| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9991537376586743, | |
| "eval_steps": 500, | |
| "global_step": 1329, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022566995768688293, | |
| "grad_norm": 1.1089675466467734, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7442, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045133991537376586, | |
| "grad_norm": 0.9032651687709552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06770098730606489, | |
| "grad_norm": 0.661414123301935, | |
| "learning_rate": 5e-06, | |
| "loss": 0.663, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09026798307475317, | |
| "grad_norm": 0.684191997191131, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11283497884344147, | |
| "grad_norm": 0.7968850136147834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13540197461212977, | |
| "grad_norm": 0.6025980511091419, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6332, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15796897038081806, | |
| "grad_norm": 0.6896440149282623, | |
| "learning_rate": 5e-06, | |
| "loss": 0.629, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18053596614950634, | |
| "grad_norm": 0.6167482460724676, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20310296191819463, | |
| "grad_norm": 0.7092392264057279, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6283, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22566995768688294, | |
| "grad_norm": 0.6757765981920996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6274, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24823695345557123, | |
| "grad_norm": 0.602546276691872, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6181, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27080394922425954, | |
| "grad_norm": 0.6184862063130019, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6173, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2933709449929478, | |
| "grad_norm": 0.9212523299186395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6186, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3159379407616361, | |
| "grad_norm": 0.6085522366969077, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6134, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3385049365303244, | |
| "grad_norm": 0.6256921238889772, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6141, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3610719322990127, | |
| "grad_norm": 0.606645633530053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6158, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.383638928067701, | |
| "grad_norm": 0.6401613005630999, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6118, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.40620592383638926, | |
| "grad_norm": 0.6243251601570871, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6088, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4287729196050776, | |
| "grad_norm": 0.6242404065068139, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6034, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4513399153737659, | |
| "grad_norm": 0.6121729700895588, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6099, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47390691114245415, | |
| "grad_norm": 0.5969802976661266, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6063, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.49647390691114246, | |
| "grad_norm": 0.6129982980567859, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5190409026798307, | |
| "grad_norm": 0.5668533739328568, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6068, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5416078984485191, | |
| "grad_norm": 0.7232774678335098, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "grad_norm": 0.6039422383722364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5998, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5867418899858956, | |
| "grad_norm": 0.7087899032677945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6025, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.609308885754584, | |
| "grad_norm": 0.553100874749091, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5979, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6318758815232722, | |
| "grad_norm": 0.66241431256307, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6046, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6544428772919605, | |
| "grad_norm": 0.832301067216732, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6770098730606487, | |
| "grad_norm": 0.9576819834043614, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6042, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6995768688293371, | |
| "grad_norm": 0.560752931056728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7221438645980254, | |
| "grad_norm": 0.5478632639125564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6005, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7447108603667136, | |
| "grad_norm": 0.5604724061444557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.767277856135402, | |
| "grad_norm": 0.5858187723986242, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5956, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7898448519040903, | |
| "grad_norm": 0.6186940151586905, | |
| "learning_rate": 5e-06, | |
| "loss": 0.597, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8124118476727785, | |
| "grad_norm": 0.580787958623627, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8349788434414669, | |
| "grad_norm": 0.6446875040901882, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6031, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8575458392101551, | |
| "grad_norm": 0.5607098113086376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5997, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8801128349788434, | |
| "grad_norm": 0.6331077663206254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9026798307475318, | |
| "grad_norm": 0.5922081888201195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.92524682651622, | |
| "grad_norm": 0.5930063432040521, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5941, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9478138222849083, | |
| "grad_norm": 0.5819547842258083, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9703808180535967, | |
| "grad_norm": 0.6092660320439263, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5886, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9929478138222849, | |
| "grad_norm": 0.7102470041653363, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5934, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9997179125528914, | |
| "eval_loss": 0.5912763476371765, | |
| "eval_runtime": 697.555, | |
| "eval_samples_per_second": 17.118, | |
| "eval_steps_per_second": 0.536, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.0155148095909732, | |
| "grad_norm": 0.7217656578243299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6009, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0380818053596614, | |
| "grad_norm": 0.5922099753160804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5282, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0606488011283497, | |
| "grad_norm": 0.6407127507440616, | |
| "learning_rate": 5e-06, | |
| "loss": 0.543, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0832157968970382, | |
| "grad_norm": 0.576580888488731, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5308, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1057827926657264, | |
| "grad_norm": 0.6154989306400179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "grad_norm": 0.5803110773211014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5399, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.150916784203103, | |
| "grad_norm": 0.6165899465430926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1734837799717912, | |
| "grad_norm": 0.5838143629087249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5336, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1960507757404795, | |
| "grad_norm": 0.6587792003103263, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5399, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2186177715091677, | |
| "grad_norm": 0.5699038771851571, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5373, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2411847672778562, | |
| "grad_norm": 0.6061015503667232, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5421, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2637517630465445, | |
| "grad_norm": 0.5832963025889784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.544, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2863187588152327, | |
| "grad_norm": 0.5816672164385919, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5412, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.308885754583921, | |
| "grad_norm": 0.5590405534898907, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3314527503526092, | |
| "grad_norm": 0.5836929150351833, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.3540197461212977, | |
| "grad_norm": 0.6281841450404138, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5464, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.376586741889986, | |
| "grad_norm": 0.8123084972654747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5391, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3991537376586742, | |
| "grad_norm": 0.5793145395265858, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5434, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4217207334273625, | |
| "grad_norm": 0.5812729927118028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5415, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4442877291960508, | |
| "grad_norm": 0.6664458859786708, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5412, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.466854724964739, | |
| "grad_norm": 0.5647691806534823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5421, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4894217207334273, | |
| "grad_norm": 0.6261523442650948, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5459, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5119887165021155, | |
| "grad_norm": 0.5871251244408628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5405, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5345557122708038, | |
| "grad_norm": 0.5429570025219707, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5346, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5571227080394923, | |
| "grad_norm": 0.6033700862868088, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5368, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5796897038081805, | |
| "grad_norm": 0.6119780310178549, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6022566995768688, | |
| "grad_norm": 0.5711515525605414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5438, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6248236953455573, | |
| "grad_norm": 0.6045746499276777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5518, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6473906911142455, | |
| "grad_norm": 0.5481917881896207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.535, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6699576868829338, | |
| "grad_norm": 0.6887524559132724, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5509, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.692524682651622, | |
| "grad_norm": 0.6373707446598362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5422, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7150916784203103, | |
| "grad_norm": 0.5959637343984598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5411, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7376586741889986, | |
| "grad_norm": 0.6663181609027282, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5418, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7602256699576868, | |
| "grad_norm": 0.6225777365866713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5377, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.782792665726375, | |
| "grad_norm": 0.5772084554676634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5413, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8053596614950633, | |
| "grad_norm": 0.5970786767490915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5363, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8279266572637518, | |
| "grad_norm": 0.6556464568292062, | |
| "learning_rate": 5e-06, | |
| "loss": 0.547, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.85049365303244, | |
| "grad_norm": 0.6665921946620136, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5344, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8730606488011283, | |
| "grad_norm": 0.6146565230270853, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5467, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8956276445698168, | |
| "grad_norm": 0.5627387129268103, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5465, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.918194640338505, | |
| "grad_norm": 0.5464136766635778, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5343, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9407616361071933, | |
| "grad_norm": 0.6141386058908015, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5394, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9633286318758816, | |
| "grad_norm": 0.6464922675747387, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5457, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9858956276445698, | |
| "grad_norm": 0.6921324613776051, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5441, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9994358251057829, | |
| "eval_loss": 0.587400496006012, | |
| "eval_runtime": 695.1905, | |
| "eval_samples_per_second": 17.177, | |
| "eval_steps_per_second": 0.538, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 2.008462623413258, | |
| "grad_norm": 1.1610399960653068, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0310296191819464, | |
| "grad_norm": 0.6487581234182378, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4787, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0535966149506346, | |
| "grad_norm": 0.6328774131189219, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4804, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.076163610719323, | |
| "grad_norm": 0.6041122255586804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4728, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.098730606488011, | |
| "grad_norm": 0.6042930918406503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4803, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1212976022566994, | |
| "grad_norm": 0.6007680878710548, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4843, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.143864598025388, | |
| "grad_norm": 0.5977697264779503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4861, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1664315937940763, | |
| "grad_norm": 0.6224632801497896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4824, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.1889985895627646, | |
| "grad_norm": 0.7298479275194018, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4807, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.211565585331453, | |
| "grad_norm": 0.6192992961102274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.476, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.234132581100141, | |
| "grad_norm": 0.580537121968891, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4757, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2566995768688294, | |
| "grad_norm": 0.59921408257906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4848, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2792665726375176, | |
| "grad_norm": 0.6091899429354127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.491, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.301833568406206, | |
| "grad_norm": 0.710504212436636, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4853, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.324400564174894, | |
| "grad_norm": 0.6579165047877594, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4897, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3469675599435824, | |
| "grad_norm": 0.6639077938288619, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4875, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.3695345557122707, | |
| "grad_norm": 0.6130071384626814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4853, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.392101551480959, | |
| "grad_norm": 0.6666570081599825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4848, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.414668547249647, | |
| "grad_norm": 0.7611806796886672, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4857, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4372355430183354, | |
| "grad_norm": 0.7898919198900027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4891, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.459802538787024, | |
| "grad_norm": 0.5773849556240105, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4871, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.4823695345557124, | |
| "grad_norm": 0.6135977931263356, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4902, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5049365303244007, | |
| "grad_norm": 0.594132854203967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4934, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.527503526093089, | |
| "grad_norm": 0.6537675061104099, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4841, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.550070521861777, | |
| "grad_norm": 0.7811576129975868, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4891, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5726375176304654, | |
| "grad_norm": 0.5924950779737967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4874, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5952045133991537, | |
| "grad_norm": 0.6437126383257294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4884, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.617771509167842, | |
| "grad_norm": 0.618147281886192, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4921, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.64033850493653, | |
| "grad_norm": 0.6453257647203345, | |
| "learning_rate": 5e-06, | |
| "loss": 0.481, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.6629055007052185, | |
| "grad_norm": 0.632332824068504, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4918, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.685472496473907, | |
| "grad_norm": 0.5721042513789194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4925, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.7080394922425954, | |
| "grad_norm": 0.6132070533315946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4911, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7306064880112837, | |
| "grad_norm": 0.5673966352972261, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4924, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.753173483779972, | |
| "grad_norm": 0.5773699546800514, | |
| "learning_rate": 5e-06, | |
| "loss": 0.489, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.77574047954866, | |
| "grad_norm": 0.5857505263001362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4955, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.7983074753173485, | |
| "grad_norm": 0.6473498773975065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4938, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8208744710860367, | |
| "grad_norm": 0.5740719012369875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4941, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.843441466854725, | |
| "grad_norm": 0.561559067194783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4958, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8660084626234132, | |
| "grad_norm": 0.5993497581530252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4928, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.8885754583921015, | |
| "grad_norm": 0.5741956451302742, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4909, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9111424541607898, | |
| "grad_norm": 0.5947983449561617, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4946, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.933709449929478, | |
| "grad_norm": 0.5946148545340252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4902, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9562764456981663, | |
| "grad_norm": 0.6578162427861818, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4939, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.9788434414668545, | |
| "grad_norm": 0.575594449194069, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4904, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "eval_loss": 0.6002166867256165, | |
| "eval_runtime": 700.2243, | |
| "eval_samples_per_second": 17.053, | |
| "eval_steps_per_second": 0.534, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "step": 1329, | |
| "total_flos": 5064195066298368.0, | |
| "train_loss": 0.5481024000140579, | |
| "train_runtime": 121980.0389, | |
| "train_samples_per_second": 5.58, | |
| "train_steps_per_second": 0.011 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1329, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5064195066298368.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |