 2.2958, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11458333333333333, | |
| "grad_norm": 0.2119539720051403, | |
| "learning_rate": 9.903805863831799e-05, | |
| "loss": 2.3299, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1171875, | |
| "grad_norm": 0.151653634781893, | |
| "learning_rate": 9.895654449083166e-05, | |
| "loss": 2.4133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11979166666666667, | |
| "grad_norm": 0.1547044553169797, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 2.5952, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12239583333333333, | |
| "grad_norm": 0.16664262013704687, | |
| "learning_rate": 9.87836996262066e-05, | |
| "loss": 2.4714, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.15551192268579045, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 2.3432, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12760416666666666, | |
| "grad_norm": 0.14968525834314664, | |
| "learning_rate": 9.859780932428756e-05, | |
| "loss": 2.4037, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13020833333333334, | |
| "grad_norm": 0.1685655914159011, | |
| "learning_rate": 9.849998929119488e-05, | |
| "loss": 2.4032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1328125, | |
| "grad_norm": 0.13644233785328275, | |
| "learning_rate": 9.839892897144663e-05, | |
| "loss": 2.4095, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13541666666666666, | |
| "grad_norm": 0.14364815720124613, | |
| "learning_rate": 9.829463589296203e-05, | |
| "loss": 2.4398, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13802083333333334, | |
| "grad_norm": 0.14915929369602085, | |
| "learning_rate": 9.818711782446645e-05, | |
| "loss": 2.4816, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.140625, | |
| "grad_norm": 0.14935461072359194, | |
| "learning_rate": 9.80763827749127e-05, | |
| "loss": 2.3426, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14322916666666666, | |
| "grad_norm": 0.15190176296605723, | |
| "learning_rate": 9.796243899288456e-05, | |
| "loss": 2.4705, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14583333333333334, | |
| "grad_norm": 0.14303795896023264, | |
| "learning_rate": 9.784529496598214e-05, | |
| "loss": 2.5108, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1484375, | |
| "grad_norm": 0.1556316812368993, | |
| "learning_rate": 9.772495942018985e-05, | |
| "loss": 2.3112, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15104166666666666, | |
| "grad_norm": 0.1483632196038671, | |
| "learning_rate": 9.760144131922628e-05, | |
| "loss": 2.2325, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15364583333333334, | |
| "grad_norm": 0.12410345584803052, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 2.3749, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.16335694957610425, | |
| "learning_rate": 9.734489449130695e-05, | |
| "loss": 2.4645, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15885416666666666, | |
| "grad_norm": 0.1479375196060614, | |
| "learning_rate": 9.721188487436195e-05, | |
| "loss": 2.3834, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.16145833333333334, | |
| "grad_norm": 0.13750323689269844, | |
| "learning_rate": 9.707573092084368e-05, | |
| "loss": 2.3592, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1640625, | |
| "grad_norm": 0.16027916915470333, | |
| "learning_rate": 9.693644277277391e-05, | |
| "loss": 2.4954, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.14229365410212697, | |
| "learning_rate": 9.679403080563861e-05, | |
| "loss": 2.4404, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16927083333333334, | |
| "grad_norm": 0.153686499622388, | |
| "learning_rate": 9.6648505627615e-05, | |
| "loss": 2.2282, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.171875, | |
| "grad_norm": 0.16590644992700104, | |
| "learning_rate": 9.649987807878148e-05, | |
| "loss": 2.5126, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17447916666666666, | |
| "grad_norm": 0.15502972088699477, | |
| "learning_rate": 9.634815923030997e-05, | |
| "loss": 2.3749, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17708333333333334, | |
| "grad_norm": 0.14756465898580834, | |
| "learning_rate": 9.61933603836415e-05, | |
| "loss": 2.3476, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1796875, | |
| "grad_norm": 0.14919525754908758, | |
| "learning_rate": 9.603549306964407e-05, | |
| "loss": 2.3509, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.18229166666666666, | |
| "grad_norm": 0.13861494211266717, | |
| "learning_rate": 9.587456904775393e-05, | |
| "loss": 2.2449, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18489583333333334, | |
| "grad_norm": 0.14821518394829722, | |
| "learning_rate": 9.57106003050996e-05, | |
| "loss": 2.3813, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.16324527196573113, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 2.477, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.19010416666666666, | |
| "grad_norm": 0.14892748528676938, | |
| "learning_rate": 9.537357773909906e-05, | |
| "loss": 2.264, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.19270833333333334, | |
| "grad_norm": 0.1284546434475265, | |
| "learning_rate": 9.520054902035035e-05, | |
| "loss": 2.4267, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1953125, | |
| "grad_norm": 0.14293551215488642, | |
| "learning_rate": 9.502452578816244e-05, | |
| "loss": 2.5131, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19791666666666666, | |
| "grad_norm": 0.14775108859068506, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 2.4076, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.20052083333333334, | |
| "grad_norm": 0.15478800535673032, | |
| "learning_rate": 9.466354845298817e-05, | |
| "loss": 2.5762, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.203125, | |
| "grad_norm": 0.16835921991226063, | |
| "learning_rate": 9.44786212389749e-05, | |
| "loss": 2.3752, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.203125, | |
| "eval_loss": 2.4171054363250732, | |
| "eval_runtime": 65.4109, | |
| "eval_samples_per_second": 1.223, | |
| "eval_steps_per_second": 0.153, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.20572916666666666, | |
| "grad_norm": 0.14467889640535875, | |
| "learning_rate": 9.42907532874657e-05, | |
| "loss": 2.4769, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 0.13503613492125413, | |
| "learning_rate": 9.40999585926253e-05, | |
| "loss": 2.4346, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2109375, | |
| "grad_norm": 0.1517728973900508, | |
| "learning_rate": 9.390625136662972e-05, | |
| "loss": 2.261, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.21354166666666666, | |
| "grad_norm": 0.1466563383653839, | |
| "learning_rate": 9.370964603860753e-05, | |
| "loss": 2.5261, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21614583333333334, | |
| "grad_norm": 0.14618631155344838, | |
| "learning_rate": 9.351015725356514e-05, | |
| "loss": 2.4269, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 0.15601390292939937, | |
| "learning_rate": 9.33077998712958e-05, | |
| "loss": 2.3773, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.22135416666666666, | |
| "grad_norm": 0.14415725413526403, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 2.3473, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22395833333333334, | |
| "grad_norm": 0.13470412653239092, | |
| "learning_rate": 9.289453982152653e-05, | |
| "loss": 2.3472, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2265625, | |
| "grad_norm": 0.15570776289510233, | |
| "learning_rate": 9.2683667937506e-05, | |
| "loss": 2.4414, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22916666666666666, | |
| "grad_norm": 0.14612626399487072, | |
| "learning_rate": 9.246998902092428e-05, | |
| "loss": 2.4655, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.23177083333333334, | |
| "grad_norm": 0.18267625807633459, | |
| "learning_rate": 9.22535189885886e-05, | |
| "loss": 2.2771, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.234375, | |
| "grad_norm": 0.16065010725957032, | |
| "learning_rate": 9.203427396521454e-05, | |
| "loss": 2.4194, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23697916666666666, | |
| "grad_norm": 0.18321820032984756, | |
| "learning_rate": 9.181227028222508e-05, | |
| "loss": 2.4456, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23958333333333334, | |
| "grad_norm": 0.13929464732035163, | |
| "learning_rate": 9.158752447653397e-05, | |
| "loss": 2.3989, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2421875, | |
| "grad_norm": 0.15585898969003706, | |
| "learning_rate": 9.136005328931395e-05, | |
| "loss": 2.4777, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.24479166666666666, | |
| "grad_norm": 0.14793073723102618, | |
| "learning_rate": 9.112987366474972e-05, | |
| "loss": 2.379, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.24739583333333334, | |
| "grad_norm": 0.14075868568691305, | |
| "learning_rate": 9.089700274877574e-05, | |
| "loss": 2.3281, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.15327339815586916, | |
| "learning_rate": 9.066145788779908e-05, | |
| "loss": 2.4517, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2526041666666667, | |
| "grad_norm": 0.15505433166839452, | |
| "learning_rate": 9.042325662740726e-05, | |
| "loss": 2.2919, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2552083333333333, | |
| "grad_norm": 0.1468856057426848, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 2.3889, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2578125, | |
| "grad_norm": 0.1478488710337695, | |
| "learning_rate": 8.993895607877418e-05, | |
| "loss": 2.3595, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2604166666666667, | |
| "grad_norm": 0.175359520279898, | |
| "learning_rate": 8.969289286577408e-05, | |
| "loss": 2.553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2630208333333333, | |
| "grad_norm": 0.14503182442700818, | |
| "learning_rate": 8.9444245401154e-05, | |
| "loss": 2.3573, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.265625, | |
| "grad_norm": 0.14177870868430487, | |
| "learning_rate": 8.919303220650606e-05, | |
| "loss": 2.3274, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2682291666666667, | |
| "grad_norm": 0.1779007031093982, | |
| "learning_rate": 8.893927199454207e-05, | |
| "loss": 2.2008, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2708333333333333, | |
| "grad_norm": 0.14578869126284813, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 2.444, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2734375, | |
| "grad_norm": 0.14046914929392473, | |
| "learning_rate": 8.842418631673365e-05, | |
| "loss": 2.2844, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2760416666666667, | |
| "grad_norm": 0.13720708755401478, | |
| "learning_rate": 8.816289921929516e-05, | |
| "loss": 2.5047, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2786458333333333, | |
| "grad_norm": 0.13901967393067377, | |
| "learning_rate": 8.789914183849449e-05, | |
| "loss": 2.4602, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 0.14165507438668587, | |
| "learning_rate": 8.763293382145195e-05, | |
| "loss": 2.3135, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2838541666666667, | |
| "grad_norm": 0.1588574639328753, | |
| "learning_rate": 8.73642949978341e-05, | |
| "loss": 2.3731, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.2864583333333333, | |
| "grad_norm": 0.1905241886636867, | |
| "learning_rate": 8.709324537837684e-05, | |
| "loss": 2.4152, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2890625, | |
| "grad_norm": 0.16919809232424363, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.2948, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.2916666666666667, | |
| "grad_norm": 0.15114015395920236, | |
| "learning_rate": 8.654399469127673e-05, | |
| "loss": 2.4309, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2942708333333333, | |
| "grad_norm": 0.13890547261939354, | |
| "learning_rate": 8.626583453696976e-05, | |
| "loss": 2.4866, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.296875, | |
| "grad_norm": 0.1490334985258922, | |
| "learning_rate": 8.598534541044747e-05, | |
| "loss": 2.4748, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2994791666666667, | |
| "grad_norm": 0.15113023404371403, | |
| "learning_rate": 8.570254820516728e-05, | |
| "loss": 2.3583, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3020833333333333, | |
| "grad_norm": 0.14358757342098682, | |
| "learning_rate": 8.541746398651395e-05, | |
| "loss": 2.4005, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.3046875, | |
| "grad_norm": 0.1494340804949735, | |
| "learning_rate": 8.513011399023036e-05, | |
| "loss": 2.3249, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.3046875, | |
| "eval_loss": 2.4119415283203125, | |
| "eval_runtime": 65.4329, | |
| "eval_samples_per_second": 1.223, | |
| "eval_steps_per_second": 0.153, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.3072916666666667, | |
| "grad_norm": 0.14857253164474957, | |
| "learning_rate": 8.484051962083579e-05, | |
| "loss": 2.3431, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.3098958333333333, | |
| "grad_norm": 0.14191988741229736, | |
| "learning_rate": 8.454870245003141e-05, | |
| "loss": 2.3861, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.1516024307266096, | |
| "learning_rate": 8.425468421509349e-05, | |
| "loss": 2.411, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3151041666666667, | |
| "grad_norm": 0.15002982823803926, | |
| "learning_rate": 8.395848681725416e-05, | |
| "loss": 2.49, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3177083333333333, | |
| "grad_norm": 0.14904411125984457, | |
| "learning_rate": 8.366013232007002e-05, | |
| "loss": 2.2998, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3203125, | |
| "grad_norm": 0.15513959182528284, | |
| "learning_rate": 8.335964294777862e-05, | |
| "loss": 2.4748, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.3229166666666667, | |
| "grad_norm": 0.16028597088352084, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 2.5415, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3255208333333333, | |
| "grad_norm": 0.1382845005964039, | |
| "learning_rate": 8.275234926828446e-05, | |
| "loss": 2.3863, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.328125, | |
| "grad_norm": 0.13146327268638525, | |
| "learning_rate": 8.244559019800328e-05, | |
| "loss": 2.2718, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3307291666666667, | |
| "grad_norm": 0.14918540441469405, | |
| "learning_rate": 8.213678672308841e-05, | |
| "loss": 2.29, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.14572964949235084, | |
| "learning_rate": 8.182596184611514e-05, | |
| "loss": 2.3865, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3359375, | |
| "grad_norm": 0.1467709610422986, | |
| "learning_rate": 8.151313872023172e-05, | |
| "loss": 2.3566, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.3385416666666667, | |
| "grad_norm": 0.1696428030171741, | |
| "learning_rate": 8.119834064743469e-05, | |
| "loss": 2.4145, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3411458333333333, | |
| "grad_norm": 0.1567212274267596, | |
| "learning_rate": 8.088159107683314e-05, | |
| "loss": 2.3996, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 0.16059171688564705, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 2.4796, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3463541666666667, | |
| "grad_norm": 0.17528470844982455, | |
| "learning_rate": 8.024233196372453e-05, | |
| "loss": 2.3711, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.3489583333333333, | |
| "grad_norm": 0.15733889602776618, | |
| "learning_rate": 7.9919870039224e-05, | |
| "loss": 2.2677, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3515625, | |
| "grad_norm": 0.14873870088112393, | |
| "learning_rate": 7.959555184938495e-05, | |
| "loss": 2.4515, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3541666666666667, | |
| "grad_norm": 0.15417965735327782, | |
| "learning_rate": 7.926940155246397e-05, | |
| "loss": 2.4285, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3567708333333333, | |
| "grad_norm": 0.1431617281765595, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 2.2096, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.359375, | |
| "grad_norm": 0.1582812354896834, | |
| "learning_rate": 7.861170195095537e-05, | |
| "loss": 2.5397, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3619791666666667, | |
| "grad_norm": 0.17372786439002758, | |
| "learning_rate": 7.828020163799455e-05, | |
| "loss": 2.4293, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.3645833333333333, | |
| "grad_norm": 0.12985922414383083, | |
| "learning_rate": 7.794696719755612e-05, | |
| "loss": 2.3064, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3671875, | |
| "grad_norm": 0.14444453543114258, | |
| "learning_rate": 7.761202345206249e-05, | |
| "loss": 2.4924, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.3697916666666667, | |
| "grad_norm": 0.14361378320872797, | |
| "learning_rate": 7.727539535126118e-05, | |
| "loss": 2.485, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.3723958333333333, | |
| "grad_norm": 0.14506765397834698, | |
| "learning_rate": 7.69371079703662e-05, | |
| "loss": 2.4081, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.15082242594669004, | |
| "learning_rate": 7.65971865081904e-05, | |
| "loss": 2.4042, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3776041666666667, | |
| "grad_norm": 0.14811116555183387, | |
| "learning_rate": 7.625565628526818e-05, | |
| "loss": 2.5335, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3802083333333333, | |
| "grad_norm": 0.14726265807121236, | |
| "learning_rate": 7.591254274196959e-05, | |
| "loss": 2.2424, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.3828125, | |
| "grad_norm": 0.1582839530592079, | |
| "learning_rate": 7.556787143660521e-05, | |
| "loss": 2.3499, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.3854166666666667, | |
| "grad_norm": 0.15670436913091046, | |
| "learning_rate": 7.522166804352226e-05, | |
| "loss": 2.4295, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3880208333333333, | |
| "grad_norm": 0.14730612216140554, | |
| "learning_rate": 7.487395835119231e-05, | |
| "loss": 2.3101, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.390625, | |
| "grad_norm": 0.15120580103738476, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 2.4888, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3932291666666667, | |
| "grad_norm": 0.15081791485599214, | |
| "learning_rate": 7.417412378176446e-05, | |
| "loss": 2.3946, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.3958333333333333, | |
| "grad_norm": 0.13244742107918075, | |
| "learning_rate": 7.382205103490043e-05, | |
| "loss": 2.2704, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3984375, | |
| "grad_norm": 0.14571632653572605, | |
| "learning_rate": 7.346857624537407e-05, | |
| "loss": 2.4644, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.4010416666666667, | |
| "grad_norm": 0.15252862923031207, | |
| "learning_rate": 7.311372574329854e-05, | |
| "loss": 2.554, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.4036458333333333, | |
| "grad_norm": 0.14927980854491554, | |
| "learning_rate": 7.275752596126308e-05, | |
| "loss": 2.3804, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 0.1406590744757482, | |
| "learning_rate": 7.240000343236385e-05, | |
| "loss": 2.2504, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "eval_loss": 2.408146619796753, | |
| "eval_runtime": 65.4856, | |
| "eval_samples_per_second": 1.222, | |
| "eval_steps_per_second": 0.153, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.4088541666666667, | |
| "grad_norm": 0.13753178031418029, | |
| "learning_rate": 7.204118478822766e-05, | |
| "loss": 2.3063, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.4114583333333333, | |
| "grad_norm": 0.13719355865812055, | |
| "learning_rate": 7.168109675702806e-05, | |
| "loss": 2.1826, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.4140625, | |
| "grad_norm": 0.14916916897375052, | |
| "learning_rate": 7.131976616149445e-05, | |
| "loss": 2.3635, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 0.1544520288957668, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 2.6067, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4192708333333333, | |
| "grad_norm": 0.1466811081471814, | |
| "learning_rate": 7.05934850291272e-05, | |
| "loss": 2.2636, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.421875, | |
| "grad_norm": 0.14245354657490636, | |
| "learning_rate": 7.022858859251517e-05, | |
| "loss": 2.3278, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4244791666666667, | |
| "grad_norm": 0.14310350882179557, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 2.2951, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.4270833333333333, | |
| "grad_norm": 0.15028525220062852, | |
| "learning_rate": 6.949541988093208e-05, | |
| "loss": 2.3647, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4296875, | |
| "grad_norm": 0.13536590220383313, | |
| "learning_rate": 6.912720221923405e-05, | |
| "loss": 2.3635, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4322916666666667, | |
| "grad_norm": 0.14965390120450028, | |
| "learning_rate": 6.875793223118888e-05, | |
| "loss": 2.3191, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.4348958333333333, | |
| "grad_norm": 0.15696846625410496, | |
| "learning_rate": 6.838763742348415e-05, | |
| "loss": 2.4342, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.16266249005182767, | |
| "learning_rate": 6.801634537914555e-05, | |
| "loss": 2.4487, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4401041666666667, | |
| "grad_norm": 0.15099304315918932, | |
| "learning_rate": 6.764408375548237e-05, | |
| "loss": 2.4774, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.4427083333333333, | |
| "grad_norm": 0.1437502300792439, | |
| "learning_rate": 6.727088028202723e-05, | |
| "loss": 2.4369, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4453125, | |
| "grad_norm": 0.13339677555582233, | |
| "learning_rate": 6.68967627584705e-05, | |
| "loss": 2.3039, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.4479166666666667, | |
| "grad_norm": 0.1416720700803862, | |
| "learning_rate": 6.652175905258963e-05, | |
| "loss": 2.2844, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4505208333333333, | |
| "grad_norm": 0.14502909820943563, | |
| "learning_rate": 6.614589709817317e-05, | |
| "loss": 2.4192, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.453125, | |
| "grad_norm": 0.14499193575249233, | |
| "learning_rate": 6.576920489294011e-05, | |
| "loss": 2.3057, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.4557291666666667, | |
| "grad_norm": 0.15038851044223103, | |
| "learning_rate": 6.539171049645426e-05, | |
| "loss": 2.4237, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4583333333333333, | |
| "grad_norm": 0.14553942382157312, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 2.4642, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.4609375, | |
| "grad_norm": 0.13896484063095102, | |
| "learning_rate": 6.463442766465847e-05, | |
| "loss": 2.4132, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.4635416666666667, | |
| "grad_norm": 0.14978646915320232, | |
| "learning_rate": 6.425469563886715e-05, | |
| "loss": 2.3692, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.4661458333333333, | |
| "grad_norm": 0.13794418734075914, | |
| "learning_rate": 6.387427423665829e-05, | |
| "loss": 2.3524, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.1467143240226456, | |
| "learning_rate": 6.349319179538126e-05, | |
| "loss": 2.359, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4713541666666667, | |
| "grad_norm": 0.14326937356779176, | |
| "learning_rate": 6.311147670162576e-05, | |
| "loss": 2.5547, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.4739583333333333, | |
| "grad_norm": 0.141220074236358, | |
| "learning_rate": 6.272915738910743e-05, | |
| "loss": 2.4299, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.4765625, | |
| "grad_norm": 0.148901889828269, | |
| "learning_rate": 6.234626233654973e-05, | |
| "loss": 2.5296, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.4791666666666667, | |
| "grad_norm": 0.15238094995154358, | |
| "learning_rate": 6.196282006556266e-05, | |
| "loss": 2.2642, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4817708333333333, | |
| "grad_norm": 0.14562487124583376, | |
| "learning_rate": 6.157885913851818e-05, | |
| "loss": 2.2485, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.484375, | |
| "grad_norm": 0.1557482340822006, | |
| "learning_rate": 6.119440815642258e-05, | |
| "loss": 2.5018, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.4869791666666667, | |
| "grad_norm": 0.15557904288598579, | |
| "learning_rate": 6.080949575678606e-05, | |
| "loss": 2.3121, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.4895833333333333, | |
| "grad_norm": 0.132624820989215, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 2.4456, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.4921875, | |
| "grad_norm": 0.14540093060758663, | |
| "learning_rate": 6.003840142464886e-05, | |
| "loss": 2.4166, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.4947916666666667, | |
| "grad_norm": 0.13698817848218522, | |
| "learning_rate": 5.9652276930476656e-05, | |
| "loss": 2.4569, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4973958333333333, | |
| "grad_norm": 0.13530133541335626, | |
| "learning_rate": 5.926580589114201e-05, | |
| "loss": 2.521, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.13985911131684764, | |
| "learning_rate": 5.8879017094627874e-05, | |
| "loss": 2.4112, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.5026041666666666, | |
| "grad_norm": 0.13203633038116566, | |
| "learning_rate": 5.849193935258679e-05, | |
| "loss": 2.1839, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.5052083333333334, | |
| "grad_norm": 0.16221179568567085, | |
| "learning_rate": 5.810460149819462e-05, | |
| "loss": 2.2793, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.5078125, | |
| "grad_norm": 0.15402021583934355, | |
| "learning_rate": 5.771703238400288e-05, | |
| "loss": 2.3905, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5078125, | |
| "eval_loss": 2.4029593467712402, | |
| "eval_runtime": 65.2935, | |
| "eval_samples_per_second": 1.225, | |
| "eval_steps_per_second": 0.153, | |
| "step": 195 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 384, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 39, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 64462761492480.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |