| { | |
| "best_metric": 0.1869634985923767, | |
| "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2350", | |
| "epoch": 1.0047267355982274, | |
| "eval_steps": 50, | |
| "global_step": 3401, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014771048744460858, | |
| "grad_norm": 10.597820832195618, | |
| "learning_rate": 1.4749262536873157e-06, | |
| "loss": 1.8844, | |
| "num_input_tokens_seen": 52288, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029542097488921715, | |
| "grad_norm": 10.631406320216014, | |
| "learning_rate": 2.9498525073746313e-06, | |
| "loss": 1.9494, | |
| "num_input_tokens_seen": 103976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004431314623338257, | |
| "grad_norm": 9.455384953384051, | |
| "learning_rate": 4.424778761061947e-06, | |
| "loss": 1.995, | |
| "num_input_tokens_seen": 155560, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005908419497784343, | |
| "grad_norm": 21.163264642835454, | |
| "learning_rate": 5.899705014749263e-06, | |
| "loss": 2.0327, | |
| "num_input_tokens_seen": 206520, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007385524372230428, | |
| "grad_norm": 10.023350257859445, | |
| "learning_rate": 7.374631268436579e-06, | |
| "loss": 1.9153, | |
| "num_input_tokens_seen": 258464, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008862629246676515, | |
| "grad_norm": 10.512071286717141, | |
| "learning_rate": 8.849557522123894e-06, | |
| "loss": 1.9723, | |
| "num_input_tokens_seen": 309800, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0103397341211226, | |
| "grad_norm": 11.56445556664387, | |
| "learning_rate": 1.032448377581121e-05, | |
| "loss": 1.6646, | |
| "num_input_tokens_seen": 361216, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011816838995568686, | |
| "grad_norm": 12.04717354860619, | |
| "learning_rate": 1.1799410029498525e-05, | |
| "loss": 1.7057, | |
| "num_input_tokens_seen": 412680, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013293943870014771, | |
| "grad_norm": 4.748411551761613, | |
| "learning_rate": 1.3274336283185843e-05, | |
| "loss": 1.4552, | |
| "num_input_tokens_seen": 464640, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014771048744460856, | |
| "grad_norm": 7.526687970196985, | |
| "learning_rate": 1.4749262536873157e-05, | |
| "loss": 1.3918, | |
| "num_input_tokens_seen": 516240, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014771048744460856, | |
| "eval_loss": 1.042170763015747, | |
| "eval_runtime": 48.777, | |
| "eval_samples_per_second": 1.23, | |
| "eval_steps_per_second": 0.308, | |
| "num_input_tokens_seen": 516240, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01624815361890694, | |
| "grad_norm": 5.812969222976318, | |
| "learning_rate": 1.6224188790560475e-05, | |
| "loss": 1.2308, | |
| "num_input_tokens_seen": 567536, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01772525849335303, | |
| "grad_norm": 2.497864489287105, | |
| "learning_rate": 1.7699115044247787e-05, | |
| "loss": 1.0922, | |
| "num_input_tokens_seen": 619392, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019202363367799114, | |
| "grad_norm": 1.4292999616096396, | |
| "learning_rate": 1.9174041297935107e-05, | |
| "loss": 0.9517, | |
| "num_input_tokens_seen": 671168, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0206794682422452, | |
| "grad_norm": 1.5696921990486115, | |
| "learning_rate": 2.064896755162242e-05, | |
| "loss": 0.9277, | |
| "num_input_tokens_seen": 722464, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.022156573116691284, | |
| "grad_norm": 2.288073027990093, | |
| "learning_rate": 2.2123893805309738e-05, | |
| "loss": 0.8741, | |
| "num_input_tokens_seen": 774120, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.023633677991137372, | |
| "grad_norm": 2.658756604981594, | |
| "learning_rate": 2.359882005899705e-05, | |
| "loss": 0.8837, | |
| "num_input_tokens_seen": 825944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.025110782865583457, | |
| "grad_norm": 2.142324288581783, | |
| "learning_rate": 2.5073746312684367e-05, | |
| "loss": 0.8658, | |
| "num_input_tokens_seen": 877632, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.026587887740029542, | |
| "grad_norm": 1.4822847258427907, | |
| "learning_rate": 2.6548672566371686e-05, | |
| "loss": 0.8626, | |
| "num_input_tokens_seen": 928664, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.028064992614475627, | |
| "grad_norm": 1.2798949826045687, | |
| "learning_rate": 2.8023598820059e-05, | |
| "loss": 0.828, | |
| "num_input_tokens_seen": 980120, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.029542097488921712, | |
| "grad_norm": 1.0072961699690943, | |
| "learning_rate": 2.9498525073746314e-05, | |
| "loss": 0.8208, | |
| "num_input_tokens_seen": 1030696, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.029542097488921712, | |
| "eval_loss": 0.8917127847671509, | |
| "eval_runtime": 19.2166, | |
| "eval_samples_per_second": 3.122, | |
| "eval_steps_per_second": 0.781, | |
| "num_input_tokens_seen": 1030696, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0310192023633678, | |
| "grad_norm": 1.8545776603803357, | |
| "learning_rate": 3.097345132743363e-05, | |
| "loss": 0.8858, | |
| "num_input_tokens_seen": 1083184, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.03249630723781388, | |
| "grad_norm": 1.5328827906971274, | |
| "learning_rate": 3.244837758112095e-05, | |
| "loss": 0.8395, | |
| "num_input_tokens_seen": 1135216, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.033973412112259974, | |
| "grad_norm": 1.2347057774721741, | |
| "learning_rate": 3.3923303834808265e-05, | |
| "loss": 0.8729, | |
| "num_input_tokens_seen": 1187592, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.03545051698670606, | |
| "grad_norm": 1.478939426983387, | |
| "learning_rate": 3.5398230088495574e-05, | |
| "loss": 0.8534, | |
| "num_input_tokens_seen": 1239544, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03692762186115214, | |
| "grad_norm": 1.7015290012303235, | |
| "learning_rate": 3.687315634218289e-05, | |
| "loss": 0.8621, | |
| "num_input_tokens_seen": 1291496, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03840472673559823, | |
| "grad_norm": 1.1767502699022077, | |
| "learning_rate": 3.834808259587021e-05, | |
| "loss": 0.8548, | |
| "num_input_tokens_seen": 1344704, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03988183161004431, | |
| "grad_norm": 0.8775651985355217, | |
| "learning_rate": 3.982300884955752e-05, | |
| "loss": 0.8555, | |
| "num_input_tokens_seen": 1396432, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0413589364844904, | |
| "grad_norm": 1.0196921729702504, | |
| "learning_rate": 4.129793510324484e-05, | |
| "loss": 0.8503, | |
| "num_input_tokens_seen": 1448304, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.04283604135893648, | |
| "grad_norm": 1.0316734242866998, | |
| "learning_rate": 4.2772861356932154e-05, | |
| "loss": 0.7974, | |
| "num_input_tokens_seen": 1500480, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.04431314623338257, | |
| "grad_norm": 1.3815092616140325, | |
| "learning_rate": 4.4247787610619477e-05, | |
| "loss": 0.8125, | |
| "num_input_tokens_seen": 1550792, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04431314623338257, | |
| "eval_loss": 0.9009397625923157, | |
| "eval_runtime": 19.1097, | |
| "eval_samples_per_second": 3.14, | |
| "eval_steps_per_second": 0.785, | |
| "num_input_tokens_seen": 1550792, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04579025110782865, | |
| "grad_norm": 0.9311064643035706, | |
| "learning_rate": 4.5722713864306786e-05, | |
| "loss": 0.8444, | |
| "num_input_tokens_seen": 1602680, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.047267355982274745, | |
| "grad_norm": 0.8826375779686524, | |
| "learning_rate": 4.71976401179941e-05, | |
| "loss": 0.8832, | |
| "num_input_tokens_seen": 1655184, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04874446085672083, | |
| "grad_norm": 1.7104989113767923, | |
| "learning_rate": 4.867256637168142e-05, | |
| "loss": 0.8428, | |
| "num_input_tokens_seen": 1707544, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.050221565731166914, | |
| "grad_norm": 1.0884565315781036, | |
| "learning_rate": 5.014749262536873e-05, | |
| "loss": 0.8235, | |
| "num_input_tokens_seen": 1759296, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.051698670605613, | |
| "grad_norm": 1.2821380368908926, | |
| "learning_rate": 5.162241887905604e-05, | |
| "loss": 0.8293, | |
| "num_input_tokens_seen": 1812488, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.053175775480059084, | |
| "grad_norm": 1.8069978017028316, | |
| "learning_rate": 5.309734513274337e-05, | |
| "loss": 0.8284, | |
| "num_input_tokens_seen": 1864408, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05465288035450517, | |
| "grad_norm": 1.3165540148767247, | |
| "learning_rate": 5.457227138643069e-05, | |
| "loss": 0.8268, | |
| "num_input_tokens_seen": 1916744, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.056129985228951254, | |
| "grad_norm": 1.5174910847154595, | |
| "learning_rate": 5.6047197640118e-05, | |
| "loss": 0.8153, | |
| "num_input_tokens_seen": 1968128, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05760709010339734, | |
| "grad_norm": 1.4410901045723357, | |
| "learning_rate": 5.752212389380531e-05, | |
| "loss": 0.8123, | |
| "num_input_tokens_seen": 2019312, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.059084194977843424, | |
| "grad_norm": 1.5417669370284124, | |
| "learning_rate": 5.899705014749263e-05, | |
| "loss": 0.7675, | |
| "num_input_tokens_seen": 2071176, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.059084194977843424, | |
| "eval_loss": 0.9007444977760315, | |
| "eval_runtime": 19.0725, | |
| "eval_samples_per_second": 3.146, | |
| "eval_steps_per_second": 0.786, | |
| "num_input_tokens_seen": 2071176, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.060561299852289516, | |
| "grad_norm": 3.485842845243708, | |
| "learning_rate": 6.0471976401179945e-05, | |
| "loss": 0.8075, | |
| "num_input_tokens_seen": 2122328, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.0620384047267356, | |
| "grad_norm": 1.9945831681716613, | |
| "learning_rate": 6.194690265486725e-05, | |
| "loss": 0.8207, | |
| "num_input_tokens_seen": 2174744, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.06351550960118169, | |
| "grad_norm": 2.5224102035468907, | |
| "learning_rate": 6.342182890855458e-05, | |
| "loss": 0.7867, | |
| "num_input_tokens_seen": 2227136, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.06499261447562776, | |
| "grad_norm": 2.7703394460607833, | |
| "learning_rate": 6.48967551622419e-05, | |
| "loss": 0.8256, | |
| "num_input_tokens_seen": 2278568, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06646971935007386, | |
| "grad_norm": 4.676590157125056, | |
| "learning_rate": 6.637168141592921e-05, | |
| "loss": 0.7897, | |
| "num_input_tokens_seen": 2330224, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.06794682422451995, | |
| "grad_norm": 1.6101062596215647, | |
| "learning_rate": 6.784660766961653e-05, | |
| "loss": 0.792, | |
| "num_input_tokens_seen": 2381344, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06942392909896603, | |
| "grad_norm": 3.202676293331468, | |
| "learning_rate": 6.932153392330384e-05, | |
| "loss": 0.8309, | |
| "num_input_tokens_seen": 2432136, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.07090103397341212, | |
| "grad_norm": 1.3573723032246008, | |
| "learning_rate": 7.079646017699115e-05, | |
| "loss": 0.7974, | |
| "num_input_tokens_seen": 2483568, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0723781388478582, | |
| "grad_norm": 1.317885929036595, | |
| "learning_rate": 7.227138643067847e-05, | |
| "loss": 0.7739, | |
| "num_input_tokens_seen": 2535040, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.07385524372230429, | |
| "grad_norm": 2.1810508869311067, | |
| "learning_rate": 7.374631268436578e-05, | |
| "loss": 0.7558, | |
| "num_input_tokens_seen": 2587272, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07385524372230429, | |
| "eval_loss": 0.810763955116272, | |
| "eval_runtime": 19.1642, | |
| "eval_samples_per_second": 3.131, | |
| "eval_steps_per_second": 0.783, | |
| "num_input_tokens_seen": 2587272, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07533234859675036, | |
| "grad_norm": 2.353270620583961, | |
| "learning_rate": 7.522123893805309e-05, | |
| "loss": 0.7851, | |
| "num_input_tokens_seen": 2638632, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.07680945347119646, | |
| "grad_norm": 3.0664271713541873, | |
| "learning_rate": 7.669616519174043e-05, | |
| "loss": 0.7211, | |
| "num_input_tokens_seen": 2691016, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07828655834564253, | |
| "grad_norm": 5.498034008223314, | |
| "learning_rate": 7.817109144542774e-05, | |
| "loss": 0.8082, | |
| "num_input_tokens_seen": 2742912, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.07976366322008863, | |
| "grad_norm": 14.573947499657416, | |
| "learning_rate": 7.964601769911504e-05, | |
| "loss": 0.7485, | |
| "num_input_tokens_seen": 2795264, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.08124076809453472, | |
| "grad_norm": 3.007807281619928, | |
| "learning_rate": 8.112094395280237e-05, | |
| "loss": 0.7454, | |
| "num_input_tokens_seen": 2846344, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.0827178729689808, | |
| "grad_norm": 6.015750773450144, | |
| "learning_rate": 8.259587020648968e-05, | |
| "loss": 0.7258, | |
| "num_input_tokens_seen": 2898304, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08419497784342689, | |
| "grad_norm": 2.390238834834483, | |
| "learning_rate": 8.4070796460177e-05, | |
| "loss": 0.7863, | |
| "num_input_tokens_seen": 2951368, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.08567208271787297, | |
| "grad_norm": 3.0216023427899357, | |
| "learning_rate": 8.554572271386431e-05, | |
| "loss": 0.7105, | |
| "num_input_tokens_seen": 3003288, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.08714918759231906, | |
| "grad_norm": 3.255437171887138, | |
| "learning_rate": 8.702064896755162e-05, | |
| "loss": 0.6885, | |
| "num_input_tokens_seen": 3054808, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.08862629246676514, | |
| "grad_norm": 3.506440325367033, | |
| "learning_rate": 8.849557522123895e-05, | |
| "loss": 0.78, | |
| "num_input_tokens_seen": 3107200, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08862629246676514, | |
| "eval_loss": 0.8194220662117004, | |
| "eval_runtime": 19.1748, | |
| "eval_samples_per_second": 3.129, | |
| "eval_steps_per_second": 0.782, | |
| "num_input_tokens_seen": 3107200, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09010339734121123, | |
| "grad_norm": 2.2491377996087385, | |
| "learning_rate": 8.997050147492626e-05, | |
| "loss": 0.7394, | |
| "num_input_tokens_seen": 3158648, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.0915805022156573, | |
| "grad_norm": 8.740989037358858, | |
| "learning_rate": 9.144542772861357e-05, | |
| "loss": 0.7371, | |
| "num_input_tokens_seen": 3210560, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0930576070901034, | |
| "grad_norm": 4.552322042735297, | |
| "learning_rate": 9.29203539823009e-05, | |
| "loss": 0.7622, | |
| "num_input_tokens_seen": 3263664, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.09453471196454949, | |
| "grad_norm": 5.062297996808734, | |
| "learning_rate": 9.43952802359882e-05, | |
| "loss": 0.7214, | |
| "num_input_tokens_seen": 3315520, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09601181683899557, | |
| "grad_norm": 4.295724990139621, | |
| "learning_rate": 9.587020648967551e-05, | |
| "loss": 0.7078, | |
| "num_input_tokens_seen": 3368088, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.09748892171344166, | |
| "grad_norm": 7.980776602247676, | |
| "learning_rate": 9.734513274336283e-05, | |
| "loss": 0.6852, | |
| "num_input_tokens_seen": 3420176, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.09896602658788774, | |
| "grad_norm": 33.51326353666061, | |
| "learning_rate": 9.882005899705014e-05, | |
| "loss": 0.7557, | |
| "num_input_tokens_seen": 3471184, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.10044313146233383, | |
| "grad_norm": 4.612370523858782, | |
| "learning_rate": 9.99999940340072e-05, | |
| "loss": 0.6709, | |
| "num_input_tokens_seen": 3523008, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.1019202363367799, | |
| "grad_norm": 3.706129373980499, | |
| "learning_rate": 9.999978522440803e-05, | |
| "loss": 0.7252, | |
| "num_input_tokens_seen": 3573880, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.103397341211226, | |
| "grad_norm": 4.907030070826967, | |
| "learning_rate": 9.999927811659165e-05, | |
| "loss": 0.6602, | |
| "num_input_tokens_seen": 3625752, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.103397341211226, | |
| "eval_loss": 0.7663387656211853, | |
| "eval_runtime": 19.2114, | |
| "eval_samples_per_second": 3.123, | |
| "eval_steps_per_second": 0.781, | |
| "num_input_tokens_seen": 3625752, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10487444608567208, | |
| "grad_norm": 21.440776172892136, | |
| "learning_rate": 9.999847271358347e-05, | |
| "loss": 0.7222, | |
| "num_input_tokens_seen": 3676984, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.10635155096011817, | |
| "grad_norm": 3.9046938348237252, | |
| "learning_rate": 9.99973690201885e-05, | |
| "loss": 0.6639, | |
| "num_input_tokens_seen": 3729168, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10782865583456426, | |
| "grad_norm": 5.783088469074539, | |
| "learning_rate": 9.999596704299139e-05, | |
| "loss": 0.6501, | |
| "num_input_tokens_seen": 3780672, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.10930576070901034, | |
| "grad_norm": 4.421078404189889, | |
| "learning_rate": 9.999426679035628e-05, | |
| "loss": 0.6871, | |
| "num_input_tokens_seen": 3832328, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.11078286558345643, | |
| "grad_norm": 6.348668054760613, | |
| "learning_rate": 9.99922682724269e-05, | |
| "loss": 0.6621, | |
| "num_input_tokens_seen": 3883112, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.11225997045790251, | |
| "grad_norm": 3.7958066942788573, | |
| "learning_rate": 9.998997150112635e-05, | |
| "loss": 0.7156, | |
| "num_input_tokens_seen": 3934976, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1137370753323486, | |
| "grad_norm": 2.694693287446712, | |
| "learning_rate": 9.998737649015718e-05, | |
| "loss": 0.6662, | |
| "num_input_tokens_seen": 3986192, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.11521418020679468, | |
| "grad_norm": 6.428397441401454, | |
| "learning_rate": 9.998448325500118e-05, | |
| "loss": 0.682, | |
| "num_input_tokens_seen": 4037760, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.11669128508124077, | |
| "grad_norm": 6.165388347571309, | |
| "learning_rate": 9.998129181291936e-05, | |
| "loss": 0.6137, | |
| "num_input_tokens_seen": 4090872, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.11816838995568685, | |
| "grad_norm": 4.354814876263017, | |
| "learning_rate": 9.997780218295185e-05, | |
| "loss": 0.6739, | |
| "num_input_tokens_seen": 4142592, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11816838995568685, | |
| "eval_loss": 0.7038857936859131, | |
| "eval_runtime": 19.0624, | |
| "eval_samples_per_second": 3.148, | |
| "eval_steps_per_second": 0.787, | |
| "num_input_tokens_seen": 4142592, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11964549483013294, | |
| "grad_norm": 4.400494365327609, | |
| "learning_rate": 9.997401438591772e-05, | |
| "loss": 0.6209, | |
| "num_input_tokens_seen": 4194920, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.12112259970457903, | |
| "grad_norm": 4.518582133930376, | |
| "learning_rate": 9.996992844441495e-05, | |
| "loss": 0.6576, | |
| "num_input_tokens_seen": 4247048, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.12259970457902511, | |
| "grad_norm": 2.6773114089558043, | |
| "learning_rate": 9.996554438282022e-05, | |
| "loss": 0.6851, | |
| "num_input_tokens_seen": 4299728, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.1240768094534712, | |
| "grad_norm": 10.583849604294256, | |
| "learning_rate": 9.996086222728879e-05, | |
| "loss": 0.6288, | |
| "num_input_tokens_seen": 4351088, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1255539143279173, | |
| "grad_norm": 5.18430085456359, | |
| "learning_rate": 9.995588200575439e-05, | |
| "loss": 0.667, | |
| "num_input_tokens_seen": 4403016, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.12703101920236337, | |
| "grad_norm": 3.624202284960618, | |
| "learning_rate": 9.995060374792892e-05, | |
| "loss": 0.6747, | |
| "num_input_tokens_seen": 4453880, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.12850812407680945, | |
| "grad_norm": 8.193068077958594, | |
| "learning_rate": 9.994502748530244e-05, | |
| "loss": 0.6594, | |
| "num_input_tokens_seen": 4505616, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.12998522895125553, | |
| "grad_norm": 6.0681139183306145, | |
| "learning_rate": 9.993915325114288e-05, | |
| "loss": 0.6727, | |
| "num_input_tokens_seen": 4558384, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.13146233382570163, | |
| "grad_norm": 3.998790148445953, | |
| "learning_rate": 9.993298108049582e-05, | |
| "loss": 0.6526, | |
| "num_input_tokens_seen": 4611184, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.1329394387001477, | |
| "grad_norm": 3.1838689643423392, | |
| "learning_rate": 9.992651101018445e-05, | |
| "loss": 0.5661, | |
| "num_input_tokens_seen": 4663320, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1329394387001477, | |
| "eval_loss": 0.7132604718208313, | |
| "eval_runtime": 18.996, | |
| "eval_samples_per_second": 3.159, | |
| "eval_steps_per_second": 0.79, | |
| "num_input_tokens_seen": 4663320, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1344165435745938, | |
| "grad_norm": 8.239876852269616, | |
| "learning_rate": 9.991974307880907e-05, | |
| "loss": 0.5954, | |
| "num_input_tokens_seen": 4714448, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.1358936484490399, | |
| "grad_norm": 21.47914479659389, | |
| "learning_rate": 9.991267732674711e-05, | |
| "loss": 0.721, | |
| "num_input_tokens_seen": 4767136, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13737075332348597, | |
| "grad_norm": 7.30460731660639, | |
| "learning_rate": 9.99053137961528e-05, | |
| "loss": 0.6578, | |
| "num_input_tokens_seen": 4819408, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.13884785819793205, | |
| "grad_norm": 8.944279395571234, | |
| "learning_rate": 9.989765253095686e-05, | |
| "loss": 0.6642, | |
| "num_input_tokens_seen": 4872120, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.14032496307237813, | |
| "grad_norm": 20.451510949854647, | |
| "learning_rate": 9.988969357686636e-05, | |
| "loss": 0.6462, | |
| "num_input_tokens_seen": 4924400, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.14180206794682423, | |
| "grad_norm": 6.498846626456819, | |
| "learning_rate": 9.988143698136429e-05, | |
| "loss": 0.6055, | |
| "num_input_tokens_seen": 4976504, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1432791728212703, | |
| "grad_norm": 9.137509561710141, | |
| "learning_rate": 9.987288279370945e-05, | |
| "loss": 0.5928, | |
| "num_input_tokens_seen": 5028648, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.1447562776957164, | |
| "grad_norm": 6.8502382033465885, | |
| "learning_rate": 9.986403106493604e-05, | |
| "loss": 0.5835, | |
| "num_input_tokens_seen": 5080488, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.14623338257016247, | |
| "grad_norm": 6.731902879463201, | |
| "learning_rate": 9.985488184785336e-05, | |
| "loss": 0.6641, | |
| "num_input_tokens_seen": 5131744, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.14771048744460857, | |
| "grad_norm": 5.718986997919185, | |
| "learning_rate": 9.984543519704557e-05, | |
| "loss": 0.6283, | |
| "num_input_tokens_seen": 5183664, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14771048744460857, | |
| "eval_loss": 0.6505001187324524, | |
| "eval_runtime": 18.9372, | |
| "eval_samples_per_second": 3.168, | |
| "eval_steps_per_second": 0.792, | |
| "num_input_tokens_seen": 5183664, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14918759231905465, | |
| "grad_norm": 11.975231950682153, | |
| "learning_rate": 9.983569116887128e-05, | |
| "loss": 0.573, | |
| "num_input_tokens_seen": 5234920, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.15066469719350073, | |
| "grad_norm": 13.701425113518031, | |
| "learning_rate": 9.982564982146327e-05, | |
| "loss": 0.6261, | |
| "num_input_tokens_seen": 5287312, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.15214180206794684, | |
| "grad_norm": 6.956866723254775, | |
| "learning_rate": 9.981531121472811e-05, | |
| "loss": 0.6072, | |
| "num_input_tokens_seen": 5340240, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.1536189069423929, | |
| "grad_norm": 5.293847645949678, | |
| "learning_rate": 9.980467541034584e-05, | |
| "loss": 0.565, | |
| "num_input_tokens_seen": 5392600, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.155096011816839, | |
| "grad_norm": 3.5333148010719357, | |
| "learning_rate": 9.979374247176956e-05, | |
| "loss": 0.6188, | |
| "num_input_tokens_seen": 5445168, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.15657311669128507, | |
| "grad_norm": 2.715838950258193, | |
| "learning_rate": 9.978251246422505e-05, | |
| "loss": 0.6069, | |
| "num_input_tokens_seen": 5496384, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.15805022156573117, | |
| "grad_norm": 7.400638197441027, | |
| "learning_rate": 9.977098545471046e-05, | |
| "loss": 0.5805, | |
| "num_input_tokens_seen": 5548264, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.15952732644017725, | |
| "grad_norm": 8.936418653401088, | |
| "learning_rate": 9.975916151199579e-05, | |
| "loss": 0.6383, | |
| "num_input_tokens_seen": 5599216, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.16100443131462333, | |
| "grad_norm": 7.142901090509074, | |
| "learning_rate": 9.974704070662254e-05, | |
| "loss": 0.5845, | |
| "num_input_tokens_seen": 5650816, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.16248153618906944, | |
| "grad_norm": 18.523556086651276, | |
| "learning_rate": 9.973462311090336e-05, | |
| "loss": 0.5957, | |
| "num_input_tokens_seen": 5703016, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.16248153618906944, | |
| "eval_loss": 0.6883422136306763, | |
| "eval_runtime": 19.183, | |
| "eval_samples_per_second": 3.128, | |
| "eval_steps_per_second": 0.782, | |
| "num_input_tokens_seen": 5703016, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.16395864106351551, | |
| "grad_norm": 10.880382658420737, | |
| "learning_rate": 9.972190879892147e-05, | |
| "loss": 0.6076, | |
| "num_input_tokens_seen": 5754192, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.1654357459379616, | |
| "grad_norm": 5.9115707757479345, | |
| "learning_rate": 9.970889784653033e-05, | |
| "loss": 0.6136, | |
| "num_input_tokens_seen": 5806272, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.16691285081240767, | |
| "grad_norm": 8.300559629359741, | |
| "learning_rate": 9.969559033135318e-05, | |
| "loss": 0.5554, | |
| "num_input_tokens_seen": 5858632, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.16838995568685378, | |
| "grad_norm": 19.24269810236072, | |
| "learning_rate": 9.96819863327825e-05, | |
| "loss": 0.5847, | |
| "num_input_tokens_seen": 5909936, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.16986706056129985, | |
| "grad_norm": 2.997295434716295, | |
| "learning_rate": 9.966808593197959e-05, | |
| "loss": 0.6217, | |
| "num_input_tokens_seen": 5961464, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.17134416543574593, | |
| "grad_norm": 8.454212007467431, | |
| "learning_rate": 9.965388921187413e-05, | |
| "loss": 0.5569, | |
| "num_input_tokens_seen": 6013696, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.172821270310192, | |
| "grad_norm": 11.728020547911296, | |
| "learning_rate": 9.963939625716361e-05, | |
| "loss": 0.5894, | |
| "num_input_tokens_seen": 6065736, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.17429837518463812, | |
| "grad_norm": 20.470288976160585, | |
| "learning_rate": 9.962460715431284e-05, | |
| "loss": 0.5783, | |
| "num_input_tokens_seen": 6118400, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.1757754800590842, | |
| "grad_norm": 4.675971808784723, | |
| "learning_rate": 9.960952199155347e-05, | |
| "loss": 0.5657, | |
| "num_input_tokens_seen": 6171120, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.17725258493353027, | |
| "grad_norm": 9.775804001092958, | |
| "learning_rate": 9.959414085888342e-05, | |
| "loss": 0.6331, | |
| "num_input_tokens_seen": 6222736, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17725258493353027, | |
| "eval_loss": 0.5883122682571411, | |
| "eval_runtime": 19.002, | |
| "eval_samples_per_second": 3.158, | |
| "eval_steps_per_second": 0.789, | |
| "num_input_tokens_seen": 6222736, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17872968980797638, | |
| "grad_norm": 8.081060384434974, | |
| "learning_rate": 9.957846384806636e-05, | |
| "loss": 0.5678, | |
| "num_input_tokens_seen": 6274328, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.18020679468242246, | |
| "grad_norm": 10.520198943062466, | |
| "learning_rate": 9.956249105263121e-05, | |
| "loss": 0.5609, | |
| "num_input_tokens_seen": 6327088, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.18168389955686853, | |
| "grad_norm": 5.336067400981417, | |
| "learning_rate": 9.95462225678715e-05, | |
| "loss": 0.5177, | |
| "num_input_tokens_seen": 6378824, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.1831610044313146, | |
| "grad_norm": 5.263245734989025, | |
| "learning_rate": 9.952965849084483e-05, | |
| "loss": 0.5839, | |
| "num_input_tokens_seen": 6431024, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.18463810930576072, | |
| "grad_norm": 5.175847441048381, | |
| "learning_rate": 9.951279892037233e-05, | |
| "loss": 0.5069, | |
| "num_input_tokens_seen": 6483072, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.1861152141802068, | |
| "grad_norm": 12.247546396996816, | |
| "learning_rate": 9.949564395703803e-05, | |
| "loss": 0.495, | |
| "num_input_tokens_seen": 6534768, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.18759231905465287, | |
| "grad_norm": 8.126956720775665, | |
| "learning_rate": 9.947819370318825e-05, | |
| "loss": 0.6435, | |
| "num_input_tokens_seen": 6586416, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.18906942392909898, | |
| "grad_norm": 9.112136009018696, | |
| "learning_rate": 9.946044826293106e-05, | |
| "loss": 0.5014, | |
| "num_input_tokens_seen": 6638592, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.19054652880354506, | |
| "grad_norm": 7.086235271485555, | |
| "learning_rate": 9.944240774213556e-05, | |
| "loss": 0.529, | |
| "num_input_tokens_seen": 6689920, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.19202363367799113, | |
| "grad_norm": 21.538813510868643, | |
| "learning_rate": 9.942407224843132e-05, | |
| "loss": 0.5483, | |
| "num_input_tokens_seen": 6743120, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.19202363367799113, | |
| "eval_loss": 0.6100574135780334, | |
| "eval_runtime": 18.9585, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.791, | |
| "num_input_tokens_seen": 6743120, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1935007385524372, | |
| "grad_norm": 5.437189286202135, | |
| "learning_rate": 9.940544189120771e-05, | |
| "loss": 0.5499, | |
| "num_input_tokens_seen": 6794096, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.19497784342688332, | |
| "grad_norm": 11.687077385856876, | |
| "learning_rate": 9.938651678161326e-05, | |
| "loss": 0.5866, | |
| "num_input_tokens_seen": 6846200, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.1964549483013294, | |
| "grad_norm": 7.149806146104705, | |
| "learning_rate": 9.936729703255498e-05, | |
| "loss": 0.4958, | |
| "num_input_tokens_seen": 6899280, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.19793205317577547, | |
| "grad_norm": 7.7389407646353225, | |
| "learning_rate": 9.93477827586977e-05, | |
| "loss": 0.4232, | |
| "num_input_tokens_seen": 6950608, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.19940915805022155, | |
| "grad_norm": 10.670856796845847, | |
| "learning_rate": 9.932797407646338e-05, | |
| "loss": 0.5407, | |
| "num_input_tokens_seen": 7002696, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.20088626292466766, | |
| "grad_norm": 4.979252179082294, | |
| "learning_rate": 9.93078711040304e-05, | |
| "loss": 0.4553, | |
| "num_input_tokens_seen": 7055160, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.20236336779911374, | |
| "grad_norm": 16.633134937375967, | |
| "learning_rate": 9.928747396133294e-05, | |
| "loss": 0.5565, | |
| "num_input_tokens_seen": 7107224, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.2038404726735598, | |
| "grad_norm": 11.730384893098227, | |
| "learning_rate": 9.926678277006011e-05, | |
| "loss": 0.5951, | |
| "num_input_tokens_seen": 7158376, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.20531757754800592, | |
| "grad_norm": 7.120874965147562, | |
| "learning_rate": 9.924579765365536e-05, | |
| "loss": 0.4764, | |
| "num_input_tokens_seen": 7210552, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.206794682422452, | |
| "grad_norm": 7.463812624673142, | |
| "learning_rate": 9.922451873731569e-05, | |
| "loss": 0.477, | |
| "num_input_tokens_seen": 7262832, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.206794682422452, | |
| "eval_loss": 0.5883837938308716, | |
| "eval_runtime": 19.0983, | |
| "eval_samples_per_second": 3.142, | |
| "eval_steps_per_second": 0.785, | |
| "num_input_tokens_seen": 7262832, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.20827178729689808, | |
| "grad_norm": 5.1484150923671, | |
| "learning_rate": 9.92029461479909e-05, | |
| "loss": 0.5151, | |
| "num_input_tokens_seen": 7314520, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.20974889217134415, | |
| "grad_norm": 10.902688361325707, | |
| "learning_rate": 9.918108001438283e-05, | |
| "loss": 0.6158, | |
| "num_input_tokens_seen": 7365368, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.21122599704579026, | |
| "grad_norm": 6.960249994011121, | |
| "learning_rate": 9.915892046694464e-05, | |
| "loss": 0.5164, | |
| "num_input_tokens_seen": 7417296, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.21270310192023634, | |
| "grad_norm": 6.138105593354917, | |
| "learning_rate": 9.913646763787992e-05, | |
| "loss": 0.5823, | |
| "num_input_tokens_seen": 7469640, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.21418020679468242, | |
| "grad_norm": 5.865897561310743, | |
| "learning_rate": 9.911372166114208e-05, | |
| "loss": 0.5145, | |
| "num_input_tokens_seen": 7521520, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.21565731166912852, | |
| "grad_norm": 14.330290158050401, | |
| "learning_rate": 9.909068267243336e-05, | |
| "loss": 0.571, | |
| "num_input_tokens_seen": 7573880, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.2171344165435746, | |
| "grad_norm": 6.90669118248274, | |
| "learning_rate": 9.906735080920413e-05, | |
| "loss": 0.4638, | |
| "num_input_tokens_seen": 7625896, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.21861152141802068, | |
| "grad_norm": 6.310395883326308, | |
| "learning_rate": 9.904372621065206e-05, | |
| "loss": 0.5449, | |
| "num_input_tokens_seen": 7676528, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.22008862629246675, | |
| "grad_norm": 27.446565035007364, | |
| "learning_rate": 9.901980901772126e-05, | |
| "loss": 0.5505, | |
| "num_input_tokens_seen": 7728240, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.22156573116691286, | |
| "grad_norm": 5.6934624405279655, | |
| "learning_rate": 9.899559937310148e-05, | |
| "loss": 0.514, | |
| "num_input_tokens_seen": 7779872, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.22156573116691286, | |
| "eval_loss": 0.4665524661540985, | |
| "eval_runtime": 19.1629, | |
| "eval_samples_per_second": 3.131, | |
| "eval_steps_per_second": 0.783, | |
| "num_input_tokens_seen": 7779872, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.22304283604135894, | |
| "grad_norm": 7.392056712218606, | |
| "learning_rate": 9.897109742122721e-05, | |
| "loss": 0.5248, | |
| "num_input_tokens_seen": 7832168, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.22451994091580502, | |
| "grad_norm": 9.230824229530686, | |
| "learning_rate": 9.894630330827686e-05, | |
| "loss": 0.5017, | |
| "num_input_tokens_seen": 7884040, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2259970457902511, | |
| "grad_norm": 11.203609848309013, | |
| "learning_rate": 9.892121718217182e-05, | |
| "loss": 0.4896, | |
| "num_input_tokens_seen": 7935528, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.2274741506646972, | |
| "grad_norm": 30.185572869944284, | |
| "learning_rate": 9.88958391925757e-05, | |
| "loss": 0.5125, | |
| "num_input_tokens_seen": 7987760, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.22895125553914328, | |
| "grad_norm": 18.649424971543322, | |
| "learning_rate": 9.887016949089333e-05, | |
| "loss": 0.5615, | |
| "num_input_tokens_seen": 8039400, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.23042836041358936, | |
| "grad_norm": 5.360845077873566, | |
| "learning_rate": 9.884420823026989e-05, | |
| "loss": 0.494, | |
| "num_input_tokens_seen": 8092440, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.23190546528803546, | |
| "grad_norm": 10.101391912363345, | |
| "learning_rate": 9.881795556558999e-05, | |
| "loss": 0.5122, | |
| "num_input_tokens_seen": 8145040, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.23338257016248154, | |
| "grad_norm": 5.90491429019666, | |
| "learning_rate": 9.879141165347678e-05, | |
| "loss": 0.4925, | |
| "num_input_tokens_seen": 8196904, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.23485967503692762, | |
| "grad_norm": 6.228283676778458, | |
| "learning_rate": 9.876457665229097e-05, | |
| "loss": 0.4752, | |
| "num_input_tokens_seen": 8249232, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.2363367799113737, | |
| "grad_norm": 8.496099871334396, | |
| "learning_rate": 9.87374507221299e-05, | |
| "loss": 0.4239, | |
| "num_input_tokens_seen": 8301976, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2363367799113737, | |
| "eval_loss": 0.48219749331474304, | |
| "eval_runtime": 19.0825, | |
| "eval_samples_per_second": 3.144, | |
| "eval_steps_per_second": 0.786, | |
| "num_input_tokens_seen": 8301976, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2378138847858198, | |
| "grad_norm": 5.415068909643764, | |
| "learning_rate": 9.87100340248266e-05, | |
| "loss": 0.4482, | |
| "num_input_tokens_seen": 8353736, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.23929098966026588, | |
| "grad_norm": 24.48801392473646, | |
| "learning_rate": 9.868232672394881e-05, | |
| "loss": 0.4764, | |
| "num_input_tokens_seen": 8406216, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.24076809453471196, | |
| "grad_norm": 12.500688224717539, | |
| "learning_rate": 9.8654328984798e-05, | |
| "loss": 0.4476, | |
| "num_input_tokens_seen": 8457752, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.24224519940915806, | |
| "grad_norm": 6.4171543173466405, | |
| "learning_rate": 9.862604097440844e-05, | |
| "loss": 0.4295, | |
| "num_input_tokens_seen": 8510440, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.24372230428360414, | |
| "grad_norm": 8.42476760299212, | |
| "learning_rate": 9.859746286154607e-05, | |
| "loss": 0.5384, | |
| "num_input_tokens_seen": 8562016, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.24519940915805022, | |
| "grad_norm": 5.79752775822047, | |
| "learning_rate": 9.856859481670764e-05, | |
| "loss": 0.5357, | |
| "num_input_tokens_seen": 8614184, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.2466765140324963, | |
| "grad_norm": 6.468218270458443, | |
| "learning_rate": 9.853943701211963e-05, | |
| "loss": 0.5309, | |
| "num_input_tokens_seen": 8666528, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.2481536189069424, | |
| "grad_norm": 6.446467495370782, | |
| "learning_rate": 9.850998962173719e-05, | |
| "loss": 0.4949, | |
| "num_input_tokens_seen": 8718048, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.24963072378138848, | |
| "grad_norm": 7.926476306574312, | |
| "learning_rate": 9.848025282124317e-05, | |
| "loss": 0.4681, | |
| "num_input_tokens_seen": 8769968, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.2511078286558346, | |
| "grad_norm": 19.45042923754815, | |
| "learning_rate": 9.845022678804701e-05, | |
| "loss": 0.4949, | |
| "num_input_tokens_seen": 8822832, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2511078286558346, | |
| "eval_loss": 0.6121839880943298, | |
| "eval_runtime": 19.1203, | |
| "eval_samples_per_second": 3.138, | |
| "eval_steps_per_second": 0.785, | |
| "num_input_tokens_seen": 8822832, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.25258493353028066, | |
| "grad_norm": 8.111385407981246, | |
| "learning_rate": 9.841991170128374e-05, | |
| "loss": 0.4636, | |
| "num_input_tokens_seen": 8875608, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.25406203840472674, | |
| "grad_norm": 4.789169716538139, | |
| "learning_rate": 9.838930774181285e-05, | |
| "loss": 0.4322, | |
| "num_input_tokens_seen": 8927600, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2555391432791728, | |
| "grad_norm": 3.6029916519925167, | |
| "learning_rate": 9.835841509221725e-05, | |
| "loss": 0.4302, | |
| "num_input_tokens_seen": 8980224, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.2570162481536189, | |
| "grad_norm": 17.138905616592684, | |
| "learning_rate": 9.83272339368022e-05, | |
| "loss": 0.5231, | |
| "num_input_tokens_seen": 9032112, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.258493353028065, | |
| "grad_norm": 6.810210745159563, | |
| "learning_rate": 9.829576446159416e-05, | |
| "loss": 0.4414, | |
| "num_input_tokens_seen": 9084480, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.25997045790251105, | |
| "grad_norm": 6.785950897404188, | |
| "learning_rate": 9.826400685433968e-05, | |
| "loss": 0.4469, | |
| "num_input_tokens_seen": 9136816, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.2614475627769572, | |
| "grad_norm": 14.335926789263953, | |
| "learning_rate": 9.823196130450434e-05, | |
| "loss": 0.3859, | |
| "num_input_tokens_seen": 9189808, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.26292466765140327, | |
| "grad_norm": 24.791700587075013, | |
| "learning_rate": 9.819962800327156e-05, | |
| "loss": 0.4794, | |
| "num_input_tokens_seen": 9241712, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.26440177252584934, | |
| "grad_norm": 16.38282434047279, | |
| "learning_rate": 9.81670071435415e-05, | |
| "loss": 0.4476, | |
| "num_input_tokens_seen": 9293328, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.2658788774002954, | |
| "grad_norm": 3.8069696135300846, | |
| "learning_rate": 9.813409891992988e-05, | |
| "loss": 0.4852, | |
| "num_input_tokens_seen": 9345160, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2658788774002954, | |
| "eval_loss": 0.5605542063713074, | |
| "eval_runtime": 19.0274, | |
| "eval_samples_per_second": 3.153, | |
| "eval_steps_per_second": 0.788, | |
| "num_input_tokens_seen": 9345160, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2673559822747415, | |
| "grad_norm": 8.596452892791511, | |
| "learning_rate": 9.810090352876685e-05, | |
| "loss": 0.4973, | |
| "num_input_tokens_seen": 9396608, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.2688330871491876, | |
| "grad_norm": 22.570326690897016, | |
| "learning_rate": 9.806742116809575e-05, | |
| "loss": 0.4845, | |
| "num_input_tokens_seen": 9448264, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.27031019202363366, | |
| "grad_norm": 10.987740344554055, | |
| "learning_rate": 9.803365203767201e-05, | |
| "loss": 0.4405, | |
| "num_input_tokens_seen": 9501288, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.2717872968980798, | |
| "grad_norm": 5.629472815681504, | |
| "learning_rate": 9.799959633896194e-05, | |
| "loss": 0.5228, | |
| "num_input_tokens_seen": 9552680, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.27326440177252587, | |
| "grad_norm": 4.8888946075363355, | |
| "learning_rate": 9.79652542751415e-05, | |
| "loss": 0.4189, | |
| "num_input_tokens_seen": 9604432, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.27474150664697194, | |
| "grad_norm": 11.753985857725072, | |
| "learning_rate": 9.793062605109509e-05, | |
| "loss": 0.4449, | |
| "num_input_tokens_seen": 9656992, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.276218611521418, | |
| "grad_norm": 10.956276728284152, | |
| "learning_rate": 9.789571187341433e-05, | |
| "loss": 0.4678, | |
| "num_input_tokens_seen": 9709016, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.2776957163958641, | |
| "grad_norm": 5.760995229664893, | |
| "learning_rate": 9.786051195039689e-05, | |
| "loss": 0.5359, | |
| "num_input_tokens_seen": 9759936, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2791728212703102, | |
| "grad_norm": 5.4002668741362365, | |
| "learning_rate": 9.782502649204512e-05, | |
| "loss": 0.5507, | |
| "num_input_tokens_seen": 9811880, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.28064992614475626, | |
| "grad_norm": 3.1909077693586876, | |
| "learning_rate": 9.778925571006495e-05, | |
| "loss": 0.4737, | |
| "num_input_tokens_seen": 9863168, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.28064992614475626, | |
| "eval_loss": 0.479105681180954, | |
| "eval_runtime": 19.2085, | |
| "eval_samples_per_second": 3.124, | |
| "eval_steps_per_second": 0.781, | |
| "num_input_tokens_seen": 9863168, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2821270310192024, | |
| "grad_norm": 3.2511615728403744, | |
| "learning_rate": 9.775319981786445e-05, | |
| "loss": 0.4393, | |
| "num_input_tokens_seen": 9914672, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.28360413589364847, | |
| "grad_norm": 16.435101279621147, | |
| "learning_rate": 9.771685903055277e-05, | |
| "loss": 0.4355, | |
| "num_input_tokens_seen": 9966736, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.28508124076809455, | |
| "grad_norm": 15.842537939054491, | |
| "learning_rate": 9.768023356493864e-05, | |
| "loss": 0.4459, | |
| "num_input_tokens_seen": 10017984, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.2865583456425406, | |
| "grad_norm": 4.234230919149069, | |
| "learning_rate": 9.764332363952927e-05, | |
| "loss": 0.4774, | |
| "num_input_tokens_seen": 10069520, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.2880354505169867, | |
| "grad_norm": 4.408868276054397, | |
| "learning_rate": 9.760612947452884e-05, | |
| "loss": 0.413, | |
| "num_input_tokens_seen": 10122208, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.2895125553914328, | |
| "grad_norm": 18.46536438022927, | |
| "learning_rate": 9.756865129183741e-05, | |
| "loss": 0.5433, | |
| "num_input_tokens_seen": 10173760, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.29098966026587886, | |
| "grad_norm": 10.416515634178488, | |
| "learning_rate": 9.753088931504944e-05, | |
| "loss": 0.4096, | |
| "num_input_tokens_seen": 10224976, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.29246676514032494, | |
| "grad_norm": 8.959580527519506, | |
| "learning_rate": 9.749284376945248e-05, | |
| "loss": 0.3916, | |
| "num_input_tokens_seen": 10276928, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.29394387001477107, | |
| "grad_norm": 4.106784187834887, | |
| "learning_rate": 9.74545148820259e-05, | |
| "loss": 0.3899, | |
| "num_input_tokens_seen": 10328048, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.29542097488921715, | |
| "grad_norm": 7.661197997005464, | |
| "learning_rate": 9.741590288143944e-05, | |
| "loss": 0.4005, | |
| "num_input_tokens_seen": 10379136, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.29542097488921715, | |
| "eval_loss": 0.5501028299331665, | |
| "eval_runtime": 19.0051, | |
| "eval_samples_per_second": 3.157, | |
| "eval_steps_per_second": 0.789, | |
| "num_input_tokens_seen": 10379136, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2968980797636632, | |
| "grad_norm": 28.402265641893973, | |
| "learning_rate": 9.737700799805191e-05, | |
| "loss": 0.4585, | |
| "num_input_tokens_seen": 10430680, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.2983751846381093, | |
| "grad_norm": 7.624783658458961, | |
| "learning_rate": 9.73378304639098e-05, | |
| "loss": 0.4257, | |
| "num_input_tokens_seen": 10482472, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.2998522895125554, | |
| "grad_norm": 9.68942996120796, | |
| "learning_rate": 9.729837051274591e-05, | |
| "loss": 0.4359, | |
| "num_input_tokens_seen": 10534392, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.30132939438700146, | |
| "grad_norm": 4.997152707865521, | |
| "learning_rate": 9.725862837997786e-05, | |
| "loss": 0.4158, | |
| "num_input_tokens_seen": 10586104, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.30280649926144754, | |
| "grad_norm": 12.772476641379384, | |
| "learning_rate": 9.721860430270685e-05, | |
| "loss": 0.4067, | |
| "num_input_tokens_seen": 10637560, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.30428360413589367, | |
| "grad_norm": 11.194625798156807, | |
| "learning_rate": 9.717829851971612e-05, | |
| "loss": 0.4811, | |
| "num_input_tokens_seen": 10689552, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.30576070901033975, | |
| "grad_norm": 8.371187346484113, | |
| "learning_rate": 9.713771127146955e-05, | |
| "loss": 0.4732, | |
| "num_input_tokens_seen": 10742208, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.3072378138847858, | |
| "grad_norm": 20.552637977751065, | |
| "learning_rate": 9.70968428001103e-05, | |
| "loss": 0.4735, | |
| "num_input_tokens_seen": 10794008, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3087149187592319, | |
| "grad_norm": 6.868858377235537, | |
| "learning_rate": 9.705569334945921e-05, | |
| "loss": 0.4381, | |
| "num_input_tokens_seen": 10845736, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.310192023633678, | |
| "grad_norm": 12.499280962869927, | |
| "learning_rate": 9.701426316501352e-05, | |
| "loss": 0.3991, | |
| "num_input_tokens_seen": 10897528, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.310192023633678, | |
| "eval_loss": 0.4378110468387604, | |
| "eval_runtime": 47.2127, | |
| "eval_samples_per_second": 1.271, | |
| "eval_steps_per_second": 0.318, | |
| "num_input_tokens_seen": 10897528, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.31166912850812406, | |
| "grad_norm": 12.581621849544964, | |
| "learning_rate": 9.697255249394527e-05, | |
| "loss": 0.3724, | |
| "num_input_tokens_seen": 10949888, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.31314623338257014, | |
| "grad_norm": 6.318957148146118, | |
| "learning_rate": 9.693056158509992e-05, | |
| "loss": 0.4483, | |
| "num_input_tokens_seen": 11001208, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.31462333825701627, | |
| "grad_norm": 5.822614134671903, | |
| "learning_rate": 9.688829068899483e-05, | |
| "loss": 0.4133, | |
| "num_input_tokens_seen": 11052368, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.31610044313146235, | |
| "grad_norm": 6.115498616882066, | |
| "learning_rate": 9.684574005781772e-05, | |
| "loss": 0.5406, | |
| "num_input_tokens_seen": 11104008, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.3175775480059084, | |
| "grad_norm": 12.381439695843321, | |
| "learning_rate": 9.680290994542523e-05, | |
| "loss": 0.4148, | |
| "num_input_tokens_seen": 11155888, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.3190546528803545, | |
| "grad_norm": 5.292808434292701, | |
| "learning_rate": 9.675980060734138e-05, | |
| "loss": 0.4169, | |
| "num_input_tokens_seen": 11207352, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3205317577548006, | |
| "grad_norm": 5.275144555938926, | |
| "learning_rate": 9.671641230075604e-05, | |
| "loss": 0.4706, | |
| "num_input_tokens_seen": 11257672, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.32200886262924666, | |
| "grad_norm": 7.458715041450571, | |
| "learning_rate": 9.667274528452344e-05, | |
| "loss": 0.3736, | |
| "num_input_tokens_seen": 11309944, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.32348596750369274, | |
| "grad_norm": 8.390618541362887, | |
| "learning_rate": 9.662879981916054e-05, | |
| "loss": 0.4413, | |
| "num_input_tokens_seen": 11361032, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.3249630723781389, | |
| "grad_norm": 14.65510134410483, | |
| "learning_rate": 9.658457616684555e-05, | |
| "loss": 0.4624, | |
| "num_input_tokens_seen": 11413120, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3249630723781389, | |
| "eval_loss": 0.5300672650337219, | |
| "eval_runtime": 19.0076, | |
| "eval_samples_per_second": 3.157, | |
| "eval_steps_per_second": 0.789, | |
| "num_input_tokens_seen": 11413120, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.32644017725258495, | |
| "grad_norm": 5.808097944570942, | |
| "learning_rate": 9.654007459141634e-05, | |
| "loss": 0.4121, | |
| "num_input_tokens_seen": 11465064, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.32791728212703103, | |
| "grad_norm": 4.015479597894709, | |
| "learning_rate": 9.649529535836887e-05, | |
| "loss": 0.4569, | |
| "num_input_tokens_seen": 11516304, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.3293943870014771, | |
| "grad_norm": 8.768813687811088, | |
| "learning_rate": 9.645023873485557e-05, | |
| "loss": 0.4121, | |
| "num_input_tokens_seen": 11568568, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.3308714918759232, | |
| "grad_norm": 10.930663245586304, | |
| "learning_rate": 9.640490498968383e-05, | |
| "loss": 0.4112, | |
| "num_input_tokens_seen": 11620672, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.33234859675036926, | |
| "grad_norm": 6.691827883878219, | |
| "learning_rate": 9.63592943933143e-05, | |
| "loss": 0.3564, | |
| "num_input_tokens_seen": 11672864, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.33382570162481534, | |
| "grad_norm": 8.33100451031768, | |
| "learning_rate": 9.631340721785934e-05, | |
| "loss": 0.3909, | |
| "num_input_tokens_seen": 11724128, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.3353028064992615, | |
| "grad_norm": 7.005971082198048, | |
| "learning_rate": 9.62672437370814e-05, | |
| "loss": 0.4636, | |
| "num_input_tokens_seen": 11776416, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.33677991137370755, | |
| "grad_norm": 14.154463913713748, | |
| "learning_rate": 9.622080422639133e-05, | |
| "loss": 0.4617, | |
| "num_input_tokens_seen": 11828256, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.33825701624815363, | |
| "grad_norm": 14.751813027169304, | |
| "learning_rate": 9.617408896284678e-05, | |
| "loss": 0.3443, | |
| "num_input_tokens_seen": 11882048, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.3397341211225997, | |
| "grad_norm": 3.2576085972339706, | |
| "learning_rate": 9.612709822515054e-05, | |
| "loss": 0.4432, | |
| "num_input_tokens_seen": 11933632, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3397341211225997, | |
| "eval_loss": 0.42494550347328186, | |
| "eval_runtime": 19.6038, | |
| "eval_samples_per_second": 3.061, | |
| "eval_steps_per_second": 0.765, | |
| "num_input_tokens_seen": 11933632, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3412112259970458, | |
| "grad_norm": 4.778973114307738, | |
| "learning_rate": 9.60798322936489e-05, | |
| "loss": 0.3716, | |
| "num_input_tokens_seen": 11986496, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.34268833087149186, | |
| "grad_norm": 8.20796735033587, | |
| "learning_rate": 9.603229145032993e-05, | |
| "loss": 0.4234, | |
| "num_input_tokens_seen": 12039112, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.34416543574593794, | |
| "grad_norm": 7.158508103350641, | |
| "learning_rate": 9.598447597882181e-05, | |
| "loss": 0.3973, | |
| "num_input_tokens_seen": 12091728, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.345642540620384, | |
| "grad_norm": 9.320131732384727, | |
| "learning_rate": 9.593638616439118e-05, | |
| "loss": 0.3494, | |
| "num_input_tokens_seen": 12143896, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.34711964549483015, | |
| "grad_norm": 10.150141046652656, | |
| "learning_rate": 9.588802229394137e-05, | |
| "loss": 0.4182, | |
| "num_input_tokens_seen": 12195336, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.34859675036927623, | |
| "grad_norm": 9.270011962927722, | |
| "learning_rate": 9.583938465601075e-05, | |
| "loss": 0.462, | |
| "num_input_tokens_seen": 12247696, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.3500738552437223, | |
| "grad_norm": 8.96068778293971, | |
| "learning_rate": 9.5790473540771e-05, | |
| "loss": 0.4451, | |
| "num_input_tokens_seen": 12300040, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.3515509601181684, | |
| "grad_norm": 24.761476817148992, | |
| "learning_rate": 9.574128924002533e-05, | |
| "loss": 0.4789, | |
| "num_input_tokens_seen": 12351904, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.35302806499261447, | |
| "grad_norm": 1.8519516556186366, | |
| "learning_rate": 9.569183204720677e-05, | |
| "loss": 0.3898, | |
| "num_input_tokens_seen": 12403280, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.35450516986706054, | |
| "grad_norm": 5.005586803143539, | |
| "learning_rate": 9.564210225737647e-05, | |
| "loss": 0.3296, | |
| "num_input_tokens_seen": 12456040, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.35450516986706054, | |
| "eval_loss": 0.2966395914554596, | |
| "eval_runtime": 19.5244, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.768, | |
| "num_input_tokens_seen": 12456040, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3559822747415066, | |
| "grad_norm": 5.5028656713393245, | |
| "learning_rate": 9.559210016722184e-05, | |
| "loss": 0.3717, | |
| "num_input_tokens_seen": 12507640, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.35745937961595275, | |
| "grad_norm": 13.214008089689216, | |
| "learning_rate": 9.554182607505484e-05, | |
| "loss": 0.541, | |
| "num_input_tokens_seen": 12559400, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.35893648449039883, | |
| "grad_norm": 6.269664608708862, | |
| "learning_rate": 9.54912802808102e-05, | |
| "loss": 0.3965, | |
| "num_input_tokens_seen": 12610992, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.3604135893648449, | |
| "grad_norm": 21.247512275128738, | |
| "learning_rate": 9.544046308604364e-05, | |
| "loss": 0.4834, | |
| "num_input_tokens_seen": 12662688, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.361890694239291, | |
| "grad_norm": 4.14272563629135, | |
| "learning_rate": 9.538937479393001e-05, | |
| "loss": 0.4538, | |
| "num_input_tokens_seen": 12713600, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.36336779911373707, | |
| "grad_norm": 12.86150407455535, | |
| "learning_rate": 9.533801570926157e-05, | |
| "loss": 0.4226, | |
| "num_input_tokens_seen": 12766360, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.36484490398818314, | |
| "grad_norm": 4.36264988758363, | |
| "learning_rate": 9.52863861384461e-05, | |
| "loss": 0.4315, | |
| "num_input_tokens_seen": 12817248, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.3663220088626292, | |
| "grad_norm": 1.6622545996067835, | |
| "learning_rate": 9.523448638950508e-05, | |
| "loss": 0.3567, | |
| "num_input_tokens_seen": 12868496, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.36779911373707536, | |
| "grad_norm": 5.5241376090939065, | |
| "learning_rate": 9.518231677207192e-05, | |
| "loss": 0.3431, | |
| "num_input_tokens_seen": 12920168, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.36927621861152143, | |
| "grad_norm": 5.717434283790562, | |
| "learning_rate": 9.512987759739003e-05, | |
| "loss": 0.335, | |
| "num_input_tokens_seen": 12972696, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.36927621861152143, | |
| "eval_loss": 0.31846168637275696, | |
| "eval_runtime": 18.9319, | |
| "eval_samples_per_second": 3.169, | |
| "eval_steps_per_second": 0.792, | |
| "num_input_tokens_seen": 12972696, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.3707533234859675, | |
| "grad_norm": 2.1850732370217045, | |
| "learning_rate": 9.507716917831099e-05, | |
| "loss": 0.3242, | |
| "num_input_tokens_seen": 13025280, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.3722304283604136, | |
| "grad_norm": 7.470465465497159, | |
| "learning_rate": 9.50241918292927e-05, | |
| "loss": 0.4083, | |
| "num_input_tokens_seen": 13075992, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.37370753323485967, | |
| "grad_norm": 10.134768151698713, | |
| "learning_rate": 9.49709458663975e-05, | |
| "loss": 0.4043, | |
| "num_input_tokens_seen": 13128592, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.37518463810930575, | |
| "grad_norm": 7.635543650225297, | |
| "learning_rate": 9.491743160729026e-05, | |
| "loss": 0.3481, | |
| "num_input_tokens_seen": 13181824, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.3766617429837518, | |
| "grad_norm": 17.089924601510244, | |
| "learning_rate": 9.486364937123651e-05, | |
| "loss": 0.4121, | |
| "num_input_tokens_seen": 13233624, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.37813884785819796, | |
| "grad_norm": 8.52905916993994, | |
| "learning_rate": 9.480959947910055e-05, | |
| "loss": 0.487, | |
| "num_input_tokens_seen": 13285808, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.37961595273264404, | |
| "grad_norm": 11.841989523288227, | |
| "learning_rate": 9.47552822533435e-05, | |
| "loss": 0.3798, | |
| "num_input_tokens_seen": 13337864, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.3810930576070901, | |
| "grad_norm": 2.1853711175575734, | |
| "learning_rate": 9.470069801802135e-05, | |
| "loss": 0.348, | |
| "num_input_tokens_seen": 13390544, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.3825701624815362, | |
| "grad_norm": 2.9516647949035826, | |
| "learning_rate": 9.464584709878313e-05, | |
| "loss": 0.41, | |
| "num_input_tokens_seen": 13441664, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.38404726735598227, | |
| "grad_norm": 3.7764410954952514, | |
| "learning_rate": 9.459072982286886e-05, | |
| "loss": 0.3594, | |
| "num_input_tokens_seen": 13493264, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.38404726735598227, | |
| "eval_loss": 0.4715976417064667, | |
| "eval_runtime": 19.0919, | |
| "eval_samples_per_second": 3.143, | |
| "eval_steps_per_second": 0.786, | |
| "num_input_tokens_seen": 13493264, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.38552437223042835, | |
| "grad_norm": 15.50071615139337, | |
| "learning_rate": 9.453534651910765e-05, | |
| "loss": 0.402, | |
| "num_input_tokens_seen": 13545256, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.3870014771048744, | |
| "grad_norm": 23.183495844663526, | |
| "learning_rate": 9.447969751791577e-05, | |
| "loss": 0.3075, | |
| "num_input_tokens_seen": 13597792, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.38847858197932056, | |
| "grad_norm": 9.67544956653079, | |
| "learning_rate": 9.442378315129455e-05, | |
| "loss": 0.3702, | |
| "num_input_tokens_seen": 13649848, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.38995568685376664, | |
| "grad_norm": 2.9059361985914416, | |
| "learning_rate": 9.436760375282859e-05, | |
| "loss": 0.3603, | |
| "num_input_tokens_seen": 13701592, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3914327917282127, | |
| "grad_norm": 10.431238621222658, | |
| "learning_rate": 9.431115965768358e-05, | |
| "loss": 0.4072, | |
| "num_input_tokens_seen": 13753064, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.3929098966026588, | |
| "grad_norm": 11.216612661805582, | |
| "learning_rate": 9.425445120260445e-05, | |
| "loss": 0.3279, | |
| "num_input_tokens_seen": 13805528, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.39438700147710487, | |
| "grad_norm": 32.22838128750362, | |
| "learning_rate": 9.419747872591325e-05, | |
| "loss": 0.3754, | |
| "num_input_tokens_seen": 13858192, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.39586410635155095, | |
| "grad_norm": 1.8703742105152936, | |
| "learning_rate": 9.414024256750723e-05, | |
| "loss": 0.3754, | |
| "num_input_tokens_seen": 13910128, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.397341211225997, | |
| "grad_norm": 5.011302513950015, | |
| "learning_rate": 9.408274306885674e-05, | |
| "loss": 0.3235, | |
| "num_input_tokens_seen": 13962536, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.3988183161004431, | |
| "grad_norm": 15.197987760428996, | |
| "learning_rate": 9.402498057300317e-05, | |
| "loss": 0.3731, | |
| "num_input_tokens_seen": 14014736, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.3988183161004431, | |
| "eval_loss": 0.5565826892852783, | |
| "eval_runtime": 19.3029, | |
| "eval_samples_per_second": 3.108, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 14014736, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.40029542097488924, | |
| "grad_norm": 2.292705535408954, | |
| "learning_rate": 9.396695542455704e-05, | |
| "loss": 0.4115, | |
| "num_input_tokens_seen": 14066880, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.4017725258493353, | |
| "grad_norm": 10.68072230240614, | |
| "learning_rate": 9.390866796969577e-05, | |
| "loss": 0.365, | |
| "num_input_tokens_seen": 14118320, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.4032496307237814, | |
| "grad_norm": 28.45565288311722, | |
| "learning_rate": 9.385011855616177e-05, | |
| "loss": 0.3904, | |
| "num_input_tokens_seen": 14169208, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.40472673559822747, | |
| "grad_norm": 9.32794663574214, | |
| "learning_rate": 9.379130753326021e-05, | |
| "loss": 0.5425, | |
| "num_input_tokens_seen": 14220632, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.40620384047267355, | |
| "grad_norm": 4.737143544435888, | |
| "learning_rate": 9.373223525185709e-05, | |
| "loss": 0.3985, | |
| "num_input_tokens_seen": 14272640, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.4076809453471196, | |
| "grad_norm": 17.480173613134482, | |
| "learning_rate": 9.367290206437702e-05, | |
| "loss": 0.3528, | |
| "num_input_tokens_seen": 14324960, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.4091580502215657, | |
| "grad_norm": 4.40598964753602, | |
| "learning_rate": 9.361330832480124e-05, | |
| "loss": 0.3687, | |
| "num_input_tokens_seen": 14376792, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.41063515509601184, | |
| "grad_norm": 15.961709998187562, | |
| "learning_rate": 9.355345438866538e-05, | |
| "loss": 0.3552, | |
| "num_input_tokens_seen": 14428192, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.4121122599704579, | |
| "grad_norm": 4.033485652398453, | |
| "learning_rate": 9.349334061305743e-05, | |
| "loss": 0.3194, | |
| "num_input_tokens_seen": 14480568, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.413589364844904, | |
| "grad_norm": 9.187315388235644, | |
| "learning_rate": 9.343296735661557e-05, | |
| "loss": 0.388, | |
| "num_input_tokens_seen": 14532288, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.413589364844904, | |
| "eval_loss": 0.38656601309776306, | |
| "eval_runtime": 19.1495, | |
| "eval_samples_per_second": 3.133, | |
| "eval_steps_per_second": 0.783, | |
| "num_input_tokens_seen": 14532288, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4150664697193501, | |
| "grad_norm": 2.8279779742550626, | |
| "learning_rate": 9.337233497952604e-05, | |
| "loss": 0.3751, | |
| "num_input_tokens_seen": 14583680, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.41654357459379615, | |
| "grad_norm": 12.899164703482258, | |
| "learning_rate": 9.331144384352099e-05, | |
| "loss": 0.3431, | |
| "num_input_tokens_seen": 14635712, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.41802067946824223, | |
| "grad_norm": 10.924332413291099, | |
| "learning_rate": 9.325029431187635e-05, | |
| "loss": 0.3786, | |
| "num_input_tokens_seen": 14687048, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.4194977843426883, | |
| "grad_norm": 13.950543503215677, | |
| "learning_rate": 9.318888674940958e-05, | |
| "loss": 0.3427, | |
| "num_input_tokens_seen": 14739336, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.42097488921713444, | |
| "grad_norm": 11.615845590184648, | |
| "learning_rate": 9.31272215224776e-05, | |
| "loss": 0.3307, | |
| "num_input_tokens_seen": 14791656, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.4224519940915805, | |
| "grad_norm": 1.4760161640643292, | |
| "learning_rate": 9.306529899897451e-05, | |
| "loss": 0.3509, | |
| "num_input_tokens_seen": 14843288, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.4239290989660266, | |
| "grad_norm": 5.925998864255826, | |
| "learning_rate": 9.300311954832952e-05, | |
| "loss": 0.4168, | |
| "num_input_tokens_seen": 14895040, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.4254062038404727, | |
| "grad_norm": 5.735184902025097, | |
| "learning_rate": 9.294068354150455e-05, | |
| "loss": 0.3203, | |
| "num_input_tokens_seen": 14947448, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.42688330871491875, | |
| "grad_norm": 19.73355339631789, | |
| "learning_rate": 9.287799135099225e-05, | |
| "loss": 0.3217, | |
| "num_input_tokens_seen": 14999480, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.42836041358936483, | |
| "grad_norm": 11.876408386949045, | |
| "learning_rate": 9.281504335081354e-05, | |
| "loss": 0.3131, | |
| "num_input_tokens_seen": 15050992, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.42836041358936483, | |
| "eval_loss": 0.4740215837955475, | |
| "eval_runtime": 19.3584, | |
| "eval_samples_per_second": 3.099, | |
| "eval_steps_per_second": 0.775, | |
| "num_input_tokens_seen": 15050992, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4298375184638109, | |
| "grad_norm": 5.756692171427544, | |
| "learning_rate": 9.275183991651558e-05, | |
| "loss": 0.3253, | |
| "num_input_tokens_seen": 15103328, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.43131462333825704, | |
| "grad_norm": 48.99329970671894, | |
| "learning_rate": 9.268838142516943e-05, | |
| "loss": 0.3999, | |
| "num_input_tokens_seen": 15154640, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.4327917282127031, | |
| "grad_norm": 4.8123322290098764, | |
| "learning_rate": 9.262466825536782e-05, | |
| "loss": 0.3529, | |
| "num_input_tokens_seen": 15206264, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.4342688330871492, | |
| "grad_norm": 8.626202826826654, | |
| "learning_rate": 9.256070078722287e-05, | |
| "loss": 0.3363, | |
| "num_input_tokens_seen": 15258160, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.4357459379615953, | |
| "grad_norm": 24.191365994287917, | |
| "learning_rate": 9.249647940236385e-05, | |
| "loss": 0.4133, | |
| "num_input_tokens_seen": 15309224, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.43722304283604135, | |
| "grad_norm": 15.447487032462668, | |
| "learning_rate": 9.243200448393492e-05, | |
| "loss": 0.3306, | |
| "num_input_tokens_seen": 15361480, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.43870014771048743, | |
| "grad_norm": 2.714376790067382, | |
| "learning_rate": 9.236727641659277e-05, | |
| "loss": 0.2993, | |
| "num_input_tokens_seen": 15414680, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.4401772525849335, | |
| "grad_norm": 11.85875780519428, | |
| "learning_rate": 9.230229558650442e-05, | |
| "loss": 0.3324, | |
| "num_input_tokens_seen": 15466552, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.44165435745937964, | |
| "grad_norm": 7.338287245679936, | |
| "learning_rate": 9.223706238134485e-05, | |
| "loss": 0.2615, | |
| "num_input_tokens_seen": 15519472, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.4431314623338257, | |
| "grad_norm": 11.54360838796349, | |
| "learning_rate": 9.217157719029469e-05, | |
| "loss": 0.2928, | |
| "num_input_tokens_seen": 15572048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4431314623338257, | |
| "eval_loss": 0.40494996309280396, | |
| "eval_runtime": 19.2568, | |
| "eval_samples_per_second": 3.116, | |
| "eval_steps_per_second": 0.779, | |
| "num_input_tokens_seen": 15572048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4446085672082718, | |
| "grad_norm": 1.4684583536766802, | |
| "learning_rate": 9.210584040403793e-05, | |
| "loss": 0.3622, | |
| "num_input_tokens_seen": 15623400, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.4460856720827179, | |
| "grad_norm": 14.96137801867225, | |
| "learning_rate": 9.20398524147596e-05, | |
| "loss": 0.3192, | |
| "num_input_tokens_seen": 15676712, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.44756277695716395, | |
| "grad_norm": 6.400159478959921, | |
| "learning_rate": 9.197361361614339e-05, | |
| "loss": 0.3463, | |
| "num_input_tokens_seen": 15729304, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.44903988183161003, | |
| "grad_norm": 4.316336693336091, | |
| "learning_rate": 9.190712440336928e-05, | |
| "loss": 0.3675, | |
| "num_input_tokens_seen": 15780144, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.4505169867060561, | |
| "grad_norm": 3.3824956383811586, | |
| "learning_rate": 9.184038517311126e-05, | |
| "loss": 0.3305, | |
| "num_input_tokens_seen": 15832032, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.4519940915805022, | |
| "grad_norm": 8.862997235708779, | |
| "learning_rate": 9.177339632353492e-05, | |
| "loss": 0.3817, | |
| "num_input_tokens_seen": 15884152, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.4534711964549483, | |
| "grad_norm": 8.942655459138996, | |
| "learning_rate": 9.170615825429502e-05, | |
| "loss": 0.3742, | |
| "num_input_tokens_seen": 15935688, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.4549483013293944, | |
| "grad_norm": 29.75871004929942, | |
| "learning_rate": 9.163867136653327e-05, | |
| "loss": 0.34, | |
| "num_input_tokens_seen": 15987800, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4564254062038405, | |
| "grad_norm": 2.7907856781115816, | |
| "learning_rate": 9.157093606287572e-05, | |
| "loss": 0.3389, | |
| "num_input_tokens_seen": 16039472, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.45790251107828656, | |
| "grad_norm": 17.658376604188195, | |
| "learning_rate": 9.150295274743053e-05, | |
| "loss": 0.3588, | |
| "num_input_tokens_seen": 16091960, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.45790251107828656, | |
| "eval_loss": 0.28714123368263245, | |
| "eval_runtime": 19.0565, | |
| "eval_samples_per_second": 3.149, | |
| "eval_steps_per_second": 0.787, | |
| "num_input_tokens_seen": 16091960, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.45937961595273263, | |
| "grad_norm": 2.40581004555412, | |
| "learning_rate": 9.143472182578547e-05, | |
| "loss": 0.3501, | |
| "num_input_tokens_seen": 16143672, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.4608567208271787, | |
| "grad_norm": 4.013146156526438, | |
| "learning_rate": 9.136624370500554e-05, | |
| "loss": 0.2684, | |
| "num_input_tokens_seen": 16195776, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.4623338257016248, | |
| "grad_norm": 11.075749009255755, | |
| "learning_rate": 9.129751879363052e-05, | |
| "loss": 0.3294, | |
| "num_input_tokens_seen": 16247752, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.4638109305760709, | |
| "grad_norm": 1.5049575714077101, | |
| "learning_rate": 9.122854750167254e-05, | |
| "loss": 0.2906, | |
| "num_input_tokens_seen": 16300680, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.465288035450517, | |
| "grad_norm": 4.448041589727679, | |
| "learning_rate": 9.115933024061365e-05, | |
| "loss": 0.3498, | |
| "num_input_tokens_seen": 16352000, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.4667651403249631, | |
| "grad_norm": 9.574179858800763, | |
| "learning_rate": 9.108986742340331e-05, | |
| "loss": 0.3262, | |
| "num_input_tokens_seen": 16403784, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.46824224519940916, | |
| "grad_norm": 5.326539404357799, | |
| "learning_rate": 9.102015946445601e-05, | |
| "loss": 0.318, | |
| "num_input_tokens_seen": 16455080, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.46971935007385524, | |
| "grad_norm": 17.72769299345548, | |
| "learning_rate": 9.095020677964874e-05, | |
| "loss": 0.3257, | |
| "num_input_tokens_seen": 16507712, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.4711964549483013, | |
| "grad_norm": 6.912966772855359, | |
| "learning_rate": 9.08800097863185e-05, | |
| "loss": 0.3253, | |
| "num_input_tokens_seen": 16559392, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.4726735598227474, | |
| "grad_norm": 3.3138006639125344, | |
| "learning_rate": 9.080956890325985e-05, | |
| "loss": 0.3879, | |
| "num_input_tokens_seen": 16609960, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4726735598227474, | |
| "eval_loss": 0.3135533034801483, | |
| "eval_runtime": 19.3013, | |
| "eval_samples_per_second": 3.109, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 16609960, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4741506646971935, | |
| "grad_norm": 11.101854016846067, | |
| "learning_rate": 9.07388845507224e-05, | |
| "loss": 0.3644, | |
| "num_input_tokens_seen": 16661440, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.4756277695716396, | |
| "grad_norm": 12.638527847469565, | |
| "learning_rate": 9.066795715040825e-05, | |
| "loss": 0.2733, | |
| "num_input_tokens_seen": 16714200, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.4771048744460857, | |
| "grad_norm": 2.7966971298188694, | |
| "learning_rate": 9.059678712546963e-05, | |
| "loss": 0.3063, | |
| "num_input_tokens_seen": 16766904, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.47858197932053176, | |
| "grad_norm": 8.210735089414575, | |
| "learning_rate": 9.052537490050614e-05, | |
| "loss": 0.3769, | |
| "num_input_tokens_seen": 16818168, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.48005908419497784, | |
| "grad_norm": 8.942406690882898, | |
| "learning_rate": 9.045372090156243e-05, | |
| "loss": 0.3089, | |
| "num_input_tokens_seen": 16869952, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.4815361890694239, | |
| "grad_norm": 11.68569569670719, | |
| "learning_rate": 9.038182555612551e-05, | |
| "loss": 0.2953, | |
| "num_input_tokens_seen": 16922608, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.48301329394387, | |
| "grad_norm": 17.89504289247946, | |
| "learning_rate": 9.030968929312231e-05, | |
| "loss": 0.3286, | |
| "num_input_tokens_seen": 16974824, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.4844903988183161, | |
| "grad_norm": 1.1612341646192372, | |
| "learning_rate": 9.023731254291705e-05, | |
| "loss": 0.3552, | |
| "num_input_tokens_seen": 17026088, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.4859675036927622, | |
| "grad_norm": 4.624302477495485, | |
| "learning_rate": 9.016469573730869e-05, | |
| "loss": 0.326, | |
| "num_input_tokens_seen": 17077904, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.4874446085672083, | |
| "grad_norm": 1.126074328380494, | |
| "learning_rate": 9.009183930952836e-05, | |
| "loss": 0.2698, | |
| "num_input_tokens_seen": 17130896, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.4874446085672083, | |
| "eval_loss": 0.40201568603515625, | |
| "eval_runtime": 19.4814, | |
| "eval_samples_per_second": 3.08, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 17130896, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.48892171344165436, | |
| "grad_norm": 0.9908097045731693, | |
| "learning_rate": 9.00187436942368e-05, | |
| "loss": 0.2956, | |
| "num_input_tokens_seen": 17182896, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.49039881831610044, | |
| "grad_norm": 2.7463420963023415, | |
| "learning_rate": 8.994540932752167e-05, | |
| "loss": 0.3027, | |
| "num_input_tokens_seen": 17235552, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.4918759231905465, | |
| "grad_norm": 12.1024464355288, | |
| "learning_rate": 8.987183664689511e-05, | |
| "loss": 0.3295, | |
| "num_input_tokens_seen": 17286816, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.4933530280649926, | |
| "grad_norm": 1.7833060218575738, | |
| "learning_rate": 8.9798026091291e-05, | |
| "loss": 0.3201, | |
| "num_input_tokens_seen": 17339072, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.4948301329394387, | |
| "grad_norm": 1.7534258589471414, | |
| "learning_rate": 8.972397810106235e-05, | |
| "loss": 0.3044, | |
| "num_input_tokens_seen": 17391288, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.4963072378138848, | |
| "grad_norm": 3.562194425832391, | |
| "learning_rate": 8.964969311797871e-05, | |
| "loss": 0.2781, | |
| "num_input_tokens_seen": 17443456, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.4977843426883309, | |
| "grad_norm": 3.1653143619735484, | |
| "learning_rate": 8.957517158522359e-05, | |
| "loss": 0.423, | |
| "num_input_tokens_seen": 17494832, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.49926144756277696, | |
| "grad_norm": 9.755061601968617, | |
| "learning_rate": 8.950041394739168e-05, | |
| "loss": 0.2747, | |
| "num_input_tokens_seen": 17547384, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.5007385524372231, | |
| "grad_norm": 6.30268931800531, | |
| "learning_rate": 8.942542065048632e-05, | |
| "loss": 0.3162, | |
| "num_input_tokens_seen": 17599120, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.5022156573116692, | |
| "grad_norm": 16.220873737158193, | |
| "learning_rate": 8.935019214191672e-05, | |
| "loss": 0.3904, | |
| "num_input_tokens_seen": 17650984, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5022156573116692, | |
| "eval_loss": 0.3297054171562195, | |
| "eval_runtime": 47.9781, | |
| "eval_samples_per_second": 1.251, | |
| "eval_steps_per_second": 0.313, | |
| "num_input_tokens_seen": 17650984, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5036927621861153, | |
| "grad_norm": 12.859842090444923, | |
| "learning_rate": 8.927472887049545e-05, | |
| "loss": 0.3484, | |
| "num_input_tokens_seen": 17702864, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.5051698670605613, | |
| "grad_norm": 1.974808718225815, | |
| "learning_rate": 8.919903128643563e-05, | |
| "loss": 0.3214, | |
| "num_input_tokens_seen": 17754792, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.5066469719350074, | |
| "grad_norm": 2.157888572043865, | |
| "learning_rate": 8.912309984134825e-05, | |
| "loss": 0.3428, | |
| "num_input_tokens_seen": 17805608, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.5081240768094535, | |
| "grad_norm": 1.7029183906768783, | |
| "learning_rate": 8.90469349882396e-05, | |
| "loss": 0.3186, | |
| "num_input_tokens_seen": 17857304, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.5096011816838996, | |
| "grad_norm": 1.6160566937167244, | |
| "learning_rate": 8.897053718150838e-05, | |
| "loss": 0.2549, | |
| "num_input_tokens_seen": 17909528, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.5110782865583456, | |
| "grad_norm": 1.3191512067150797, | |
| "learning_rate": 8.889390687694317e-05, | |
| "loss": 0.3248, | |
| "num_input_tokens_seen": 17960976, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.5125553914327917, | |
| "grad_norm": 4.7911741928611065, | |
| "learning_rate": 8.88170445317196e-05, | |
| "loss": 0.3234, | |
| "num_input_tokens_seen": 18013008, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.5140324963072378, | |
| "grad_norm": 2.1869693250421514, | |
| "learning_rate": 8.873995060439764e-05, | |
| "loss": 0.2883, | |
| "num_input_tokens_seen": 18065200, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.5155096011816839, | |
| "grad_norm": 2.878830043797237, | |
| "learning_rate": 8.86626255549189e-05, | |
| "loss": 0.2691, | |
| "num_input_tokens_seen": 18116880, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.51698670605613, | |
| "grad_norm": 13.298568339033883, | |
| "learning_rate": 8.858506984460383e-05, | |
| "loss": 0.3173, | |
| "num_input_tokens_seen": 18169344, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.51698670605613, | |
| "eval_loss": 0.44908422231674194, | |
| "eval_runtime": 19.4293, | |
| "eval_samples_per_second": 3.088, | |
| "eval_steps_per_second": 0.772, | |
| "num_input_tokens_seen": 18169344, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.518463810930576, | |
| "grad_norm": 9.533140259257635, | |
| "learning_rate": 8.850728393614902e-05, | |
| "loss": 0.2966, | |
| "num_input_tokens_seen": 18221144, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.5199409158050221, | |
| "grad_norm": 1.1902233180287396, | |
| "learning_rate": 8.842926829362446e-05, | |
| "loss": 0.3101, | |
| "num_input_tokens_seen": 18272752, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5214180206794683, | |
| "grad_norm": 5.4464127921059635, | |
| "learning_rate": 8.835102338247064e-05, | |
| "loss": 0.2545, | |
| "num_input_tokens_seen": 18325888, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.5228951255539144, | |
| "grad_norm": 4.908248580861331, | |
| "learning_rate": 8.827254966949593e-05, | |
| "loss": 0.3223, | |
| "num_input_tokens_seen": 18378016, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.5243722304283605, | |
| "grad_norm": 8.878082941549529, | |
| "learning_rate": 8.819384762287373e-05, | |
| "loss": 0.2714, | |
| "num_input_tokens_seen": 18431240, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.5258493353028065, | |
| "grad_norm": 1.3922104834090385, | |
| "learning_rate": 8.811491771213964e-05, | |
| "loss": 0.3438, | |
| "num_input_tokens_seen": 18482832, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.5273264401772526, | |
| "grad_norm": 6.15513486850916, | |
| "learning_rate": 8.803576040818873e-05, | |
| "loss": 0.2324, | |
| "num_input_tokens_seen": 18534992, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.5288035450516987, | |
| "grad_norm": 5.349889126448278, | |
| "learning_rate": 8.795637618327269e-05, | |
| "loss": 0.2259, | |
| "num_input_tokens_seen": 18587752, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.5302806499261448, | |
| "grad_norm": 11.727285406275136, | |
| "learning_rate": 8.7876765510997e-05, | |
| "loss": 0.2468, | |
| "num_input_tokens_seen": 18640440, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.5317577548005908, | |
| "grad_norm": 2.562809564221474, | |
| "learning_rate": 8.779692886631812e-05, | |
| "loss": 0.3127, | |
| "num_input_tokens_seen": 18691928, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5317577548005908, | |
| "eval_loss": 0.3499237596988678, | |
| "eval_runtime": 19.3376, | |
| "eval_samples_per_second": 3.103, | |
| "eval_steps_per_second": 0.776, | |
| "num_input_tokens_seen": 18691928, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5332348596750369, | |
| "grad_norm": 2.1114949572134596, | |
| "learning_rate": 8.771686672554067e-05, | |
| "loss": 0.3145, | |
| "num_input_tokens_seen": 18743600, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.534711964549483, | |
| "grad_norm": 2.661731170516522, | |
| "learning_rate": 8.763657956631462e-05, | |
| "loss": 0.3207, | |
| "num_input_tokens_seen": 18794920, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.5361890694239291, | |
| "grad_norm": 10.01115206187178, | |
| "learning_rate": 8.75560678676323e-05, | |
| "loss": 0.2463, | |
| "num_input_tokens_seen": 18847600, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.5376661742983752, | |
| "grad_norm": 2.5996909028595963, | |
| "learning_rate": 8.747533210982575e-05, | |
| "loss": 0.3199, | |
| "num_input_tokens_seen": 18899936, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5391432791728212, | |
| "grad_norm": 1.5344678453995588, | |
| "learning_rate": 8.739437277456366e-05, | |
| "loss": 0.282, | |
| "num_input_tokens_seen": 18952336, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.5406203840472673, | |
| "grad_norm": 1.0236614886630173, | |
| "learning_rate": 8.731319034484862e-05, | |
| "loss": 0.2846, | |
| "num_input_tokens_seen": 19004528, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.5420974889217134, | |
| "grad_norm": 2.459552261348287, | |
| "learning_rate": 8.723178530501417e-05, | |
| "loss": 0.3537, | |
| "num_input_tokens_seen": 19056296, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.5435745937961596, | |
| "grad_norm": 6.813862731810714, | |
| "learning_rate": 8.7150158140722e-05, | |
| "loss": 0.3289, | |
| "num_input_tokens_seen": 19108832, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5450516986706057, | |
| "grad_norm": 9.828132924879462, | |
| "learning_rate": 8.706830933895894e-05, | |
| "loss": 0.3094, | |
| "num_input_tokens_seen": 19160960, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.5465288035450517, | |
| "grad_norm": 1.3290993068913195, | |
| "learning_rate": 8.698623938803409e-05, | |
| "loss": 0.2828, | |
| "num_input_tokens_seen": 19212992, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5465288035450517, | |
| "eval_loss": 0.3780718147754669, | |
| "eval_runtime": 19.3274, | |
| "eval_samples_per_second": 3.104, | |
| "eval_steps_per_second": 0.776, | |
| "num_input_tokens_seen": 19212992, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5480059084194978, | |
| "grad_norm": 2.1847334280581436, | |
| "learning_rate": 8.6903948777576e-05, | |
| "loss": 0.2084, | |
| "num_input_tokens_seen": 19266312, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.5494830132939439, | |
| "grad_norm": 16.345570907477917, | |
| "learning_rate": 8.68214379985296e-05, | |
| "loss": 0.3262, | |
| "num_input_tokens_seen": 19318888, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.55096011816839, | |
| "grad_norm": 5.031283231514028, | |
| "learning_rate": 8.673870754315336e-05, | |
| "loss": 0.3074, | |
| "num_input_tokens_seen": 19371352, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.552437223042836, | |
| "grad_norm": 7.773374329248698, | |
| "learning_rate": 8.665575790501639e-05, | |
| "loss": 0.2795, | |
| "num_input_tokens_seen": 19424160, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.5539143279172821, | |
| "grad_norm": 19.56194874042025, | |
| "learning_rate": 8.657258957899535e-05, | |
| "loss": 0.2396, | |
| "num_input_tokens_seen": 19477720, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.5553914327917282, | |
| "grad_norm": 1.2813519038705325, | |
| "learning_rate": 8.648920306127169e-05, | |
| "loss": 0.302, | |
| "num_input_tokens_seen": 19528512, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5568685376661743, | |
| "grad_norm": 19.876066610019436, | |
| "learning_rate": 8.640559884932848e-05, | |
| "loss": 0.3457, | |
| "num_input_tokens_seen": 19579624, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.5583456425406204, | |
| "grad_norm": 2.133717936227167, | |
| "learning_rate": 8.632177744194765e-05, | |
| "loss": 0.3194, | |
| "num_input_tokens_seen": 19631432, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.5598227474150664, | |
| "grad_norm": 27.424806916466594, | |
| "learning_rate": 8.623773933920688e-05, | |
| "loss": 0.3135, | |
| "num_input_tokens_seen": 19682792, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.5612998522895125, | |
| "grad_norm": 12.744054056352415, | |
| "learning_rate": 8.615348504247663e-05, | |
| "loss": 0.306, | |
| "num_input_tokens_seen": 19735976, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5612998522895125, | |
| "eval_loss": 0.37662214040756226, | |
| "eval_runtime": 19.3962, | |
| "eval_samples_per_second": 3.093, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 19735976, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5627769571639586, | |
| "grad_norm": 7.406464018339625, | |
| "learning_rate": 8.606901505441718e-05, | |
| "loss": 0.3128, | |
| "num_input_tokens_seen": 19787504, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.5642540620384048, | |
| "grad_norm": 2.9136695732910467, | |
| "learning_rate": 8.598432987897565e-05, | |
| "loss": 0.2711, | |
| "num_input_tokens_seen": 19839104, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.5657311669128509, | |
| "grad_norm": 16.37365104368587, | |
| "learning_rate": 8.589943002138295e-05, | |
| "loss": 0.3735, | |
| "num_input_tokens_seen": 19891064, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.5672082717872969, | |
| "grad_norm": 12.090734435687315, | |
| "learning_rate": 8.581431598815077e-05, | |
| "loss": 0.29, | |
| "num_input_tokens_seen": 19942368, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.568685376661743, | |
| "grad_norm": 2.098717687702263, | |
| "learning_rate": 8.572898828706857e-05, | |
| "loss": 0.2977, | |
| "num_input_tokens_seen": 19994816, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.5701624815361891, | |
| "grad_norm": 8.108786754862253, | |
| "learning_rate": 8.564344742720059e-05, | |
| "loss": 0.2483, | |
| "num_input_tokens_seen": 20046192, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.5716395864106352, | |
| "grad_norm": 32.34891985769585, | |
| "learning_rate": 8.55576939188827e-05, | |
| "loss": 0.3126, | |
| "num_input_tokens_seen": 20097328, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.5731166912850812, | |
| "grad_norm": 10.903589696110263, | |
| "learning_rate": 8.54717282737195e-05, | |
| "loss": 0.2688, | |
| "num_input_tokens_seen": 20149392, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5745937961595273, | |
| "grad_norm": 1.6351631003571967, | |
| "learning_rate": 8.538555100458114e-05, | |
| "loss": 0.2491, | |
| "num_input_tokens_seen": 20201392, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.5760709010339734, | |
| "grad_norm": 13.847094678250938, | |
| "learning_rate": 8.529916262560038e-05, | |
| "loss": 0.2992, | |
| "num_input_tokens_seen": 20253288, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5760709010339734, | |
| "eval_loss": 0.3468088209629059, | |
| "eval_runtime": 19.3874, | |
| "eval_samples_per_second": 3.095, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 20253288, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5775480059084195, | |
| "grad_norm": 1.1014534289470133, | |
| "learning_rate": 8.521256365216941e-05, | |
| "loss": 0.2505, | |
| "num_input_tokens_seen": 20305536, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.5790251107828656, | |
| "grad_norm": 2.0823493015928736, | |
| "learning_rate": 8.512575460093683e-05, | |
| "loss": 0.2487, | |
| "num_input_tokens_seen": 20357912, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5805022156573116, | |
| "grad_norm": 27.36036946104022, | |
| "learning_rate": 8.503873598980456e-05, | |
| "loss": 0.3441, | |
| "num_input_tokens_seen": 20409624, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.5819793205317577, | |
| "grad_norm": 2.332187139346983, | |
| "learning_rate": 8.495150833792478e-05, | |
| "loss": 0.2973, | |
| "num_input_tokens_seen": 20461080, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.5834564254062038, | |
| "grad_norm": 6.745585839667694, | |
| "learning_rate": 8.486407216569678e-05, | |
| "loss": 0.316, | |
| "num_input_tokens_seen": 20512000, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.5849335302806499, | |
| "grad_norm": 1.85548504039152, | |
| "learning_rate": 8.477642799476387e-05, | |
| "loss": 0.338, | |
| "num_input_tokens_seen": 20563824, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5864106351550961, | |
| "grad_norm": 1.7632477883915527, | |
| "learning_rate": 8.468857634801033e-05, | |
| "loss": 0.2472, | |
| "num_input_tokens_seen": 20615944, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.5878877400295421, | |
| "grad_norm": 1.4299099445196912, | |
| "learning_rate": 8.460051774955818e-05, | |
| "loss": 0.3045, | |
| "num_input_tokens_seen": 20666720, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.5893648449039882, | |
| "grad_norm": 1.6846270262315524, | |
| "learning_rate": 8.451225272476412e-05, | |
| "loss": 0.2606, | |
| "num_input_tokens_seen": 20718504, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 3.1983448844727196, | |
| "learning_rate": 8.442378180021644e-05, | |
| "loss": 0.2341, | |
| "num_input_tokens_seen": 20770728, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "eval_loss": 0.3366144299507141, | |
| "eval_runtime": 19.2317, | |
| "eval_samples_per_second": 3.12, | |
| "eval_steps_per_second": 0.78, | |
| "num_input_tokens_seen": 20770728, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5923190546528804, | |
| "grad_norm": 2.085951928012366, | |
| "learning_rate": 8.433510550373175e-05, | |
| "loss": 0.2844, | |
| "num_input_tokens_seen": 20823136, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 0.5937961595273265, | |
| "grad_norm": 1.3563763759741745, | |
| "learning_rate": 8.424622436435199e-05, | |
| "loss": 0.2786, | |
| "num_input_tokens_seen": 20875080, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.5952732644017725, | |
| "grad_norm": 1.9044297891885509, | |
| "learning_rate": 8.41571389123411e-05, | |
| "loss": 0.2647, | |
| "num_input_tokens_seen": 20927584, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 0.5967503692762186, | |
| "grad_norm": 16.58759330144968, | |
| "learning_rate": 8.406784967918203e-05, | |
| "loss": 0.2673, | |
| "num_input_tokens_seen": 20980640, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.5982274741506647, | |
| "grad_norm": 3.4967962357260673, | |
| "learning_rate": 8.397835719757343e-05, | |
| "loss": 0.2973, | |
| "num_input_tokens_seen": 21033272, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.5997045790251108, | |
| "grad_norm": 15.74237531026009, | |
| "learning_rate": 8.388866200142656e-05, | |
| "loss": 0.302, | |
| "num_input_tokens_seen": 21086032, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.6011816838995568, | |
| "grad_norm": 1.5694876926785786, | |
| "learning_rate": 8.379876462586203e-05, | |
| "loss": 0.2758, | |
| "num_input_tokens_seen": 21137800, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 0.6026587887740029, | |
| "grad_norm": 2.5665191340339018, | |
| "learning_rate": 8.370866560720671e-05, | |
| "loss": 0.2687, | |
| "num_input_tokens_seen": 21189264, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.604135893648449, | |
| "grad_norm": 6.275127746938625, | |
| "learning_rate": 8.361836548299045e-05, | |
| "loss": 0.295, | |
| "num_input_tokens_seen": 21240184, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 0.6056129985228951, | |
| "grad_norm": 17.85896449030129, | |
| "learning_rate": 8.352786479194288e-05, | |
| "loss": 0.2931, | |
| "num_input_tokens_seen": 21291664, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6056129985228951, | |
| "eval_loss": 0.33863261342048645, | |
| "eval_runtime": 19.3289, | |
| "eval_samples_per_second": 3.104, | |
| "eval_steps_per_second": 0.776, | |
| "num_input_tokens_seen": 21291664, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6070901033973413, | |
| "grad_norm": 1.4664266327354816, | |
| "learning_rate": 8.343716407399019e-05, | |
| "loss": 0.2338, | |
| "num_input_tokens_seen": 21344232, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 0.6085672082717873, | |
| "grad_norm": 1.440796404258189, | |
| "learning_rate": 8.334626387025197e-05, | |
| "loss": 0.3026, | |
| "num_input_tokens_seen": 21396160, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.6100443131462334, | |
| "grad_norm": 3.112422612662143, | |
| "learning_rate": 8.325516472303792e-05, | |
| "loss": 0.2898, | |
| "num_input_tokens_seen": 21448032, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 0.6115214180206795, | |
| "grad_norm": 7.791629500233522, | |
| "learning_rate": 8.316386717584463e-05, | |
| "loss": 0.3265, | |
| "num_input_tokens_seen": 21499144, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.6129985228951256, | |
| "grad_norm": 7.664415048315268, | |
| "learning_rate": 8.307237177335239e-05, | |
| "loss": 0.2513, | |
| "num_input_tokens_seen": 21551328, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.6144756277695717, | |
| "grad_norm": 7.353575088308837, | |
| "learning_rate": 8.298067906142182e-05, | |
| "loss": 0.2864, | |
| "num_input_tokens_seen": 21603800, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.6159527326440177, | |
| "grad_norm": 6.877908422150131, | |
| "learning_rate": 8.288878958709072e-05, | |
| "loss": 0.243, | |
| "num_input_tokens_seen": 21656480, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 0.6174298375184638, | |
| "grad_norm": 7.551272364447902, | |
| "learning_rate": 8.279670389857079e-05, | |
| "loss": 0.2711, | |
| "num_input_tokens_seen": 21708824, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.6189069423929099, | |
| "grad_norm": 1.5109531594598573, | |
| "learning_rate": 8.27044225452443e-05, | |
| "loss": 0.2475, | |
| "num_input_tokens_seen": 21760744, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 0.620384047267356, | |
| "grad_norm": 10.98724867961312, | |
| "learning_rate": 8.26119460776609e-05, | |
| "loss": 0.1826, | |
| "num_input_tokens_seen": 21813984, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.620384047267356, | |
| "eval_loss": 0.5386325716972351, | |
| "eval_runtime": 19.2817, | |
| "eval_samples_per_second": 3.112, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 21813984, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.621861152141802, | |
| "grad_norm": 11.844781107327274, | |
| "learning_rate": 8.251927504753426e-05, | |
| "loss": 0.3018, | |
| "num_input_tokens_seen": 21865304, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 0.6233382570162481, | |
| "grad_norm": 1.4332555229426183, | |
| "learning_rate": 8.24264100077388e-05, | |
| "loss": 0.2725, | |
| "num_input_tokens_seen": 21918568, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.6248153618906942, | |
| "grad_norm": 16.587502798944953, | |
| "learning_rate": 8.233335151230646e-05, | |
| "loss": 0.3103, | |
| "num_input_tokens_seen": 21970352, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 0.6262924667651403, | |
| "grad_norm": 2.1746923737074333, | |
| "learning_rate": 8.224010011642326e-05, | |
| "loss": 0.2868, | |
| "num_input_tokens_seen": 22021312, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.6277695716395865, | |
| "grad_norm": 20.536802693642485, | |
| "learning_rate": 8.21466563764261e-05, | |
| "loss": 0.335, | |
| "num_input_tokens_seen": 22073496, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.6292466765140325, | |
| "grad_norm": 2.23347350807466, | |
| "learning_rate": 8.205302084979937e-05, | |
| "loss": 0.3764, | |
| "num_input_tokens_seen": 22124088, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.6307237813884786, | |
| "grad_norm": 1.4129621191965986, | |
| "learning_rate": 8.19591940951717e-05, | |
| "loss": 0.2681, | |
| "num_input_tokens_seen": 22175824, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 0.6322008862629247, | |
| "grad_norm": 1.1767190413631534, | |
| "learning_rate": 8.186517667231259e-05, | |
| "loss": 0.2619, | |
| "num_input_tokens_seen": 22227376, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.6336779911373708, | |
| "grad_norm": 1.5721543022398727, | |
| "learning_rate": 8.1770969142129e-05, | |
| "loss": 0.2516, | |
| "num_input_tokens_seen": 22279928, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 0.6351550960118169, | |
| "grad_norm": 1.1838050704992382, | |
| "learning_rate": 8.167657206666217e-05, | |
| "loss": 0.2387, | |
| "num_input_tokens_seen": 22332144, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6351550960118169, | |
| "eval_loss": 0.25809118151664734, | |
| "eval_runtime": 19.3071, | |
| "eval_samples_per_second": 3.108, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 22332144, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6366322008862629, | |
| "grad_norm": 48.075734297605706, | |
| "learning_rate": 8.158198600908405e-05, | |
| "loss": 0.2606, | |
| "num_input_tokens_seen": 22383912, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 0.638109305760709, | |
| "grad_norm": 12.349268472522956, | |
| "learning_rate": 8.148721153369411e-05, | |
| "loss": 0.2672, | |
| "num_input_tokens_seen": 22435504, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.6395864106351551, | |
| "grad_norm": 17.499211985691577, | |
| "learning_rate": 8.139224920591598e-05, | |
| "loss": 0.2771, | |
| "num_input_tokens_seen": 22487696, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 0.6410635155096012, | |
| "grad_norm": 7.176310226710563, | |
| "learning_rate": 8.129709959229388e-05, | |
| "loss": 0.3018, | |
| "num_input_tokens_seen": 22539664, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.6425406203840472, | |
| "grad_norm": 22.989487671947256, | |
| "learning_rate": 8.120176326048949e-05, | |
| "loss": 0.312, | |
| "num_input_tokens_seen": 22592240, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.6440177252584933, | |
| "grad_norm": 2.0595093158376825, | |
| "learning_rate": 8.110624077927842e-05, | |
| "loss": 0.2413, | |
| "num_input_tokens_seen": 22643648, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.6454948301329394, | |
| "grad_norm": 1.0826681349485223, | |
| "learning_rate": 8.101053271854682e-05, | |
| "loss": 0.2585, | |
| "num_input_tokens_seen": 22695208, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 0.6469719350073855, | |
| "grad_norm": 1.351248688875387, | |
| "learning_rate": 8.091463964928801e-05, | |
| "loss": 0.2621, | |
| "num_input_tokens_seen": 22746896, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.6484490398818316, | |
| "grad_norm": 7.190623982268162, | |
| "learning_rate": 8.081856214359908e-05, | |
| "loss": 0.324, | |
| "num_input_tokens_seen": 22797936, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 0.6499261447562777, | |
| "grad_norm": 0.9587990520200799, | |
| "learning_rate": 8.072230077467748e-05, | |
| "loss": 0.2662, | |
| "num_input_tokens_seen": 22849552, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6499261447562777, | |
| "eval_loss": 0.48401138186454773, | |
| "eval_runtime": 19.182, | |
| "eval_samples_per_second": 3.128, | |
| "eval_steps_per_second": 0.782, | |
| "num_input_tokens_seen": 22849552, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6514032496307238, | |
| "grad_norm": 1.9654706291736397, | |
| "learning_rate": 8.062585611681758e-05, | |
| "loss": 0.3016, | |
| "num_input_tokens_seen": 22900184, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 0.6528803545051699, | |
| "grad_norm": 4.7148538513910285, | |
| "learning_rate": 8.052922874540722e-05, | |
| "loss": 0.2661, | |
| "num_input_tokens_seen": 22951816, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.654357459379616, | |
| "grad_norm": 15.154253210273424, | |
| "learning_rate": 8.043241923692436e-05, | |
| "loss": 0.2698, | |
| "num_input_tokens_seen": 23003952, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 0.6558345642540621, | |
| "grad_norm": 1.544288424619005, | |
| "learning_rate": 8.03354281689335e-05, | |
| "loss": 0.2683, | |
| "num_input_tokens_seen": 23056272, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.6573116691285081, | |
| "grad_norm": 1.7746096025671347, | |
| "learning_rate": 8.023825612008242e-05, | |
| "loss": 0.3237, | |
| "num_input_tokens_seen": 23106472, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.6587887740029542, | |
| "grad_norm": 8.974887056755184, | |
| "learning_rate": 8.014090367009859e-05, | |
| "loss": 0.2906, | |
| "num_input_tokens_seen": 23158064, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.6602658788774003, | |
| "grad_norm": 0.9042498724932153, | |
| "learning_rate": 8.004337139978574e-05, | |
| "loss": 0.2067, | |
| "num_input_tokens_seen": 23210584, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 0.6617429837518464, | |
| "grad_norm": 1.7463381173392456, | |
| "learning_rate": 7.994565989102042e-05, | |
| "loss": 0.2648, | |
| "num_input_tokens_seen": 23262864, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.6632200886262924, | |
| "grad_norm": 2.846956174007256, | |
| "learning_rate": 7.98477697267485e-05, | |
| "loss": 0.2496, | |
| "num_input_tokens_seen": 23314568, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 0.6646971935007385, | |
| "grad_norm": 4.665885044883532, | |
| "learning_rate": 7.974970149098174e-05, | |
| "loss": 0.2332, | |
| "num_input_tokens_seen": 23366784, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6646971935007385, | |
| "eval_loss": 0.4966147541999817, | |
| "eval_runtime": 19.1792, | |
| "eval_samples_per_second": 3.128, | |
| "eval_steps_per_second": 0.782, | |
| "num_input_tokens_seen": 23366784, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6661742983751846, | |
| "grad_norm": 1.646844160605743, | |
| "learning_rate": 7.965145576879423e-05, | |
| "loss": 0.3135, | |
| "num_input_tokens_seen": 23418504, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 0.6676514032496307, | |
| "grad_norm": 4.433343767927195, | |
| "learning_rate": 7.955303314631898e-05, | |
| "loss": 0.3268, | |
| "num_input_tokens_seen": 23469840, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.6691285081240768, | |
| "grad_norm": 2.741861673744247, | |
| "learning_rate": 7.945443421074436e-05, | |
| "loss": 0.2706, | |
| "num_input_tokens_seen": 23521416, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 0.670605612998523, | |
| "grad_norm": 13.390920032881771, | |
| "learning_rate": 7.935565955031064e-05, | |
| "loss": 0.2044, | |
| "num_input_tokens_seen": 23573176, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.672082717872969, | |
| "grad_norm": 4.093699227168353, | |
| "learning_rate": 7.925670975430644e-05, | |
| "loss": 0.2724, | |
| "num_input_tokens_seen": 23625080, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.6735598227474151, | |
| "grad_norm": 1.060930943475367, | |
| "learning_rate": 7.915758541306523e-05, | |
| "loss": 0.2543, | |
| "num_input_tokens_seen": 23677096, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.6750369276218612, | |
| "grad_norm": 2.1755423246760515, | |
| "learning_rate": 7.90582871179619e-05, | |
| "loss": 0.2372, | |
| "num_input_tokens_seen": 23729168, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 0.6765140324963073, | |
| "grad_norm": 8.00546036386453, | |
| "learning_rate": 7.895881546140902e-05, | |
| "loss": 0.2695, | |
| "num_input_tokens_seen": 23780568, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.6779911373707533, | |
| "grad_norm": 7.074026968521074, | |
| "learning_rate": 7.885917103685353e-05, | |
| "loss": 0.3282, | |
| "num_input_tokens_seen": 23831360, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 0.6794682422451994, | |
| "grad_norm": 1.221854745565416, | |
| "learning_rate": 7.875935443877305e-05, | |
| "loss": 0.2481, | |
| "num_input_tokens_seen": 23883032, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6794682422451994, | |
| "eval_loss": 0.24180778861045837, | |
| "eval_runtime": 18.9575, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.791, | |
| "num_input_tokens_seen": 23883032, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6809453471196455, | |
| "grad_norm": 15.468575933907964, | |
| "learning_rate": 7.865936626267243e-05, | |
| "loss": 0.2474, | |
| "num_input_tokens_seen": 23934880, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 0.6824224519940916, | |
| "grad_norm": 3.9259269918244932, | |
| "learning_rate": 7.855920710508009e-05, | |
| "loss": 0.2613, | |
| "num_input_tokens_seen": 23986160, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.6838995568685377, | |
| "grad_norm": 1.443222642921112, | |
| "learning_rate": 7.845887756354458e-05, | |
| "loss": 0.1957, | |
| "num_input_tokens_seen": 24038984, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 0.6853766617429837, | |
| "grad_norm": 2.418773014069429, | |
| "learning_rate": 7.835837823663092e-05, | |
| "loss": 0.2709, | |
| "num_input_tokens_seen": 24090648, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.6868537666174298, | |
| "grad_norm": 1.2678547091245644, | |
| "learning_rate": 7.825770972391712e-05, | |
| "loss": 0.2873, | |
| "num_input_tokens_seen": 24142200, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.6883308714918759, | |
| "grad_norm": 1.5899740505737827, | |
| "learning_rate": 7.81568726259905e-05, | |
| "loss": 0.2378, | |
| "num_input_tokens_seen": 24194400, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.689807976366322, | |
| "grad_norm": 1.6209911075093861, | |
| "learning_rate": 7.805586754444416e-05, | |
| "loss": 0.2615, | |
| "num_input_tokens_seen": 24245328, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 0.691285081240768, | |
| "grad_norm": 16.06254938606901, | |
| "learning_rate": 7.795469508187343e-05, | |
| "loss": 0.2234, | |
| "num_input_tokens_seen": 24297400, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.6927621861152142, | |
| "grad_norm": 2.2353075576651085, | |
| "learning_rate": 7.785335584187219e-05, | |
| "loss": 0.2833, | |
| "num_input_tokens_seen": 24348536, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.6942392909896603, | |
| "grad_norm": 11.321777956495533, | |
| "learning_rate": 7.775185042902933e-05, | |
| "loss": 0.2313, | |
| "num_input_tokens_seen": 24401256, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6942392909896603, | |
| "eval_loss": 0.1869634985923767, | |
| "eval_runtime": 19.499, | |
| "eval_samples_per_second": 3.077, | |
| "eval_steps_per_second": 0.769, | |
| "num_input_tokens_seen": 24401256, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6957163958641064, | |
| "grad_norm": 1.2627287884293426, | |
| "learning_rate": 7.765017944892514e-05, | |
| "loss": 0.2499, | |
| "num_input_tokens_seen": 24453384, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 0.6971935007385525, | |
| "grad_norm": 1.476393664852338, | |
| "learning_rate": 7.754834350812765e-05, | |
| "loss": 0.2132, | |
| "num_input_tokens_seen": 24505960, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.6986706056129985, | |
| "grad_norm": 3.9395522365245226, | |
| "learning_rate": 7.744634321418906e-05, | |
| "loss": 0.2049, | |
| "num_input_tokens_seen": 24559008, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 0.7001477104874446, | |
| "grad_norm": 2.1895254551218115, | |
| "learning_rate": 7.734417917564211e-05, | |
| "loss": 0.2222, | |
| "num_input_tokens_seen": 24611128, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.7016248153618907, | |
| "grad_norm": 2.3733905521598353, | |
| "learning_rate": 7.724185200199643e-05, | |
| "loss": 0.2678, | |
| "num_input_tokens_seen": 24662336, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.7031019202363368, | |
| "grad_norm": 6.930201726148201, | |
| "learning_rate": 7.713936230373491e-05, | |
| "loss": 0.2888, | |
| "num_input_tokens_seen": 24714032, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.7045790251107829, | |
| "grad_norm": 1.2305357870388025, | |
| "learning_rate": 7.703671069231007e-05, | |
| "loss": 0.2609, | |
| "num_input_tokens_seen": 24765296, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 0.7060561299852289, | |
| "grad_norm": 1.3830979392967684, | |
| "learning_rate": 7.693389778014037e-05, | |
| "loss": 0.2654, | |
| "num_input_tokens_seen": 24816744, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.707533234859675, | |
| "grad_norm": 1.641476112098168, | |
| "learning_rate": 7.683092418060664e-05, | |
| "loss": 0.2231, | |
| "num_input_tokens_seen": 24869320, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 0.7090103397341211, | |
| "grad_norm": 9.651892844655563, | |
| "learning_rate": 7.672779050804834e-05, | |
| "loss": 0.262, | |
| "num_input_tokens_seen": 24921872, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7090103397341211, | |
| "eval_loss": 0.34713664650917053, | |
| "eval_runtime": 18.9635, | |
| "eval_samples_per_second": 3.164, | |
| "eval_steps_per_second": 0.791, | |
| "num_input_tokens_seen": 24921872, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7104874446085672, | |
| "grad_norm": 1.761600275948819, | |
| "learning_rate": 7.662449737775991e-05, | |
| "loss": 0.2704, | |
| "num_input_tokens_seen": 24973200, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 0.7119645494830132, | |
| "grad_norm": 1.9815653528675592, | |
| "learning_rate": 7.652104540598712e-05, | |
| "loss": 0.2792, | |
| "num_input_tokens_seen": 25024168, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.7134416543574594, | |
| "grad_norm": 8.315884146956419, | |
| "learning_rate": 7.641743520992343e-05, | |
| "loss": 0.2798, | |
| "num_input_tokens_seen": 25075704, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 0.7149187592319055, | |
| "grad_norm": 0.7729904952291985, | |
| "learning_rate": 7.631366740770622e-05, | |
| "loss": 0.2411, | |
| "num_input_tokens_seen": 25128264, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.7163958641063516, | |
| "grad_norm": 2.9686769656164547, | |
| "learning_rate": 7.620974261841314e-05, | |
| "loss": 0.2204, | |
| "num_input_tokens_seen": 25180080, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.7178729689807977, | |
| "grad_norm": 1.4885611311756322, | |
| "learning_rate": 7.610566146205846e-05, | |
| "loss": 0.2295, | |
| "num_input_tokens_seen": 25232312, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.7193500738552437, | |
| "grad_norm": 17.482084035542726, | |
| "learning_rate": 7.60014245595893e-05, | |
| "loss": 0.3177, | |
| "num_input_tokens_seen": 25283688, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 0.7208271787296898, | |
| "grad_norm": 2.0884881532897253, | |
| "learning_rate": 7.589703253288196e-05, | |
| "loss": 0.2606, | |
| "num_input_tokens_seen": 25335656, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.7223042836041359, | |
| "grad_norm": 2.1877676236194934, | |
| "learning_rate": 7.579248600473827e-05, | |
| "loss": 0.2406, | |
| "num_input_tokens_seen": 25387752, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 0.723781388478582, | |
| "grad_norm": 1.04372356426487, | |
| "learning_rate": 7.568778559888173e-05, | |
| "loss": 0.2412, | |
| "num_input_tokens_seen": 25439896, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.723781388478582, | |
| "eval_loss": 0.34561124444007874, | |
| "eval_runtime": 19.0832, | |
| "eval_samples_per_second": 3.144, | |
| "eval_steps_per_second": 0.786, | |
| "num_input_tokens_seen": 25439896, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.725258493353028, | |
| "grad_norm": 15.826053352114771, | |
| "learning_rate": 7.558293193995394e-05, | |
| "loss": 0.2752, | |
| "num_input_tokens_seen": 25491160, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 0.7267355982274741, | |
| "grad_norm": 1.401909903248283, | |
| "learning_rate": 7.547792565351075e-05, | |
| "loss": 0.2399, | |
| "num_input_tokens_seen": 25543152, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.7282127031019202, | |
| "grad_norm": 0.8017657229162621, | |
| "learning_rate": 7.537276736601864e-05, | |
| "loss": 0.2351, | |
| "num_input_tokens_seen": 25595312, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 0.7296898079763663, | |
| "grad_norm": 1.4744204191665158, | |
| "learning_rate": 7.526745770485088e-05, | |
| "loss": 0.1837, | |
| "num_input_tokens_seen": 25648680, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.7311669128508124, | |
| "grad_norm": 1.2465650859091382, | |
| "learning_rate": 7.516199729828385e-05, | |
| "loss": 0.3093, | |
| "num_input_tokens_seen": 25701464, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.7326440177252584, | |
| "grad_norm": 1.880567862109699, | |
| "learning_rate": 7.505638677549327e-05, | |
| "loss": 0.223, | |
| "num_input_tokens_seen": 25753528, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.7341211225997046, | |
| "grad_norm": 0.6866693023387563, | |
| "learning_rate": 7.495062676655049e-05, | |
| "loss": 0.2128, | |
| "num_input_tokens_seen": 25805768, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 0.7355982274741507, | |
| "grad_norm": 1.1016249736691914, | |
| "learning_rate": 7.484471790241865e-05, | |
| "loss": 0.2703, | |
| "num_input_tokens_seen": 25856672, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.7370753323485968, | |
| "grad_norm": 11.244379366241214, | |
| "learning_rate": 7.473866081494896e-05, | |
| "loss": 0.2456, | |
| "num_input_tokens_seen": 25908544, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 0.7385524372230429, | |
| "grad_norm": 1.4228671338565775, | |
| "learning_rate": 7.463245613687695e-05, | |
| "loss": 0.2382, | |
| "num_input_tokens_seen": 25961056, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7385524372230429, | |
| "eval_loss": 0.2542795240879059, | |
| "eval_runtime": 19.1344, | |
| "eval_samples_per_second": 3.136, | |
| "eval_steps_per_second": 0.784, | |
| "num_input_tokens_seen": 25961056, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.740029542097489, | |
| "grad_norm": 3.4127573468108934, | |
| "learning_rate": 7.452610450181865e-05, | |
| "loss": 0.2843, | |
| "num_input_tokens_seen": 26012232, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 0.741506646971935, | |
| "grad_norm": 1.8065383217954118, | |
| "learning_rate": 7.441960654426687e-05, | |
| "loss": 0.2376, | |
| "num_input_tokens_seen": 26064432, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.7429837518463811, | |
| "grad_norm": 1.038286812818806, | |
| "learning_rate": 7.431296289958735e-05, | |
| "loss": 0.2464, | |
| "num_input_tokens_seen": 26115856, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 0.7444608567208272, | |
| "grad_norm": 1.3908978510260759, | |
| "learning_rate": 7.4206174204015e-05, | |
| "loss": 0.2793, | |
| "num_input_tokens_seen": 26167176, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.7459379615952733, | |
| "grad_norm": 1.785011959334391, | |
| "learning_rate": 7.409924109465011e-05, | |
| "loss": 0.2141, | |
| "num_input_tokens_seen": 26219144, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.7474150664697193, | |
| "grad_norm": 1.0393762543520273, | |
| "learning_rate": 7.399216420945453e-05, | |
| "loss": 0.2137, | |
| "num_input_tokens_seen": 26271712, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.7488921713441654, | |
| "grad_norm": 5.12895726872253, | |
| "learning_rate": 7.388494418724789e-05, | |
| "loss": 0.2177, | |
| "num_input_tokens_seen": 26323656, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 0.7503692762186115, | |
| "grad_norm": 9.06455667620907, | |
| "learning_rate": 7.377758166770377e-05, | |
| "loss": 0.2762, | |
| "num_input_tokens_seen": 26375392, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.7518463810930576, | |
| "grad_norm": 1.4100384205361678, | |
| "learning_rate": 7.367007729134588e-05, | |
| "loss": 0.2794, | |
| "num_input_tokens_seen": 26426080, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 0.7533234859675036, | |
| "grad_norm": 0.9925649690798728, | |
| "learning_rate": 7.356243169954426e-05, | |
| "loss": 0.2364, | |
| "num_input_tokens_seen": 26477208, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7533234859675036, | |
| "eval_loss": 0.38712552189826965, | |
| "eval_runtime": 19.0707, | |
| "eval_samples_per_second": 3.146, | |
| "eval_steps_per_second": 0.787, | |
| "num_input_tokens_seen": 26477208, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7548005908419497, | |
| "grad_norm": 9.286838829443976, | |
| "learning_rate": 7.34546455345114e-05, | |
| "loss": 0.2649, | |
| "num_input_tokens_seen": 26528824, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 0.7562776957163959, | |
| "grad_norm": 0.847615423645702, | |
| "learning_rate": 7.334671943929853e-05, | |
| "loss": 0.1834, | |
| "num_input_tokens_seen": 26581512, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.757754800590842, | |
| "grad_norm": 11.003109854541512, | |
| "learning_rate": 7.323865405779162e-05, | |
| "loss": 0.2539, | |
| "num_input_tokens_seen": 26633144, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 0.7592319054652881, | |
| "grad_norm": 1.2876198439398636, | |
| "learning_rate": 7.313045003470766e-05, | |
| "loss": 0.2592, | |
| "num_input_tokens_seen": 26684024, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.7607090103397341, | |
| "grad_norm": 1.1302004834491934, | |
| "learning_rate": 7.302210801559075e-05, | |
| "loss": 0.228, | |
| "num_input_tokens_seen": 26736512, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.7621861152141802, | |
| "grad_norm": 11.72346624813136, | |
| "learning_rate": 7.291362864680831e-05, | |
| "loss": 0.232, | |
| "num_input_tokens_seen": 26788656, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.7636632200886263, | |
| "grad_norm": 1.5381808841738496, | |
| "learning_rate": 7.280501257554716e-05, | |
| "loss": 0.2411, | |
| "num_input_tokens_seen": 26840856, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 0.7651403249630724, | |
| "grad_norm": 0.8088247020348738, | |
| "learning_rate": 7.269626044980968e-05, | |
| "loss": 0.2214, | |
| "num_input_tokens_seen": 26892840, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.7666174298375185, | |
| "grad_norm": 19.483946991905242, | |
| "learning_rate": 7.258737291841e-05, | |
| "loss": 0.236, | |
| "num_input_tokens_seen": 26945200, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 0.7680945347119645, | |
| "grad_norm": 1.070187466620262, | |
| "learning_rate": 7.247835063097e-05, | |
| "loss": 0.2082, | |
| "num_input_tokens_seen": 26997904, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7680945347119645, | |
| "eval_loss": 0.3406156003475189, | |
| "eval_runtime": 19.2307, | |
| "eval_samples_per_second": 3.12, | |
| "eval_steps_per_second": 0.78, | |
| "num_input_tokens_seen": 26997904, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7695716395864106, | |
| "grad_norm": 8.368958056782812, | |
| "learning_rate": 7.236919423791556e-05, | |
| "loss": 0.1983, | |
| "num_input_tokens_seen": 27050064, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 0.7710487444608567, | |
| "grad_norm": 45.77692642603359, | |
| "learning_rate": 7.225990439047264e-05, | |
| "loss": 0.2442, | |
| "num_input_tokens_seen": 27102096, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.7725258493353028, | |
| "grad_norm": 0.9661489018651128, | |
| "learning_rate": 7.215048174066337e-05, | |
| "loss": 0.2095, | |
| "num_input_tokens_seen": 27155064, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 0.7740029542097489, | |
| "grad_norm": 1.7684270980979584, | |
| "learning_rate": 7.204092694130218e-05, | |
| "loss": 0.2332, | |
| "num_input_tokens_seen": 27206472, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.7754800590841949, | |
| "grad_norm": 1.480868253020904, | |
| "learning_rate": 7.193124064599188e-05, | |
| "loss": 0.2078, | |
| "num_input_tokens_seen": 27258792, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.7769571639586411, | |
| "grad_norm": 1.586650982980591, | |
| "learning_rate": 7.182142350911985e-05, | |
| "loss": 0.2311, | |
| "num_input_tokens_seen": 27310840, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.7784342688330872, | |
| "grad_norm": 1.4722666794337897, | |
| "learning_rate": 7.1711476185854e-05, | |
| "loss": 0.2639, | |
| "num_input_tokens_seen": 27362496, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 0.7799113737075333, | |
| "grad_norm": 1.8648085527091647, | |
| "learning_rate": 7.160139933213898e-05, | |
| "loss": 0.2475, | |
| "num_input_tokens_seen": 27414544, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.7813884785819794, | |
| "grad_norm": 1.1194589162002906, | |
| "learning_rate": 7.149119360469217e-05, | |
| "loss": 0.1917, | |
| "num_input_tokens_seen": 27467408, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 0.7828655834564254, | |
| "grad_norm": 1.1768147878553037, | |
| "learning_rate": 7.138085966099985e-05, | |
| "loss": 0.1736, | |
| "num_input_tokens_seen": 27521088, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7828655834564254, | |
| "eval_loss": 0.269732803106308, | |
| "eval_runtime": 18.9263, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 0.793, | |
| "num_input_tokens_seen": 27521088, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7843426883308715, | |
| "grad_norm": 21.321277048653876, | |
| "learning_rate": 7.127039815931322e-05, | |
| "loss": 0.2047, | |
| "num_input_tokens_seen": 27573512, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 0.7858197932053176, | |
| "grad_norm": 17.20183228158753, | |
| "learning_rate": 7.11598097586445e-05, | |
| "loss": 0.2309, | |
| "num_input_tokens_seen": 27625488, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.7872968980797637, | |
| "grad_norm": 1.7315172011761586, | |
| "learning_rate": 7.104909511876293e-05, | |
| "loss": 0.2188, | |
| "num_input_tokens_seen": 27677824, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 0.7887740029542097, | |
| "grad_norm": 1.1907445578210916, | |
| "learning_rate": 7.0938254900191e-05, | |
| "loss": 0.2127, | |
| "num_input_tokens_seen": 27730048, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.7902511078286558, | |
| "grad_norm": 1.81826608908883, | |
| "learning_rate": 7.082728976420032e-05, | |
| "loss": 0.2534, | |
| "num_input_tokens_seen": 27781512, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.7917282127031019, | |
| "grad_norm": 1.2558672573153766, | |
| "learning_rate": 7.071620037280779e-05, | |
| "loss": 0.204, | |
| "num_input_tokens_seen": 27833808, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.793205317577548, | |
| "grad_norm": 16.755851819106958, | |
| "learning_rate": 7.060498738877159e-05, | |
| "loss": 0.2218, | |
| "num_input_tokens_seen": 27886232, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 0.794682422451994, | |
| "grad_norm": 1.6442173318750486, | |
| "learning_rate": 7.049365147558727e-05, | |
| "loss": 0.2157, | |
| "num_input_tokens_seen": 27938696, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.7961595273264401, | |
| "grad_norm": 20.30442824896465, | |
| "learning_rate": 7.038219329748376e-05, | |
| "loss": 0.2401, | |
| "num_input_tokens_seen": 27990816, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 0.7976366322008862, | |
| "grad_norm": 0.9565866694207389, | |
| "learning_rate": 7.027061351941948e-05, | |
| "loss": 0.2225, | |
| "num_input_tokens_seen": 28042992, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7976366322008862, | |
| "eval_loss": 0.41549214720726013, | |
| "eval_runtime": 18.9524, | |
| "eval_samples_per_second": 3.166, | |
| "eval_steps_per_second": 0.791, | |
| "num_input_tokens_seen": 28042992, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7991137370753324, | |
| "grad_norm": 1.2540711450587154, | |
| "learning_rate": 7.01589128070782e-05, | |
| "loss": 0.2279, | |
| "num_input_tokens_seen": 28094200, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 0.8005908419497785, | |
| "grad_norm": 1.1647829910589267, | |
| "learning_rate": 7.004709182686531e-05, | |
| "loss": 0.2307, | |
| "num_input_tokens_seen": 28146144, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.8020679468242246, | |
| "grad_norm": 1.911821987729577, | |
| "learning_rate": 6.993515124590362e-05, | |
| "loss": 0.2025, | |
| "num_input_tokens_seen": 28198600, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 0.8035450516986706, | |
| "grad_norm": 3.9104392867751003, | |
| "learning_rate": 6.982309173202951e-05, | |
| "loss": 0.2318, | |
| "num_input_tokens_seen": 28249928, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.8050221565731167, | |
| "grad_norm": 3.023688281243673, | |
| "learning_rate": 6.971091395378895e-05, | |
| "loss": 0.2074, | |
| "num_input_tokens_seen": 28301928, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.8064992614475628, | |
| "grad_norm": 1.4517739851550877, | |
| "learning_rate": 6.95986185804334e-05, | |
| "loss": 0.1935, | |
| "num_input_tokens_seen": 28354256, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.8079763663220089, | |
| "grad_norm": 1.273143787849072, | |
| "learning_rate": 6.948620628191595e-05, | |
| "loss": 0.2457, | |
| "num_input_tokens_seen": 28405800, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 0.8094534711964549, | |
| "grad_norm": 7.171460586418023, | |
| "learning_rate": 6.937367772888725e-05, | |
| "loss": 0.2021, | |
| "num_input_tokens_seen": 28457664, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.810930576070901, | |
| "grad_norm": 4.016097948044553, | |
| "learning_rate": 6.926103359269152e-05, | |
| "loss": 0.2323, | |
| "num_input_tokens_seen": 28509944, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 0.8124076809453471, | |
| "grad_norm": 1.7260282738026802, | |
| "learning_rate": 6.914827454536254e-05, | |
| "loss": 0.2501, | |
| "num_input_tokens_seen": 28561248, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8124076809453471, | |
| "eval_loss": 0.41148969531059265, | |
| "eval_runtime": 19.291, | |
| "eval_samples_per_second": 3.11, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 28561248, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8138847858197932, | |
| "grad_norm": 1.1919186743284782, | |
| "learning_rate": 6.903540125961965e-05, | |
| "loss": 0.225, | |
| "num_input_tokens_seen": 28613120, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 0.8153618906942393, | |
| "grad_norm": 1.4599715179768002, | |
| "learning_rate": 6.892241440886377e-05, | |
| "loss": 0.2365, | |
| "num_input_tokens_seen": 28664864, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.8168389955686853, | |
| "grad_norm": 1.2279132312954155, | |
| "learning_rate": 6.880931466717327e-05, | |
| "loss": 0.2386, | |
| "num_input_tokens_seen": 28716896, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 0.8183161004431314, | |
| "grad_norm": 22.206631253466607, | |
| "learning_rate": 6.86961027093001e-05, | |
| "loss": 0.2358, | |
| "num_input_tokens_seen": 28769528, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.8197932053175776, | |
| "grad_norm": 6.630701043823761, | |
| "learning_rate": 6.858277921066568e-05, | |
| "loss": 0.2844, | |
| "num_input_tokens_seen": 28821304, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.8212703101920237, | |
| "grad_norm": 0.7473512414072709, | |
| "learning_rate": 6.846934484735686e-05, | |
| "loss": 0.1867, | |
| "num_input_tokens_seen": 28872712, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.8227474150664698, | |
| "grad_norm": 1.1277045436573916, | |
| "learning_rate": 6.83558002961219e-05, | |
| "loss": 0.2184, | |
| "num_input_tokens_seen": 28924272, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 0.8242245199409158, | |
| "grad_norm": 14.609958116422174, | |
| "learning_rate": 6.824214623436644e-05, | |
| "loss": 0.1938, | |
| "num_input_tokens_seen": 28976352, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.8257016248153619, | |
| "grad_norm": 1.2950871631178849, | |
| "learning_rate": 6.812838334014951e-05, | |
| "loss": 0.2046, | |
| "num_input_tokens_seen": 29028344, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 0.827178729689808, | |
| "grad_norm": 1.6899801995875487, | |
| "learning_rate": 6.801451229217938e-05, | |
| "loss": 0.2507, | |
| "num_input_tokens_seen": 29079576, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.827178729689808, | |
| "eval_loss": 0.32233569025993347, | |
| "eval_runtime": 19.2788, | |
| "eval_samples_per_second": 3.112, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 29079576, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8286558345642541, | |
| "grad_norm": 1.7749470743647537, | |
| "learning_rate": 6.790053376980959e-05, | |
| "loss": 0.1752, | |
| "num_input_tokens_seen": 29131768, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 0.8301329394387001, | |
| "grad_norm": 1.3850536432850993, | |
| "learning_rate": 6.778644845303483e-05, | |
| "loss": 0.2502, | |
| "num_input_tokens_seen": 29183952, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.8316100443131462, | |
| "grad_norm": 1.0103366085788665, | |
| "learning_rate": 6.767225702248698e-05, | |
| "loss": 0.2092, | |
| "num_input_tokens_seen": 29236232, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 0.8330871491875923, | |
| "grad_norm": 13.569757844040682, | |
| "learning_rate": 6.755796015943097e-05, | |
| "loss": 0.2492, | |
| "num_input_tokens_seen": 29287672, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.8345642540620384, | |
| "grad_norm": 1.23710967928213, | |
| "learning_rate": 6.744355854576075e-05, | |
| "loss": 0.2377, | |
| "num_input_tokens_seen": 29339952, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.8360413589364845, | |
| "grad_norm": 1.3865093164785327, | |
| "learning_rate": 6.732905286399516e-05, | |
| "loss": 0.168, | |
| "num_input_tokens_seen": 29392128, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.8375184638109305, | |
| "grad_norm": 1.585429725562894, | |
| "learning_rate": 6.721444379727398e-05, | |
| "loss": 0.1919, | |
| "num_input_tokens_seen": 29444168, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 0.8389955686853766, | |
| "grad_norm": 9.069319490379504, | |
| "learning_rate": 6.709973202935374e-05, | |
| "loss": 0.2225, | |
| "num_input_tokens_seen": 29495592, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.8404726735598228, | |
| "grad_norm": 0.9134374448072771, | |
| "learning_rate": 6.698491824460371e-05, | |
| "loss": 0.1715, | |
| "num_input_tokens_seen": 29548008, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 0.8419497784342689, | |
| "grad_norm": 1.4124132378382863, | |
| "learning_rate": 6.687000312800178e-05, | |
| "loss": 0.1928, | |
| "num_input_tokens_seen": 29600536, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.8419497784342689, | |
| "eval_loss": 0.28275948762893677, | |
| "eval_runtime": 19.4837, | |
| "eval_samples_per_second": 3.08, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 29600536, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.843426883308715, | |
| "grad_norm": 1.4547945162774674, | |
| "learning_rate": 6.675498736513036e-05, | |
| "loss": 0.2163, | |
| "num_input_tokens_seen": 29652440, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 0.844903988183161, | |
| "grad_norm": 1.3348915008279034, | |
| "learning_rate": 6.663987164217236e-05, | |
| "loss": 0.2589, | |
| "num_input_tokens_seen": 29704376, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.8463810930576071, | |
| "grad_norm": 2.2889038673998603, | |
| "learning_rate": 6.652465664590703e-05, | |
| "loss": 0.2325, | |
| "num_input_tokens_seen": 29756504, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 0.8478581979320532, | |
| "grad_norm": 1.3144459851000174, | |
| "learning_rate": 6.640934306370586e-05, | |
| "loss": 0.242, | |
| "num_input_tokens_seen": 29807328, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.8493353028064993, | |
| "grad_norm": 1.2238000417554058, | |
| "learning_rate": 6.629393158352854e-05, | |
| "loss": 0.2169, | |
| "num_input_tokens_seen": 29859208, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.8508124076809453, | |
| "grad_norm": 1.5853683051276755, | |
| "learning_rate": 6.61784228939188e-05, | |
| "loss": 0.2335, | |
| "num_input_tokens_seen": 29911128, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.8522895125553914, | |
| "grad_norm": 0.8463095817606877, | |
| "learning_rate": 6.606281768400032e-05, | |
| "loss": 0.1913, | |
| "num_input_tokens_seen": 29962384, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 0.8537666174298375, | |
| "grad_norm": 1.6841064365294203, | |
| "learning_rate": 6.594711664347264e-05, | |
| "loss": 0.2425, | |
| "num_input_tokens_seen": 30013664, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.8552437223042836, | |
| "grad_norm": 1.1559578384960632, | |
| "learning_rate": 6.5831320462607e-05, | |
| "loss": 0.2312, | |
| "num_input_tokens_seen": 30066016, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 0.8567208271787297, | |
| "grad_norm": 0.9327537302615286, | |
| "learning_rate": 6.571542983224223e-05, | |
| "loss": 0.2029, | |
| "num_input_tokens_seen": 30118072, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8567208271787297, | |
| "eval_loss": 0.39434579014778137, | |
| "eval_runtime": 19.1253, | |
| "eval_samples_per_second": 3.137, | |
| "eval_steps_per_second": 0.784, | |
| "num_input_tokens_seen": 30118072, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8581979320531757, | |
| "grad_norm": 1.2779653791980783, | |
| "learning_rate": 6.559944544378072e-05, | |
| "loss": 0.2241, | |
| "num_input_tokens_seen": 30170248, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 0.8596750369276218, | |
| "grad_norm": 1.6407050078852088, | |
| "learning_rate": 6.548336798918411e-05, | |
| "loss": 0.2298, | |
| "num_input_tokens_seen": 30222016, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.8611521418020679, | |
| "grad_norm": 1.5078723595666699, | |
| "learning_rate": 6.536719816096935e-05, | |
| "loss": 0.2396, | |
| "num_input_tokens_seen": 30273312, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 0.8626292466765141, | |
| "grad_norm": 1.852309531147588, | |
| "learning_rate": 6.52509366522045e-05, | |
| "loss": 0.2324, | |
| "num_input_tokens_seen": 30324328, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.8641063515509602, | |
| "grad_norm": 1.3789560520965807, | |
| "learning_rate": 6.513458415650452e-05, | |
| "loss": 0.2263, | |
| "num_input_tokens_seen": 30376488, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.8655834564254062, | |
| "grad_norm": 1.904793400524472, | |
| "learning_rate": 6.501814136802725e-05, | |
| "loss": 0.1734, | |
| "num_input_tokens_seen": 30429504, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.8670605612998523, | |
| "grad_norm": 1.15273615308065, | |
| "learning_rate": 6.490160898146918e-05, | |
| "loss": 0.2235, | |
| "num_input_tokens_seen": 30480400, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 0.8685376661742984, | |
| "grad_norm": 1.4070108528869274, | |
| "learning_rate": 6.47849876920614e-05, | |
| "loss": 0.2297, | |
| "num_input_tokens_seen": 30531912, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.8700147710487445, | |
| "grad_norm": 1.182373794273276, | |
| "learning_rate": 6.46682781955653e-05, | |
| "loss": 0.1764, | |
| "num_input_tokens_seen": 30584688, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 0.8714918759231906, | |
| "grad_norm": 17.302996120392294, | |
| "learning_rate": 6.455148118826859e-05, | |
| "loss": 0.1692, | |
| "num_input_tokens_seen": 30637448, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8714918759231906, | |
| "eval_loss": 0.20344533026218414, | |
| "eval_runtime": 18.8463, | |
| "eval_samples_per_second": 3.184, | |
| "eval_steps_per_second": 0.796, | |
| "num_input_tokens_seen": 30637448, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8729689807976366, | |
| "grad_norm": 1.8856590605160186, | |
| "learning_rate": 6.443459736698105e-05, | |
| "loss": 0.152, | |
| "num_input_tokens_seen": 30690624, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 0.8744460856720827, | |
| "grad_norm": 1.6528236741968945, | |
| "learning_rate": 6.431762742903038e-05, | |
| "loss": 0.1945, | |
| "num_input_tokens_seen": 30742992, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.8759231905465288, | |
| "grad_norm": 8.103341069666943, | |
| "learning_rate": 6.420057207225807e-05, | |
| "loss": 0.2177, | |
| "num_input_tokens_seen": 30795256, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 0.8774002954209749, | |
| "grad_norm": 1.1109514825198903, | |
| "learning_rate": 6.408343199501519e-05, | |
| "loss": 0.1579, | |
| "num_input_tokens_seen": 30847696, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.8788774002954209, | |
| "grad_norm": 1.2328126120792269, | |
| "learning_rate": 6.396620789615825e-05, | |
| "loss": 0.1943, | |
| "num_input_tokens_seen": 30899904, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.880354505169867, | |
| "grad_norm": 1.3844672046567905, | |
| "learning_rate": 6.384890047504508e-05, | |
| "loss": 0.1749, | |
| "num_input_tokens_seen": 30952168, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.8818316100443131, | |
| "grad_norm": 1.3306213585837874, | |
| "learning_rate": 6.373151043153056e-05, | |
| "loss": 0.2156, | |
| "num_input_tokens_seen": 31004192, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 0.8833087149187593, | |
| "grad_norm": 1.3085143966848831, | |
| "learning_rate": 6.361403846596252e-05, | |
| "loss": 0.2083, | |
| "num_input_tokens_seen": 31056712, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.8847858197932054, | |
| "grad_norm": 0.8113418641584603, | |
| "learning_rate": 6.349648527917752e-05, | |
| "loss": 0.1721, | |
| "num_input_tokens_seen": 31108944, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 0.8862629246676514, | |
| "grad_norm": 1.4549871288078948, | |
| "learning_rate": 6.33788515724967e-05, | |
| "loss": 0.234, | |
| "num_input_tokens_seen": 31159736, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8862629246676514, | |
| "eval_loss": 0.25555509328842163, | |
| "eval_runtime": 19.3746, | |
| "eval_samples_per_second": 3.097, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 31159736, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8877400295420975, | |
| "grad_norm": 1.2324370262682327, | |
| "learning_rate": 6.326113804772157e-05, | |
| "loss": 0.2011, | |
| "num_input_tokens_seen": 31211632, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 0.8892171344165436, | |
| "grad_norm": 1.7142403977850047, | |
| "learning_rate": 6.314334540712983e-05, | |
| "loss": 0.2197, | |
| "num_input_tokens_seen": 31264376, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.8906942392909897, | |
| "grad_norm": 1.50601762442169, | |
| "learning_rate": 6.302547435347122e-05, | |
| "loss": 0.1853, | |
| "num_input_tokens_seen": 31316584, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 0.8921713441654358, | |
| "grad_norm": 1.2451326697290692, | |
| "learning_rate": 6.290752558996325e-05, | |
| "loss": 0.2312, | |
| "num_input_tokens_seen": 31367768, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.8936484490398818, | |
| "grad_norm": 1.3816673419860452, | |
| "learning_rate": 6.278949982028704e-05, | |
| "loss": 0.2608, | |
| "num_input_tokens_seen": 31419664, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.8951255539143279, | |
| "grad_norm": 1.430852186731335, | |
| "learning_rate": 6.267139774858318e-05, | |
| "loss": 0.225, | |
| "num_input_tokens_seen": 31471672, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.896602658788774, | |
| "grad_norm": 22.943001206859204, | |
| "learning_rate": 6.255322007944743e-05, | |
| "loss": 0.225, | |
| "num_input_tokens_seen": 31523888, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 0.8980797636632201, | |
| "grad_norm": 0.8776969753848171, | |
| "learning_rate": 6.243496751792658e-05, | |
| "loss": 0.2291, | |
| "num_input_tokens_seen": 31574992, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.8995568685376661, | |
| "grad_norm": 0.8040234911638864, | |
| "learning_rate": 6.231664076951421e-05, | |
| "loss": 0.1926, | |
| "num_input_tokens_seen": 31627608, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 0.9010339734121122, | |
| "grad_norm": 1.336878225583922, | |
| "learning_rate": 6.219824054014656e-05, | |
| "loss": 0.2303, | |
| "num_input_tokens_seen": 31679080, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.9010339734121122, | |
| "eval_loss": 0.22528553009033203, | |
| "eval_runtime": 19.2502, | |
| "eval_samples_per_second": 3.117, | |
| "eval_steps_per_second": 0.779, | |
| "num_input_tokens_seen": 31679080, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.9025110782865583, | |
| "grad_norm": 1.1996422945391199, | |
| "learning_rate": 6.207976753619816e-05, | |
| "loss": 0.1854, | |
| "num_input_tokens_seen": 31731232, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 0.9039881831610044, | |
| "grad_norm": 1.142249274568305, | |
| "learning_rate": 6.196122246447779e-05, | |
| "loss": 0.1813, | |
| "num_input_tokens_seen": 31783480, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.9054652880354506, | |
| "grad_norm": 1.8891844898246446, | |
| "learning_rate": 6.184260603222416e-05, | |
| "loss": 0.2099, | |
| "num_input_tokens_seen": 31835864, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 0.9069423929098966, | |
| "grad_norm": 1.1771283819772904, | |
| "learning_rate": 6.17239189471017e-05, | |
| "loss": 0.2158, | |
| "num_input_tokens_seen": 31887120, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.9084194977843427, | |
| "grad_norm": 1.000017408106927, | |
| "learning_rate": 6.160516191719638e-05, | |
| "loss": 0.1947, | |
| "num_input_tokens_seen": 31938768, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.9098966026587888, | |
| "grad_norm": 10.76780458746382, | |
| "learning_rate": 6.148633565101145e-05, | |
| "loss": 0.2058, | |
| "num_input_tokens_seen": 31990800, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.9113737075332349, | |
| "grad_norm": 1.5246138398849078, | |
| "learning_rate": 6.136744085746322e-05, | |
| "loss": 0.2366, | |
| "num_input_tokens_seen": 32042096, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 0.912850812407681, | |
| "grad_norm": 1.3169793573688027, | |
| "learning_rate": 6.124847824587684e-05, | |
| "loss": 0.2749, | |
| "num_input_tokens_seen": 32092864, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.914327917282127, | |
| "grad_norm": 1.0350686863717118, | |
| "learning_rate": 6.112944852598205e-05, | |
| "loss": 0.2242, | |
| "num_input_tokens_seen": 32144288, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 0.9158050221565731, | |
| "grad_norm": 0.8553950294390508, | |
| "learning_rate": 6.1010352407908966e-05, | |
| "loss": 0.1999, | |
| "num_input_tokens_seen": 32196176, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9158050221565731, | |
| "eval_loss": 0.2710443437099457, | |
| "eval_runtime": 19.0309, | |
| "eval_samples_per_second": 3.153, | |
| "eval_steps_per_second": 0.788, | |
| "num_input_tokens_seen": 32196176, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9172821270310192, | |
| "grad_norm": 0.9733516483269293, | |
| "learning_rate": 6.089119060218385e-05, | |
| "loss": 0.2205, | |
| "num_input_tokens_seen": 32247416, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 0.9187592319054653, | |
| "grad_norm": 1.393227303687879, | |
| "learning_rate": 6.077196381972482e-05, | |
| "loss": 0.2161, | |
| "num_input_tokens_seen": 32298088, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.9202363367799113, | |
| "grad_norm": 1.0898822094479876, | |
| "learning_rate": 6.065267277183767e-05, | |
| "loss": 0.1846, | |
| "num_input_tokens_seen": 32349768, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 0.9217134416543574, | |
| "grad_norm": 1.613649982790536, | |
| "learning_rate": 6.0533318170211584e-05, | |
| "loss": 0.2246, | |
| "num_input_tokens_seen": 32401136, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.9231905465288035, | |
| "grad_norm": 1.3536108105978324, | |
| "learning_rate": 6.041390072691495e-05, | |
| "loss": 0.1909, | |
| "num_input_tokens_seen": 32453424, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.9246676514032496, | |
| "grad_norm": 4.434791836263956, | |
| "learning_rate": 6.0294421154391013e-05, | |
| "loss": 0.1651, | |
| "num_input_tokens_seen": 32506104, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.9261447562776958, | |
| "grad_norm": 1.518977363790944, | |
| "learning_rate": 6.0174880165453714e-05, | |
| "loss": 0.2352, | |
| "num_input_tokens_seen": 32557496, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 0.9276218611521418, | |
| "grad_norm": 22.226709781269058, | |
| "learning_rate": 6.005527847328338e-05, | |
| "loss": 0.1875, | |
| "num_input_tokens_seen": 32609696, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.9290989660265879, | |
| "grad_norm": 1.4067637855508932, | |
| "learning_rate": 5.993561679142253e-05, | |
| "loss": 0.1889, | |
| "num_input_tokens_seen": 32661992, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 0.930576070901034, | |
| "grad_norm": 1.2192858374169209, | |
| "learning_rate": 5.981589583377154e-05, | |
| "loss": 0.2069, | |
| "num_input_tokens_seen": 32713824, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.930576070901034, | |
| "eval_loss": 0.20293839275836945, | |
| "eval_runtime": 19.3509, | |
| "eval_samples_per_second": 3.101, | |
| "eval_steps_per_second": 0.775, | |
| "num_input_tokens_seen": 32713824, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.9320531757754801, | |
| "grad_norm": 1.7783073907151754, | |
| "learning_rate": 5.969611631458444e-05, | |
| "loss": 0.2035, | |
| "num_input_tokens_seen": 32765648, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 0.9335302806499262, | |
| "grad_norm": 2.7800459727804068, | |
| "learning_rate": 5.957627894846465e-05, | |
| "loss": 0.1655, | |
| "num_input_tokens_seen": 32818192, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.9350073855243722, | |
| "grad_norm": 0.9191763474328299, | |
| "learning_rate": 5.9456384450360694e-05, | |
| "loss": 0.196, | |
| "num_input_tokens_seen": 32870520, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 0.9364844903988183, | |
| "grad_norm": 4.38220903682666, | |
| "learning_rate": 5.933643353556195e-05, | |
| "loss": 0.1774, | |
| "num_input_tokens_seen": 32922712, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.9379615952732644, | |
| "grad_norm": 6.889422152522515, | |
| "learning_rate": 5.9216426919694356e-05, | |
| "loss": 0.1731, | |
| "num_input_tokens_seen": 32975768, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.9394387001477105, | |
| "grad_norm": 38.21208106263, | |
| "learning_rate": 5.9096365318716194e-05, | |
| "loss": 0.2306, | |
| "num_input_tokens_seen": 33027264, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.9409158050221565, | |
| "grad_norm": 3.8776611584865295, | |
| "learning_rate": 5.897624944891378e-05, | |
| "loss": 0.1972, | |
| "num_input_tokens_seen": 33079712, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 0.9423929098966026, | |
| "grad_norm": 1.1372460555071302, | |
| "learning_rate": 5.8856080026897144e-05, | |
| "loss": 0.1612, | |
| "num_input_tokens_seen": 33132048, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.9438700147710487, | |
| "grad_norm": 1.366569822997117, | |
| "learning_rate": 5.8735857769595905e-05, | |
| "loss": 0.2148, | |
| "num_input_tokens_seen": 33184488, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 0.9453471196454948, | |
| "grad_norm": 1.2035899680395865, | |
| "learning_rate": 5.8615583394254814e-05, | |
| "loss": 0.2135, | |
| "num_input_tokens_seen": 33235872, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9453471196454948, | |
| "eval_loss": 0.3564297556877136, | |
| "eval_runtime": 19.2969, | |
| "eval_samples_per_second": 3.109, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 33235872, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.946824224519941, | |
| "grad_norm": 1.3270189069274072, | |
| "learning_rate": 5.849525761842961e-05, | |
| "loss": 0.2059, | |
| "num_input_tokens_seen": 33287792, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 0.948301329394387, | |
| "grad_norm": 1.5700498259079116, | |
| "learning_rate": 5.837488115998264e-05, | |
| "loss": 0.1482, | |
| "num_input_tokens_seen": 33340168, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.9497784342688331, | |
| "grad_norm": 1.3963642572652624, | |
| "learning_rate": 5.825445473707867e-05, | |
| "loss": 0.2017, | |
| "num_input_tokens_seen": 33391904, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 0.9512555391432792, | |
| "grad_norm": 1.2363860850370896, | |
| "learning_rate": 5.813397906818051e-05, | |
| "loss": 0.206, | |
| "num_input_tokens_seen": 33443080, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.9527326440177253, | |
| "grad_norm": 1.4364140192060484, | |
| "learning_rate": 5.801345487204482e-05, | |
| "loss": 0.1868, | |
| "num_input_tokens_seen": 33495320, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.9542097488921714, | |
| "grad_norm": 1.2413385170484263, | |
| "learning_rate": 5.78928828677177e-05, | |
| "loss": 0.2033, | |
| "num_input_tokens_seen": 33546688, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.9556868537666174, | |
| "grad_norm": 1.2267190013200722, | |
| "learning_rate": 5.777226377453057e-05, | |
| "loss": 0.2008, | |
| "num_input_tokens_seen": 33597928, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 0.9571639586410635, | |
| "grad_norm": 1.2199044517627364, | |
| "learning_rate": 5.76515983120957e-05, | |
| "loss": 0.2121, | |
| "num_input_tokens_seen": 33649752, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.9586410635155096, | |
| "grad_norm": 1.134606964963097, | |
| "learning_rate": 5.7530887200302055e-05, | |
| "loss": 0.2204, | |
| "num_input_tokens_seen": 33700792, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 0.9601181683899557, | |
| "grad_norm": 0.8601990098934698, | |
| "learning_rate": 5.741013115931088e-05, | |
| "loss": 0.1964, | |
| "num_input_tokens_seen": 33752488, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9601181683899557, | |
| "eval_loss": 0.308076411485672, | |
| "eval_runtime": 19.4071, | |
| "eval_samples_per_second": 3.092, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 33752488, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9615952732644018, | |
| "grad_norm": 1.0061109126775716, | |
| "learning_rate": 5.728933090955151e-05, | |
| "loss": 0.227, | |
| "num_input_tokens_seen": 33803968, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 0.9630723781388478, | |
| "grad_norm": 7.1108905990118645, | |
| "learning_rate": 5.7168487171717056e-05, | |
| "loss": 0.2117, | |
| "num_input_tokens_seen": 33856104, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.9645494830132939, | |
| "grad_norm": 11.468727046658728, | |
| "learning_rate": 5.704760066676003e-05, | |
| "loss": 0.196, | |
| "num_input_tokens_seen": 33907912, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 0.96602658788774, | |
| "grad_norm": 1.7059623021479096, | |
| "learning_rate": 5.69266721158881e-05, | |
| "loss": 0.1984, | |
| "num_input_tokens_seen": 33960104, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.9675036927621861, | |
| "grad_norm": 1.099758304724886, | |
| "learning_rate": 5.6805702240559786e-05, | |
| "loss": 0.182, | |
| "num_input_tokens_seen": 34012120, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.9689807976366323, | |
| "grad_norm": 1.1569544282160544, | |
| "learning_rate": 5.668469176248017e-05, | |
| "loss": 0.2219, | |
| "num_input_tokens_seen": 34063520, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.9704579025110783, | |
| "grad_norm": 5.82612333029224, | |
| "learning_rate": 5.6563641403596536e-05, | |
| "loss": 0.2421, | |
| "num_input_tokens_seen": 34115800, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 0.9719350073855244, | |
| "grad_norm": 1.3328615698520316, | |
| "learning_rate": 5.644255188609411e-05, | |
| "loss": 0.1888, | |
| "num_input_tokens_seen": 34168208, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.9734121122599705, | |
| "grad_norm": 1.458848145104471, | |
| "learning_rate": 5.632142393239174e-05, | |
| "loss": 0.2366, | |
| "num_input_tokens_seen": 34218456, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 0.9748892171344166, | |
| "grad_norm": 1.6219152592756263, | |
| "learning_rate": 5.6200258265137585e-05, | |
| "loss": 0.2131, | |
| "num_input_tokens_seen": 34269496, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9748892171344166, | |
| "eval_loss": 0.3541204631328583, | |
| "eval_runtime": 19.2633, | |
| "eval_samples_per_second": 3.115, | |
| "eval_steps_per_second": 0.779, | |
| "num_input_tokens_seen": 34269496, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9763663220088626, | |
| "grad_norm": 0.7198899395850713, | |
| "learning_rate": 5.607905560720481e-05, | |
| "loss": 0.1993, | |
| "num_input_tokens_seen": 34321480, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 0.9778434268833087, | |
| "grad_norm": 1.1646925735801659, | |
| "learning_rate": 5.595781668168725e-05, | |
| "loss": 0.1965, | |
| "num_input_tokens_seen": 34372752, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.9793205317577548, | |
| "grad_norm": 1.5473226512651947, | |
| "learning_rate": 5.5836542211895105e-05, | |
| "loss": 0.2429, | |
| "num_input_tokens_seen": 34424768, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 0.9807976366322009, | |
| "grad_norm": 1.6745702087485874, | |
| "learning_rate": 5.571523292135067e-05, | |
| "loss": 0.2214, | |
| "num_input_tokens_seen": 34475248, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.982274741506647, | |
| "grad_norm": 1.7074791320051903, | |
| "learning_rate": 5.559388953378393e-05, | |
| "loss": 0.1624, | |
| "num_input_tokens_seen": 34528200, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.983751846381093, | |
| "grad_norm": 1.3494994119412924, | |
| "learning_rate": 5.547251277312833e-05, | |
| "loss": 0.2222, | |
| "num_input_tokens_seen": 34579080, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.9852289512555391, | |
| "grad_norm": 1.399722512313767, | |
| "learning_rate": 5.535110336351642e-05, | |
| "loss": 0.1895, | |
| "num_input_tokens_seen": 34630680, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 0.9867060561299852, | |
| "grad_norm": 1.6811876091944713, | |
| "learning_rate": 5.5229662029275505e-05, | |
| "loss": 0.2164, | |
| "num_input_tokens_seen": 34682208, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.9881831610044313, | |
| "grad_norm": 1.3810047796468525, | |
| "learning_rate": 5.510818949492337e-05, | |
| "loss": 0.223, | |
| "num_input_tokens_seen": 34732696, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 0.9896602658788775, | |
| "grad_norm": 1.6151906286753892, | |
| "learning_rate": 5.498668648516394e-05, | |
| "loss": 0.1779, | |
| "num_input_tokens_seen": 34784784, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9896602658788775, | |
| "eval_loss": 0.22550027072429657, | |
| "eval_runtime": 19.403, | |
| "eval_samples_per_second": 3.092, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 34784784, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9911373707533235, | |
| "grad_norm": 1.6778824792393197, | |
| "learning_rate": 5.4865153724882945e-05, | |
| "loss": 0.2145, | |
| "num_input_tokens_seen": 34836528, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 0.9926144756277696, | |
| "grad_norm": 1.177435164237277, | |
| "learning_rate": 5.4743591939143624e-05, | |
| "loss": 0.1839, | |
| "num_input_tokens_seen": 34888888, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.9940915805022157, | |
| "grad_norm": 0.9272308554713589, | |
| "learning_rate": 5.462200185318236e-05, | |
| "loss": 0.1665, | |
| "num_input_tokens_seen": 34941112, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 0.9955686853766618, | |
| "grad_norm": 1.3886029969999028, | |
| "learning_rate": 5.4500384192404395e-05, | |
| "loss": 0.1908, | |
| "num_input_tokens_seen": 34992976, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.9970457902511078, | |
| "grad_norm": 0.7182575806960926, | |
| "learning_rate": 5.4378739682379475e-05, | |
| "loss": 0.1577, | |
| "num_input_tokens_seen": 35045680, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.9985228951255539, | |
| "grad_norm": 1.3292843771600575, | |
| "learning_rate": 5.425706904883753e-05, | |
| "loss": 0.2097, | |
| "num_input_tokens_seen": 35097928, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.7761867380933323, | |
| "learning_rate": 5.4135373017664326e-05, | |
| "loss": 0.1933, | |
| "num_input_tokens_seen": 35150544, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 1.0014771048744462, | |
| "grad_norm": 1.2787364659066394, | |
| "learning_rate": 5.401365231489718e-05, | |
| "loss": 0.1708, | |
| "num_input_tokens_seen": 35203152, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.0029542097488922, | |
| "grad_norm": 1.1654168781378111, | |
| "learning_rate": 5.389190766672056e-05, | |
| "loss": 0.1766, | |
| "num_input_tokens_seen": 35254992, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 1.0044313146233383, | |
| "grad_norm": 1.3171125278735354, | |
| "learning_rate": 5.3770139799461824e-05, | |
| "loss": 0.2173, | |
| "num_input_tokens_seen": 35305984, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0044313146233383, | |
| "eval_loss": 0.40779221057891846, | |
| "eval_runtime": 19.1316, | |
| "eval_samples_per_second": 3.136, | |
| "eval_steps_per_second": 0.784, | |
| "num_input_tokens_seen": 35305984, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0047267355982274, | |
| "num_input_tokens_seen": 35316128, | |
| "step": 3401, | |
| "total_flos": 2329910849044480.0, | |
| "train_loss": 0.0003882907692455818, | |
| "train_runtime": 103.5396, | |
| "train_samples_per_second": 788.104, | |
| "train_steps_per_second": 32.838 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3400, | |
| "num_input_tokens_seen": 35316128, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2329910849044480.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |