| { | |
| "best_metric": 0.007714101579040289, | |
| "best_model_checkpoint": "./all-observation-type/checkpoint-2500", | |
| "epoch": 40.0, | |
| "eval_steps": 100, | |
| "global_step": 3440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 0.09591829776763916, | |
| "learning_rate": 0.0001994186046511628, | |
| "loss": 0.6339, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 0.09048111736774445, | |
| "learning_rate": 0.0001988372093023256, | |
| "loss": 0.5034, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 0.08638294041156769, | |
| "learning_rate": 0.00019825581395348837, | |
| "loss": 0.3894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 0.07995904237031937, | |
| "learning_rate": 0.00019767441860465116, | |
| "loss": 0.2951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 0.07135872542858124, | |
| "learning_rate": 0.00019709302325581396, | |
| "loss": 0.223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 0.0624060332775116, | |
| "learning_rate": 0.00019651162790697676, | |
| "loss": 0.1703, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 0.05441118776798248, | |
| "learning_rate": 0.00019593023255813952, | |
| "loss": 0.133, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.04721858724951744, | |
| "learning_rate": 0.00019534883720930232, | |
| "loss": 0.1057, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 0.041243478655815125, | |
| "learning_rate": 0.00019476744186046511, | |
| "loss": 0.0866, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "grad_norm": 0.036053091287612915, | |
| "learning_rate": 0.0001941860465116279, | |
| "loss": 0.0726, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.06596538424491882, | |
| "eval_runtime": 1.8015, | |
| "eval_samples_per_second": 40.522, | |
| "eval_steps_per_second": 5.551, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2790697674418605, | |
| "grad_norm": 0.03166024759411812, | |
| "learning_rate": 0.0001936046511627907, | |
| "loss": 0.0617, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 0.0280374176800251, | |
| "learning_rate": 0.0001930232558139535, | |
| "loss": 0.0537, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "grad_norm": 0.025035331025719643, | |
| "learning_rate": 0.0001924418604651163, | |
| "loss": 0.0469, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 0.02311284840106964, | |
| "learning_rate": 0.0001918604651162791, | |
| "loss": 0.042, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "grad_norm": 0.020456839352846146, | |
| "learning_rate": 0.0001912790697674419, | |
| "loss": 0.0383, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 0.01917686127126217, | |
| "learning_rate": 0.00019069767441860466, | |
| "loss": 0.034, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9767441860465116, | |
| "grad_norm": 0.017376938834786415, | |
| "learning_rate": 0.00019011627906976745, | |
| "loss": 0.0314, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 0.01589462347328663, | |
| "learning_rate": 0.00018953488372093025, | |
| "loss": 0.0292, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.2093023255813953, | |
| "grad_norm": 0.014865094795823097, | |
| "learning_rate": 0.00018895348837209304, | |
| "loss": 0.0274, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "grad_norm": 0.013694318942725658, | |
| "learning_rate": 0.00018837209302325584, | |
| "loss": 0.0264, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.02468988113105297, | |
| "eval_runtime": 1.6978, | |
| "eval_samples_per_second": 42.996, | |
| "eval_steps_per_second": 5.89, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.441860465116279, | |
| "grad_norm": 0.012708564288914204, | |
| "learning_rate": 0.0001877906976744186, | |
| "loss": 0.0244, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.558139534883721, | |
| "grad_norm": 0.011777268722653389, | |
| "learning_rate": 0.0001872093023255814, | |
| "loss": 0.023, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.6744186046511627, | |
| "grad_norm": 0.011043795384466648, | |
| "learning_rate": 0.0001866279069767442, | |
| "loss": 0.0212, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.7906976744186047, | |
| "grad_norm": 0.010540899820625782, | |
| "learning_rate": 0.000186046511627907, | |
| "loss": 0.0206, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.9069767441860463, | |
| "grad_norm": 0.0098367715254426, | |
| "learning_rate": 0.00018546511627906976, | |
| "loss": 0.0192, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0232558139534884, | |
| "grad_norm": 0.009457371197640896, | |
| "learning_rate": 0.00018488372093023256, | |
| "loss": 0.0186, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.13953488372093, | |
| "grad_norm": 0.0089762257412076, | |
| "learning_rate": 0.00018430232558139535, | |
| "loss": 0.0182, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.255813953488372, | |
| "grad_norm": 0.00830694381147623, | |
| "learning_rate": 0.00018372093023255815, | |
| "loss": 0.0177, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.3720930232558137, | |
| "grad_norm": 0.008157115429639816, | |
| "learning_rate": 0.00018313953488372094, | |
| "loss": 0.0171, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.488372093023256, | |
| "grad_norm": 0.007526726461946964, | |
| "learning_rate": 0.0001825581395348837, | |
| "loss": 0.0161, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.488372093023256, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.016456665471196175, | |
| "eval_runtime": 1.81, | |
| "eval_samples_per_second": 40.33, | |
| "eval_steps_per_second": 5.525, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.604651162790698, | |
| "grad_norm": 0.006970840971916914, | |
| "learning_rate": 0.0001819767441860465, | |
| "loss": 0.0171, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.7209302325581395, | |
| "grad_norm": 0.006966202985495329, | |
| "learning_rate": 0.0001813953488372093, | |
| "loss": 0.0157, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.8372093023255816, | |
| "grad_norm": 0.006569746416062117, | |
| "learning_rate": 0.00018081395348837212, | |
| "loss": 0.0155, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.953488372093023, | |
| "grad_norm": 0.006560744717717171, | |
| "learning_rate": 0.0001802325581395349, | |
| "loss": 0.0154, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.069767441860465, | |
| "grad_norm": 0.006836111657321453, | |
| "learning_rate": 0.0001796511627906977, | |
| "loss": 0.0144, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.186046511627907, | |
| "grad_norm": 0.005944866221398115, | |
| "learning_rate": 0.00017906976744186048, | |
| "loss": 0.0144, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.3023255813953485, | |
| "grad_norm": 0.00594041682779789, | |
| "learning_rate": 0.00017848837209302328, | |
| "loss": 0.0142, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.4186046511627906, | |
| "grad_norm": 0.005508134141564369, | |
| "learning_rate": 0.00017790697674418605, | |
| "loss": 0.0136, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.534883720930233, | |
| "grad_norm": 0.005419102031737566, | |
| "learning_rate": 0.00017732558139534884, | |
| "loss": 0.0135, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.651162790697675, | |
| "grad_norm": 0.005490223411470652, | |
| "learning_rate": 0.00017674418604651164, | |
| "loss": 0.0133, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.651162790697675, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.013475539162755013, | |
| "eval_runtime": 1.7409, | |
| "eval_samples_per_second": 41.933, | |
| "eval_steps_per_second": 5.744, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.767441860465116, | |
| "grad_norm": 0.005142460577189922, | |
| "learning_rate": 0.00017616279069767443, | |
| "loss": 0.0132, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.883720930232558, | |
| "grad_norm": 0.00514647364616394, | |
| "learning_rate": 0.00017558139534883723, | |
| "loss": 0.0137, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.005101104732602835, | |
| "learning_rate": 0.000175, | |
| "loss": 0.0135, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.116279069767442, | |
| "grad_norm": 0.005293596535921097, | |
| "learning_rate": 0.0001744186046511628, | |
| "loss": 0.0122, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.232558139534884, | |
| "grad_norm": 0.004600506741553545, | |
| "learning_rate": 0.0001738372093023256, | |
| "loss": 0.0123, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.348837209302325, | |
| "grad_norm": 0.005292165093123913, | |
| "learning_rate": 0.00017325581395348838, | |
| "loss": 0.0125, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.465116279069767, | |
| "grad_norm": 0.004837548825889826, | |
| "learning_rate": 0.00017267441860465118, | |
| "loss": 0.012, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.5813953488372094, | |
| "grad_norm": 0.004367106128484011, | |
| "learning_rate": 0.00017209302325581395, | |
| "loss": 0.0127, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.6976744186046515, | |
| "grad_norm": 0.004551732446998358, | |
| "learning_rate": 0.00017151162790697674, | |
| "loss": 0.0123, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.813953488372093, | |
| "grad_norm": 0.004141143057495356, | |
| "learning_rate": 0.00017093023255813954, | |
| "loss": 0.0124, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.813953488372093, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.012049774639308453, | |
| "eval_runtime": 1.8113, | |
| "eval_samples_per_second": 40.303, | |
| "eval_steps_per_second": 5.521, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.930232558139535, | |
| "grad_norm": 0.0041281660087406635, | |
| "learning_rate": 0.00017034883720930233, | |
| "loss": 0.0123, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.046511627906977, | |
| "grad_norm": 0.004327772185206413, | |
| "learning_rate": 0.0001697674418604651, | |
| "loss": 0.0114, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.162790697674419, | |
| "grad_norm": 0.00425134040415287, | |
| "learning_rate": 0.0001691860465116279, | |
| "loss": 0.0108, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.27906976744186, | |
| "grad_norm": 0.004197305999696255, | |
| "learning_rate": 0.00016860465116279072, | |
| "loss": 0.0119, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.395348837209302, | |
| "grad_norm": 0.004064254928380251, | |
| "learning_rate": 0.00016802325581395352, | |
| "loss": 0.0117, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.511627906976744, | |
| "grad_norm": 0.004467037972062826, | |
| "learning_rate": 0.00016744186046511629, | |
| "loss": 0.012, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.627906976744186, | |
| "grad_norm": 0.004210630431771278, | |
| "learning_rate": 0.00016686046511627908, | |
| "loss": 0.0116, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.7441860465116275, | |
| "grad_norm": 0.003937269560992718, | |
| "learning_rate": 0.00016627906976744188, | |
| "loss": 0.0116, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.8604651162790695, | |
| "grad_norm": 0.003829133929684758, | |
| "learning_rate": 0.00016569767441860467, | |
| "loss": 0.0114, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.976744186046512, | |
| "grad_norm": 0.0037258623633533716, | |
| "learning_rate": 0.00016511627906976747, | |
| "loss": 0.011, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.976744186046512, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.011244768276810646, | |
| "eval_runtime": 1.6726, | |
| "eval_samples_per_second": 43.646, | |
| "eval_steps_per_second": 5.979, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.093023255813954, | |
| "grad_norm": 0.0038892878219485283, | |
| "learning_rate": 0.00016453488372093024, | |
| "loss": 0.0108, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.209302325581396, | |
| "grad_norm": 0.003730091731995344, | |
| "learning_rate": 0.00016395348837209303, | |
| "loss": 0.0108, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.325581395348837, | |
| "grad_norm": 0.0035813930444419384, | |
| "learning_rate": 0.00016337209302325583, | |
| "loss": 0.0113, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.441860465116279, | |
| "grad_norm": 0.004092409275472164, | |
| "learning_rate": 0.00016279069767441862, | |
| "loss": 0.0105, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.558139534883721, | |
| "grad_norm": 0.004152482841163874, | |
| "learning_rate": 0.0001622093023255814, | |
| "loss": 0.0107, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.674418604651163, | |
| "grad_norm": 0.0035718800500035286, | |
| "learning_rate": 0.00016162790697674419, | |
| "loss": 0.0106, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.790697674418604, | |
| "grad_norm": 0.004181632772088051, | |
| "learning_rate": 0.00016104651162790698, | |
| "loss": 0.0112, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.906976744186046, | |
| "grad_norm": 0.003530286019667983, | |
| "learning_rate": 0.00016046511627906978, | |
| "loss": 0.0112, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.023255813953488, | |
| "grad_norm": 0.003953536041080952, | |
| "learning_rate": 0.00015988372093023257, | |
| "loss": 0.0107, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.13953488372093, | |
| "grad_norm": 0.00364445592276752, | |
| "learning_rate": 0.00015930232558139534, | |
| "loss": 0.0114, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.13953488372093, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.010723751038312912, | |
| "eval_runtime": 1.705, | |
| "eval_samples_per_second": 42.815, | |
| "eval_steps_per_second": 5.865, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.255813953488373, | |
| "grad_norm": 0.004072926007211208, | |
| "learning_rate": 0.00015872093023255814, | |
| "loss": 0.0105, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.372093023255815, | |
| "grad_norm": 0.003972381353378296, | |
| "learning_rate": 0.00015813953488372093, | |
| "loss": 0.0103, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.488372093023255, | |
| "grad_norm": 0.003728296374902129, | |
| "learning_rate": 0.00015755813953488373, | |
| "loss": 0.0107, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.604651162790697, | |
| "grad_norm": 0.0036759586073458195, | |
| "learning_rate": 0.00015697674418604652, | |
| "loss": 0.01, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.720930232558139, | |
| "grad_norm": 0.0035114786587655544, | |
| "learning_rate": 0.0001563953488372093, | |
| "loss": 0.0105, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.837209302325581, | |
| "grad_norm": 0.0033980573061853647, | |
| "learning_rate": 0.0001558139534883721, | |
| "loss": 0.0102, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.953488372093023, | |
| "grad_norm": 0.0035892720334231853, | |
| "learning_rate": 0.0001552325581395349, | |
| "loss": 0.0099, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.069767441860465, | |
| "grad_norm": 0.0031818547286093235, | |
| "learning_rate": 0.00015465116279069768, | |
| "loss": 0.0098, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.186046511627907, | |
| "grad_norm": 0.003511944320052862, | |
| "learning_rate": 0.00015406976744186047, | |
| "loss": 0.0101, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 9.30232558139535, | |
| "grad_norm": 0.0032857146579772234, | |
| "learning_rate": 0.00015348837209302327, | |
| "loss": 0.0109, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.30232558139535, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.010318118147552013, | |
| "eval_runtime": 1.6682, | |
| "eval_samples_per_second": 43.76, | |
| "eval_steps_per_second": 5.995, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.418604651162791, | |
| "grad_norm": 0.004180931951850653, | |
| "learning_rate": 0.00015290697674418606, | |
| "loss": 0.0104, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.534883720930232, | |
| "grad_norm": 0.0035553001798689365, | |
| "learning_rate": 0.00015232558139534886, | |
| "loss": 0.0107, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.651162790697674, | |
| "grad_norm": 0.004481980111449957, | |
| "learning_rate": 0.00015174418604651163, | |
| "loss": 0.0098, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.767441860465116, | |
| "grad_norm": 0.004224750213325024, | |
| "learning_rate": 0.00015116279069767442, | |
| "loss": 0.0102, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.883720930232558, | |
| "grad_norm": 0.0038431661669164896, | |
| "learning_rate": 0.00015058139534883722, | |
| "loss": 0.0095, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.004212440922856331, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0099, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.116279069767442, | |
| "grad_norm": 0.003633901011198759, | |
| "learning_rate": 0.0001494186046511628, | |
| "loss": 0.0095, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 10.232558139534884, | |
| "grad_norm": 0.003657746594399214, | |
| "learning_rate": 0.00014883720930232558, | |
| "loss": 0.0096, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 10.348837209302326, | |
| "grad_norm": 0.003825038904324174, | |
| "learning_rate": 0.00014825581395348837, | |
| "loss": 0.0102, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 10.465116279069768, | |
| "grad_norm": 0.0041350796818733215, | |
| "learning_rate": 0.00014767441860465117, | |
| "loss": 0.0096, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.465116279069768, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.010230067186057568, | |
| "eval_runtime": 1.6982, | |
| "eval_samples_per_second": 42.987, | |
| "eval_steps_per_second": 5.889, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.581395348837209, | |
| "grad_norm": 0.003846728475764394, | |
| "learning_rate": 0.00014709302325581396, | |
| "loss": 0.0106, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.69767441860465, | |
| "grad_norm": 0.0042284755036234856, | |
| "learning_rate": 0.00014651162790697673, | |
| "loss": 0.0102, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 10.813953488372093, | |
| "grad_norm": 0.003174531040713191, | |
| "learning_rate": 0.00014593023255813953, | |
| "loss": 0.009, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.930232558139535, | |
| "grad_norm": 0.0035903833340853453, | |
| "learning_rate": 0.00014534883720930232, | |
| "loss": 0.0101, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 11.046511627906977, | |
| "grad_norm": 0.0043946849182248116, | |
| "learning_rate": 0.00014476744186046512, | |
| "loss": 0.0093, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.162790697674419, | |
| "grad_norm": 0.0035909838043153286, | |
| "learning_rate": 0.00014418604651162791, | |
| "loss": 0.0093, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 11.279069767441861, | |
| "grad_norm": 0.0036394952330738306, | |
| "learning_rate": 0.0001436046511627907, | |
| "loss": 0.0092, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 11.395348837209303, | |
| "grad_norm": 0.0038749193772673607, | |
| "learning_rate": 0.0001430232558139535, | |
| "loss": 0.009, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 11.511627906976745, | |
| "grad_norm": 0.0044557624496519566, | |
| "learning_rate": 0.0001424418604651163, | |
| "loss": 0.0097, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.627906976744185, | |
| "grad_norm": 0.0037609776481986046, | |
| "learning_rate": 0.0001418604651162791, | |
| "loss": 0.0099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.627906976744185, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.00977805070579052, | |
| "eval_runtime": 1.7092, | |
| "eval_samples_per_second": 42.71, | |
| "eval_steps_per_second": 5.851, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.744186046511627, | |
| "grad_norm": 0.003938957117497921, | |
| "learning_rate": 0.00014127906976744186, | |
| "loss": 0.0093, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 11.86046511627907, | |
| "grad_norm": 0.006434954237192869, | |
| "learning_rate": 0.00014069767441860466, | |
| "loss": 0.0095, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 11.976744186046512, | |
| "grad_norm": 0.007113784551620483, | |
| "learning_rate": 0.00014011627906976746, | |
| "loss": 0.0105, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 12.093023255813954, | |
| "grad_norm": 0.0040367101319134235, | |
| "learning_rate": 0.00013953488372093025, | |
| "loss": 0.0093, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 12.209302325581396, | |
| "grad_norm": 0.0035031838342547417, | |
| "learning_rate": 0.00013895348837209302, | |
| "loss": 0.0096, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.325581395348838, | |
| "grad_norm": 0.0033588423393666744, | |
| "learning_rate": 0.00013837209302325582, | |
| "loss": 0.0091, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 12.44186046511628, | |
| "grad_norm": 0.0037452862598001957, | |
| "learning_rate": 0.0001377906976744186, | |
| "loss": 0.0092, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 12.55813953488372, | |
| "grad_norm": 0.004363079089671373, | |
| "learning_rate": 0.0001372093023255814, | |
| "loss": 0.0082, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.674418604651162, | |
| "grad_norm": 0.006496877875179052, | |
| "learning_rate": 0.0001366279069767442, | |
| "loss": 0.0092, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 12.790697674418604, | |
| "grad_norm": 0.00442136637866497, | |
| "learning_rate": 0.00013604651162790697, | |
| "loss": 0.0089, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.790697674418604, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.009442531503736973, | |
| "eval_runtime": 1.7071, | |
| "eval_samples_per_second": 42.762, | |
| "eval_steps_per_second": 5.858, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.906976744186046, | |
| "grad_norm": 0.004154372029006481, | |
| "learning_rate": 0.00013546511627906977, | |
| "loss": 0.0097, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 13.023255813953488, | |
| "grad_norm": 0.004947633482515812, | |
| "learning_rate": 0.00013488372093023256, | |
| "loss": 0.0094, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 13.13953488372093, | |
| "grad_norm": 0.004092765972018242, | |
| "learning_rate": 0.00013430232558139536, | |
| "loss": 0.0087, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 13.255813953488373, | |
| "grad_norm": 0.003843548009172082, | |
| "learning_rate": 0.00013372093023255815, | |
| "loss": 0.0084, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 13.372093023255815, | |
| "grad_norm": 0.0034843245521187782, | |
| "learning_rate": 0.00013313953488372092, | |
| "loss": 0.0084, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 13.488372093023255, | |
| "grad_norm": 0.0045846025459468365, | |
| "learning_rate": 0.00013255813953488372, | |
| "loss": 0.0094, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 13.604651162790697, | |
| "grad_norm": 0.0040568090043962, | |
| "learning_rate": 0.0001319767441860465, | |
| "loss": 0.0092, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.720930232558139, | |
| "grad_norm": 0.0035901013761758804, | |
| "learning_rate": 0.0001313953488372093, | |
| "loss": 0.0086, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 13.837209302325581, | |
| "grad_norm": 0.003683890914544463, | |
| "learning_rate": 0.0001308139534883721, | |
| "loss": 0.0092, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 13.953488372093023, | |
| "grad_norm": 0.003873488400131464, | |
| "learning_rate": 0.0001302325581395349, | |
| "loss": 0.0091, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.953488372093023, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.009279163554310799, | |
| "eval_runtime": 1.6753, | |
| "eval_samples_per_second": 43.574, | |
| "eval_steps_per_second": 5.969, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.069767441860465, | |
| "grad_norm": 0.0047092861495912075, | |
| "learning_rate": 0.0001296511627906977, | |
| "loss": 0.0078, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 14.186046511627907, | |
| "grad_norm": 0.005257419776171446, | |
| "learning_rate": 0.0001290697674418605, | |
| "loss": 0.0083, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 14.30232558139535, | |
| "grad_norm": 0.005552452523261309, | |
| "learning_rate": 0.00012848837209302326, | |
| "loss": 0.0087, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 14.418604651162791, | |
| "grad_norm": 0.0051083252765238285, | |
| "learning_rate": 0.00012790697674418605, | |
| "loss": 0.0092, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 14.534883720930232, | |
| "grad_norm": 0.0037808313500136137, | |
| "learning_rate": 0.00012732558139534885, | |
| "loss": 0.0082, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 14.651162790697674, | |
| "grad_norm": 0.004120196681469679, | |
| "learning_rate": 0.00012674418604651164, | |
| "loss": 0.0082, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.767441860465116, | |
| "grad_norm": 0.004169652238488197, | |
| "learning_rate": 0.00012616279069767444, | |
| "loss": 0.0085, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 14.883720930232558, | |
| "grad_norm": 0.004740726202726364, | |
| "learning_rate": 0.0001255813953488372, | |
| "loss": 0.0082, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 0.00697332015261054, | |
| "learning_rate": 0.000125, | |
| "loss": 0.0087, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 15.116279069767442, | |
| "grad_norm": 0.004342319909483194, | |
| "learning_rate": 0.0001244186046511628, | |
| "loss": 0.0081, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 15.116279069767442, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.008884104900062084, | |
| "eval_runtime": 1.7593, | |
| "eval_samples_per_second": 41.494, | |
| "eval_steps_per_second": 5.684, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 15.232558139534884, | |
| "grad_norm": 0.00661982037127018, | |
| "learning_rate": 0.0001238372093023256, | |
| "loss": 0.008, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 15.348837209302326, | |
| "grad_norm": 0.004550145473331213, | |
| "learning_rate": 0.00012325581395348836, | |
| "loss": 0.0082, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 15.465116279069768, | |
| "grad_norm": 0.00338382157497108, | |
| "learning_rate": 0.00012267441860465116, | |
| "loss": 0.0084, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 15.581395348837209, | |
| "grad_norm": 0.005567767191678286, | |
| "learning_rate": 0.00012209302325581395, | |
| "loss": 0.008, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 15.69767441860465, | |
| "grad_norm": 0.0051926677115261555, | |
| "learning_rate": 0.00012151162790697675, | |
| "loss": 0.0071, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.813953488372093, | |
| "grad_norm": 0.004935986362397671, | |
| "learning_rate": 0.00012093023255813953, | |
| "loss": 0.0085, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 15.930232558139535, | |
| "grad_norm": 0.0048750354908406734, | |
| "learning_rate": 0.00012034883720930233, | |
| "loss": 0.0078, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 16.046511627906977, | |
| "grad_norm": 0.0055388594046235085, | |
| "learning_rate": 0.00011976744186046511, | |
| "loss": 0.0082, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 16.162790697674417, | |
| "grad_norm": 0.004739618394523859, | |
| "learning_rate": 0.0001191860465116279, | |
| "loss": 0.0077, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 16.27906976744186, | |
| "grad_norm": 0.004103164654225111, | |
| "learning_rate": 0.00011860465116279071, | |
| "loss": 0.0073, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 16.27906976744186, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.008862593211233616, | |
| "eval_runtime": 1.7176, | |
| "eval_samples_per_second": 42.5, | |
| "eval_steps_per_second": 5.822, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 16.3953488372093, | |
| "grad_norm": 0.0057744914665818214, | |
| "learning_rate": 0.00011802325581395351, | |
| "loss": 0.0078, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 16.511627906976745, | |
| "grad_norm": 0.003924832213670015, | |
| "learning_rate": 0.00011744186046511629, | |
| "loss": 0.0076, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 16.627906976744185, | |
| "grad_norm": 0.004951529670506716, | |
| "learning_rate": 0.00011686046511627909, | |
| "loss": 0.0077, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 16.74418604651163, | |
| "grad_norm": 0.004139590077102184, | |
| "learning_rate": 0.00011627906976744187, | |
| "loss": 0.0073, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.86046511627907, | |
| "grad_norm": 0.004691829439252615, | |
| "learning_rate": 0.00011569767441860466, | |
| "loss": 0.0078, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.97674418604651, | |
| "grad_norm": 0.011304708197712898, | |
| "learning_rate": 0.00011511627906976746, | |
| "loss": 0.0073, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 17.093023255813954, | |
| "grad_norm": 0.004497618414461613, | |
| "learning_rate": 0.00011453488372093024, | |
| "loss": 0.0075, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 17.209302325581394, | |
| "grad_norm": 0.004640204831957817, | |
| "learning_rate": 0.00011395348837209304, | |
| "loss": 0.0067, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 17.325581395348838, | |
| "grad_norm": 0.008850700221955776, | |
| "learning_rate": 0.00011337209302325582, | |
| "loss": 0.0074, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 17.441860465116278, | |
| "grad_norm": 0.0063476236537098885, | |
| "learning_rate": 0.00011279069767441861, | |
| "loss": 0.0071, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 17.441860465116278, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.008479787036776543, | |
| "eval_runtime": 1.7053, | |
| "eval_samples_per_second": 42.808, | |
| "eval_steps_per_second": 5.864, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 17.558139534883722, | |
| "grad_norm": 0.005328552797436714, | |
| "learning_rate": 0.0001122093023255814, | |
| "loss": 0.0071, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 17.674418604651162, | |
| "grad_norm": 0.006423116661608219, | |
| "learning_rate": 0.00011162790697674419, | |
| "loss": 0.0075, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 17.790697674418606, | |
| "grad_norm": 0.006245277356356382, | |
| "learning_rate": 0.00011104651162790699, | |
| "loss": 0.0074, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.906976744186046, | |
| "grad_norm": 0.006818824913352728, | |
| "learning_rate": 0.00011046511627906977, | |
| "loss": 0.0065, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 18.023255813953487, | |
| "grad_norm": 0.005169364158064127, | |
| "learning_rate": 0.00010988372093023256, | |
| "loss": 0.0076, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 18.13953488372093, | |
| "grad_norm": 0.0035659593995660543, | |
| "learning_rate": 0.00010930232558139534, | |
| "loss": 0.0067, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 18.25581395348837, | |
| "grad_norm": 0.004306168295443058, | |
| "learning_rate": 0.00010872093023255814, | |
| "loss": 0.0066, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 18.372093023255815, | |
| "grad_norm": 0.004275166429579258, | |
| "learning_rate": 0.00010813953488372092, | |
| "loss": 0.0064, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 18.488372093023255, | |
| "grad_norm": 0.003919180482625961, | |
| "learning_rate": 0.00010755813953488372, | |
| "loss": 0.0071, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 18.6046511627907, | |
| "grad_norm": 0.008834786713123322, | |
| "learning_rate": 0.00010697674418604651, | |
| "loss": 0.0068, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.6046511627907, | |
| "eval_f1": 0.0182648401826484, | |
| "eval_loss": 0.008239569142460823, | |
| "eval_runtime": 1.7236, | |
| "eval_samples_per_second": 42.353, | |
| "eval_steps_per_second": 5.802, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.72093023255814, | |
| "grad_norm": 0.004857208579778671, | |
| "learning_rate": 0.0001063953488372093, | |
| "loss": 0.0062, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 18.837209302325583, | |
| "grad_norm": 0.005715236067771912, | |
| "learning_rate": 0.0001058139534883721, | |
| "loss": 0.0074, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.953488372093023, | |
| "grad_norm": 0.005261226557195187, | |
| "learning_rate": 0.0001052325581395349, | |
| "loss": 0.0065, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 19.069767441860463, | |
| "grad_norm": 0.005216473713517189, | |
| "learning_rate": 0.00010465116279069768, | |
| "loss": 0.0066, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 19.186046511627907, | |
| "grad_norm": 0.004990010056644678, | |
| "learning_rate": 0.00010406976744186048, | |
| "loss": 0.0065, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 19.302325581395348, | |
| "grad_norm": 0.005021219607442617, | |
| "learning_rate": 0.00010348837209302327, | |
| "loss": 0.0064, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 19.41860465116279, | |
| "grad_norm": 0.006166994571685791, | |
| "learning_rate": 0.00010290697674418605, | |
| "loss": 0.0069, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 19.53488372093023, | |
| "grad_norm": 0.0043314131908118725, | |
| "learning_rate": 0.00010232558139534885, | |
| "loss": 0.0064, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 19.651162790697676, | |
| "grad_norm": 0.006082617212086916, | |
| "learning_rate": 0.00010174418604651163, | |
| "loss": 0.006, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 19.767441860465116, | |
| "grad_norm": 0.008033761754631996, | |
| "learning_rate": 0.00010116279069767443, | |
| "loss": 0.0064, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.767441860465116, | |
| "eval_f1": 0.0365296803652968, | |
| "eval_loss": 0.008163763210177422, | |
| "eval_runtime": 1.7458, | |
| "eval_samples_per_second": 41.815, | |
| "eval_steps_per_second": 5.728, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.88372093023256, | |
| "grad_norm": 0.006994906347244978, | |
| "learning_rate": 0.00010058139534883721, | |
| "loss": 0.0061, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.006535364780575037, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 20.11627906976744, | |
| "grad_norm": 0.004905609879642725, | |
| "learning_rate": 9.94186046511628e-05, | |
| "loss": 0.006, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 20.232558139534884, | |
| "grad_norm": 0.004114439245313406, | |
| "learning_rate": 9.883720930232558e-05, | |
| "loss": 0.0064, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 20.348837209302324, | |
| "grad_norm": 0.003827931359410286, | |
| "learning_rate": 9.825581395348838e-05, | |
| "loss": 0.0052, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 20.46511627906977, | |
| "grad_norm": 0.0036556690465658903, | |
| "learning_rate": 9.767441860465116e-05, | |
| "loss": 0.0059, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 20.58139534883721, | |
| "grad_norm": 0.00459684245288372, | |
| "learning_rate": 9.709302325581396e-05, | |
| "loss": 0.0053, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 20.697674418604652, | |
| "grad_norm": 0.0047168247401714325, | |
| "learning_rate": 9.651162790697675e-05, | |
| "loss": 0.0059, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 20.813953488372093, | |
| "grad_norm": 0.005462776403874159, | |
| "learning_rate": 9.593023255813955e-05, | |
| "loss": 0.006, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 20.930232558139537, | |
| "grad_norm": 0.004429865162819624, | |
| "learning_rate": 9.534883720930233e-05, | |
| "loss": 0.0061, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.930232558139537, | |
| "eval_f1": 0.0091324200913242, | |
| "eval_loss": 0.008642657659947872, | |
| "eval_runtime": 1.6675, | |
| "eval_samples_per_second": 43.777, | |
| "eval_steps_per_second": 5.997, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 21.046511627906977, | |
| "grad_norm": 0.008058182895183563, | |
| "learning_rate": 9.476744186046512e-05, | |
| "loss": 0.0062, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 21.162790697674417, | |
| "grad_norm": 0.0037425195332616568, | |
| "learning_rate": 9.418604651162792e-05, | |
| "loss": 0.0053, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 21.27906976744186, | |
| "grad_norm": 0.004587921779602766, | |
| "learning_rate": 9.36046511627907e-05, | |
| "loss": 0.006, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 21.3953488372093, | |
| "grad_norm": 0.006532969884574413, | |
| "learning_rate": 9.30232558139535e-05, | |
| "loss": 0.0056, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 21.511627906976745, | |
| "grad_norm": 0.008152597583830357, | |
| "learning_rate": 9.244186046511628e-05, | |
| "loss": 0.0061, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 21.627906976744185, | |
| "grad_norm": 0.005781789310276508, | |
| "learning_rate": 9.186046511627907e-05, | |
| "loss": 0.0059, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 21.74418604651163, | |
| "grad_norm": 0.004202969837933779, | |
| "learning_rate": 9.127906976744186e-05, | |
| "loss": 0.0055, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 21.86046511627907, | |
| "grad_norm": 0.0047506955452263355, | |
| "learning_rate": 9.069767441860465e-05, | |
| "loss": 0.0058, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 21.97674418604651, | |
| "grad_norm": 0.005872243549674749, | |
| "learning_rate": 9.011627906976745e-05, | |
| "loss": 0.0056, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 22.093023255813954, | |
| "grad_norm": 0.005416091997176409, | |
| "learning_rate": 8.953488372093024e-05, | |
| "loss": 0.0054, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 22.093023255813954, | |
| "eval_f1": 0.0593607305936073, | |
| "eval_loss": 0.008248222060501575, | |
| "eval_runtime": 1.7364, | |
| "eval_samples_per_second": 42.04, | |
| "eval_steps_per_second": 5.759, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 22.209302325581394, | |
| "grad_norm": 0.0039680940099060535, | |
| "learning_rate": 8.895348837209302e-05, | |
| "loss": 0.005, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 22.325581395348838, | |
| "grad_norm": 0.0041343714110553265, | |
| "learning_rate": 8.837209302325582e-05, | |
| "loss": 0.006, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 22.441860465116278, | |
| "grad_norm": 0.0031660939566791058, | |
| "learning_rate": 8.779069767441861e-05, | |
| "loss": 0.0053, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 22.558139534883722, | |
| "grad_norm": 0.005090238060802221, | |
| "learning_rate": 8.72093023255814e-05, | |
| "loss": 0.0053, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 22.674418604651162, | |
| "grad_norm": 0.0037465649656951427, | |
| "learning_rate": 8.662790697674419e-05, | |
| "loss": 0.0048, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 22.790697674418606, | |
| "grad_norm": 0.0040254793129861355, | |
| "learning_rate": 8.604651162790697e-05, | |
| "loss": 0.0051, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 22.906976744186046, | |
| "grad_norm": 0.007103138603270054, | |
| "learning_rate": 8.546511627906977e-05, | |
| "loss": 0.0054, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 23.023255813953487, | |
| "grad_norm": 0.00407650088891387, | |
| "learning_rate": 8.488372093023255e-05, | |
| "loss": 0.0055, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 23.13953488372093, | |
| "grad_norm": 0.004379500634968281, | |
| "learning_rate": 8.430232558139536e-05, | |
| "loss": 0.0054, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 23.25581395348837, | |
| "grad_norm": 0.004481241572648287, | |
| "learning_rate": 8.372093023255814e-05, | |
| "loss": 0.0051, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 23.25581395348837, | |
| "eval_f1": 0.0502283105022831, | |
| "eval_loss": 0.008041327819228172, | |
| "eval_runtime": 1.6921, | |
| "eval_samples_per_second": 43.14, | |
| "eval_steps_per_second": 5.91, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 23.372093023255815, | |
| "grad_norm": 0.005388026591390371, | |
| "learning_rate": 8.313953488372094e-05, | |
| "loss": 0.0053, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 23.488372093023255, | |
| "grad_norm": 0.004522989969700575, | |
| "learning_rate": 8.255813953488373e-05, | |
| "loss": 0.0051, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 23.6046511627907, | |
| "grad_norm": 0.0037742829881608486, | |
| "learning_rate": 8.197674418604652e-05, | |
| "loss": 0.0054, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 23.72093023255814, | |
| "grad_norm": 0.0024201772175729275, | |
| "learning_rate": 8.139534883720931e-05, | |
| "loss": 0.0047, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 23.837209302325583, | |
| "grad_norm": 0.010637535713613033, | |
| "learning_rate": 8.081395348837209e-05, | |
| "loss": 0.0053, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 23.953488372093023, | |
| "grad_norm": 0.0036848525051027536, | |
| "learning_rate": 8.023255813953489e-05, | |
| "loss": 0.0045, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 24.069767441860463, | |
| "grad_norm": 0.0036426165606826544, | |
| "learning_rate": 7.965116279069767e-05, | |
| "loss": 0.0051, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 24.186046511627907, | |
| "grad_norm": 0.004131542984396219, | |
| "learning_rate": 7.906976744186047e-05, | |
| "loss": 0.005, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 24.302325581395348, | |
| "grad_norm": 0.005381637252867222, | |
| "learning_rate": 7.848837209302326e-05, | |
| "loss": 0.0049, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 24.41860465116279, | |
| "grad_norm": 0.00364381424151361, | |
| "learning_rate": 7.790697674418606e-05, | |
| "loss": 0.0048, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 24.41860465116279, | |
| "eval_f1": 0.0639269406392694, | |
| "eval_loss": 0.007898622192442417, | |
| "eval_runtime": 1.74, | |
| "eval_samples_per_second": 41.953, | |
| "eval_steps_per_second": 5.747, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 24.53488372093023, | |
| "grad_norm": 0.0032041827216744423, | |
| "learning_rate": 7.732558139534884e-05, | |
| "loss": 0.0047, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 24.651162790697676, | |
| "grad_norm": 0.004305603448301554, | |
| "learning_rate": 7.674418604651163e-05, | |
| "loss": 0.0048, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 24.767441860465116, | |
| "grad_norm": 0.003094649873673916, | |
| "learning_rate": 7.616279069767443e-05, | |
| "loss": 0.0042, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 24.88372093023256, | |
| "grad_norm": 0.0032246061600744724, | |
| "learning_rate": 7.558139534883721e-05, | |
| "loss": 0.0045, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 0.00515501806512475, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0047, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 25.11627906976744, | |
| "grad_norm": 0.003303398611024022, | |
| "learning_rate": 7.441860465116279e-05, | |
| "loss": 0.0039, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 25.232558139534884, | |
| "grad_norm": 0.00300194276496768, | |
| "learning_rate": 7.383720930232558e-05, | |
| "loss": 0.0042, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 25.348837209302324, | |
| "grad_norm": 0.007243013009428978, | |
| "learning_rate": 7.325581395348837e-05, | |
| "loss": 0.0048, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 25.46511627906977, | |
| "grad_norm": 0.00349716329947114, | |
| "learning_rate": 7.267441860465116e-05, | |
| "loss": 0.005, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 25.58139534883721, | |
| "grad_norm": 0.003004447091370821, | |
| "learning_rate": 7.209302325581396e-05, | |
| "loss": 0.0045, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 25.58139534883721, | |
| "eval_f1": 0.0639269406392694, | |
| "eval_loss": 0.008040810003876686, | |
| "eval_runtime": 1.6946, | |
| "eval_samples_per_second": 43.078, | |
| "eval_steps_per_second": 5.901, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 25.697674418604652, | |
| "grad_norm": 0.0032493805047124624, | |
| "learning_rate": 7.151162790697675e-05, | |
| "loss": 0.0042, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 25.813953488372093, | |
| "grad_norm": 0.005652161315083504, | |
| "learning_rate": 7.093023255813955e-05, | |
| "loss": 0.0043, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 25.930232558139537, | |
| "grad_norm": 0.003228959860280156, | |
| "learning_rate": 7.034883720930233e-05, | |
| "loss": 0.004, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 26.046511627906977, | |
| "grad_norm": 0.0029076021164655685, | |
| "learning_rate": 6.976744186046513e-05, | |
| "loss": 0.0046, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 26.162790697674417, | |
| "grad_norm": 0.004093965515494347, | |
| "learning_rate": 6.918604651162791e-05, | |
| "loss": 0.0046, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 26.27906976744186, | |
| "grad_norm": 0.0039006653241813183, | |
| "learning_rate": 6.86046511627907e-05, | |
| "loss": 0.0044, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 26.3953488372093, | |
| "grad_norm": 0.0035654634702950716, | |
| "learning_rate": 6.802325581395348e-05, | |
| "loss": 0.0043, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 26.511627906976745, | |
| "grad_norm": 0.0034853783436119556, | |
| "learning_rate": 6.744186046511628e-05, | |
| "loss": 0.0035, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 26.627906976744185, | |
| "grad_norm": 0.0032556080259382725, | |
| "learning_rate": 6.686046511627908e-05, | |
| "loss": 0.0039, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 26.74418604651163, | |
| "grad_norm": 0.004529784433543682, | |
| "learning_rate": 6.627906976744186e-05, | |
| "loss": 0.0036, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 26.74418604651163, | |
| "eval_f1": 0.10273972602739725, | |
| "eval_loss": 0.007886539213359356, | |
| "eval_runtime": 1.7923, | |
| "eval_samples_per_second": 40.73, | |
| "eval_steps_per_second": 5.579, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 26.86046511627907, | |
| "grad_norm": 0.0036729234270751476, | |
| "learning_rate": 6.569767441860465e-05, | |
| "loss": 0.0041, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 26.97674418604651, | |
| "grad_norm": 0.003093762556090951, | |
| "learning_rate": 6.511627906976745e-05, | |
| "loss": 0.0043, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 27.093023255813954, | |
| "grad_norm": 0.0035506237763911486, | |
| "learning_rate": 6.453488372093024e-05, | |
| "loss": 0.0038, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 27.209302325581394, | |
| "grad_norm": 0.004144872073084116, | |
| "learning_rate": 6.395348837209303e-05, | |
| "loss": 0.0041, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 27.325581395348838, | |
| "grad_norm": 0.0029570453334599733, | |
| "learning_rate": 6.337209302325582e-05, | |
| "loss": 0.0039, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 27.441860465116278, | |
| "grad_norm": 0.0029905049595981836, | |
| "learning_rate": 6.27906976744186e-05, | |
| "loss": 0.0038, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 27.558139534883722, | |
| "grad_norm": 0.0037850120570510626, | |
| "learning_rate": 6.22093023255814e-05, | |
| "loss": 0.0041, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 27.674418604651162, | |
| "grad_norm": 0.0027285381220281124, | |
| "learning_rate": 6.162790697674418e-05, | |
| "loss": 0.004, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 27.790697674418606, | |
| "grad_norm": 0.0033172164112329483, | |
| "learning_rate": 6.104651162790698e-05, | |
| "loss": 0.0036, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 27.906976744186046, | |
| "grad_norm": 0.0038614473305642605, | |
| "learning_rate": 6.0465116279069765e-05, | |
| "loss": 0.0038, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 27.906976744186046, | |
| "eval_f1": 0.10273972602739725, | |
| "eval_loss": 0.007930786348879337, | |
| "eval_runtime": 1.6954, | |
| "eval_samples_per_second": 43.058, | |
| "eval_steps_per_second": 5.898, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 28.023255813953487, | |
| "grad_norm": 0.004366340581327677, | |
| "learning_rate": 5.9883720930232554e-05, | |
| "loss": 0.004, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 28.13953488372093, | |
| "grad_norm": 0.0038022997323423624, | |
| "learning_rate": 5.9302325581395356e-05, | |
| "loss": 0.0038, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 28.25581395348837, | |
| "grad_norm": 0.0036421448457986116, | |
| "learning_rate": 5.8720930232558145e-05, | |
| "loss": 0.0038, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 28.372093023255815, | |
| "grad_norm": 0.003124956740066409, | |
| "learning_rate": 5.8139534883720933e-05, | |
| "loss": 0.0038, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 28.488372093023255, | |
| "grad_norm": 0.0033948852214962244, | |
| "learning_rate": 5.755813953488373e-05, | |
| "loss": 0.0036, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 28.6046511627907, | |
| "grad_norm": 0.002520653186365962, | |
| "learning_rate": 5.697674418604652e-05, | |
| "loss": 0.0035, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 28.72093023255814, | |
| "grad_norm": 0.003338318085297942, | |
| "learning_rate": 5.6395348837209306e-05, | |
| "loss": 0.0037, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 28.837209302325583, | |
| "grad_norm": 0.0030738948844373226, | |
| "learning_rate": 5.5813953488372095e-05, | |
| "loss": 0.0035, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 28.953488372093023, | |
| "grad_norm": 0.0024965908378362656, | |
| "learning_rate": 5.5232558139534884e-05, | |
| "loss": 0.0037, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 29.069767441860463, | |
| "grad_norm": 0.0026568674948066473, | |
| "learning_rate": 5.465116279069767e-05, | |
| "loss": 0.0032, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 29.069767441860463, | |
| "eval_f1": 0.091324200913242, | |
| "eval_loss": 0.007714101579040289, | |
| "eval_runtime": 1.768, | |
| "eval_samples_per_second": 41.289, | |
| "eval_steps_per_second": 5.656, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 29.186046511627907, | |
| "grad_norm": 0.004428944084793329, | |
| "learning_rate": 5.406976744186046e-05, | |
| "loss": 0.0036, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 29.302325581395348, | |
| "grad_norm": 0.0083547318354249, | |
| "learning_rate": 5.348837209302326e-05, | |
| "loss": 0.0033, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 29.41860465116279, | |
| "grad_norm": 0.003402271308004856, | |
| "learning_rate": 5.290697674418605e-05, | |
| "loss": 0.0039, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 29.53488372093023, | |
| "grad_norm": 0.0033303038217127323, | |
| "learning_rate": 5.232558139534884e-05, | |
| "loss": 0.0035, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 29.651162790697676, | |
| "grad_norm": 0.03485463559627533, | |
| "learning_rate": 5.1744186046511636e-05, | |
| "loss": 0.0038, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 29.767441860465116, | |
| "grad_norm": 0.004661730024963617, | |
| "learning_rate": 5.1162790697674425e-05, | |
| "loss": 0.0036, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 29.88372093023256, | |
| "grad_norm": 0.0038003467489033937, | |
| "learning_rate": 5.0581395348837214e-05, | |
| "loss": 0.0035, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.004514409229159355, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0033, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 30.11627906976744, | |
| "grad_norm": 0.004792849998921156, | |
| "learning_rate": 4.941860465116279e-05, | |
| "loss": 0.0035, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 30.232558139534884, | |
| "grad_norm": 0.004430180415511131, | |
| "learning_rate": 4.883720930232558e-05, | |
| "loss": 0.004, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 30.232558139534884, | |
| "eval_f1": 0.10273972602739725, | |
| "eval_loss": 0.007851834408938885, | |
| "eval_runtime": 1.6578, | |
| "eval_samples_per_second": 44.034, | |
| "eval_steps_per_second": 6.032, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 30.348837209302324, | |
| "grad_norm": 0.0030448336619883776, | |
| "learning_rate": 4.8255813953488375e-05, | |
| "loss": 0.0034, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 30.46511627906977, | |
| "grad_norm": 0.0026765645015984774, | |
| "learning_rate": 4.7674418604651164e-05, | |
| "loss": 0.0033, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 30.58139534883721, | |
| "grad_norm": 0.002969229593873024, | |
| "learning_rate": 4.709302325581396e-05, | |
| "loss": 0.0033, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 30.697674418604652, | |
| "grad_norm": 0.005750367883592844, | |
| "learning_rate": 4.651162790697675e-05, | |
| "loss": 0.0029, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 30.813953488372093, | |
| "grad_norm": 0.0028870333917438984, | |
| "learning_rate": 4.593023255813954e-05, | |
| "loss": 0.0033, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 30.930232558139537, | |
| "grad_norm": 0.003318176371976733, | |
| "learning_rate": 4.5348837209302326e-05, | |
| "loss": 0.0034, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 31.046511627906977, | |
| "grad_norm": 0.0030346305575221777, | |
| "learning_rate": 4.476744186046512e-05, | |
| "loss": 0.003, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 31.162790697674417, | |
| "grad_norm": 0.0031568079721182585, | |
| "learning_rate": 4.418604651162791e-05, | |
| "loss": 0.0033, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 31.27906976744186, | |
| "grad_norm": 0.0028284024447202682, | |
| "learning_rate": 4.36046511627907e-05, | |
| "loss": 0.0031, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 31.3953488372093, | |
| "grad_norm": 0.003977891989052296, | |
| "learning_rate": 4.302325581395349e-05, | |
| "loss": 0.003, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 31.3953488372093, | |
| "eval_f1": 0.09360730593607304, | |
| "eval_loss": 0.008055122569203377, | |
| "eval_runtime": 1.6937, | |
| "eval_samples_per_second": 43.101, | |
| "eval_steps_per_second": 5.904, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 31.511627906976745, | |
| "grad_norm": 0.0026259180158376694, | |
| "learning_rate": 4.2441860465116276e-05, | |
| "loss": 0.0036, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 31.627906976744185, | |
| "grad_norm": 0.003417164785787463, | |
| "learning_rate": 4.186046511627907e-05, | |
| "loss": 0.0032, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 31.74418604651163, | |
| "grad_norm": 0.0038994085043668747, | |
| "learning_rate": 4.127906976744187e-05, | |
| "loss": 0.0032, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 31.86046511627907, | |
| "grad_norm": 0.0034232349134981632, | |
| "learning_rate": 4.0697674418604655e-05, | |
| "loss": 0.0027, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 31.97674418604651, | |
| "grad_norm": 0.004144703969359398, | |
| "learning_rate": 4.0116279069767444e-05, | |
| "loss": 0.0035, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 32.093023255813954, | |
| "grad_norm": 0.0026302810292690992, | |
| "learning_rate": 3.953488372093023e-05, | |
| "loss": 0.0032, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 32.2093023255814, | |
| "grad_norm": 0.002205599332228303, | |
| "learning_rate": 3.895348837209303e-05, | |
| "loss": 0.0033, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 32.325581395348834, | |
| "grad_norm": 0.003439367515966296, | |
| "learning_rate": 3.837209302325582e-05, | |
| "loss": 0.0032, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 32.44186046511628, | |
| "grad_norm": 0.0022263077553361654, | |
| "learning_rate": 3.7790697674418606e-05, | |
| "loss": 0.0029, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 32.55813953488372, | |
| "grad_norm": 0.003249467583373189, | |
| "learning_rate": 3.7209302325581394e-05, | |
| "loss": 0.0029, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 32.55813953488372, | |
| "eval_f1": 0.08904109589041094, | |
| "eval_loss": 0.008000507019460201, | |
| "eval_runtime": 1.6639, | |
| "eval_samples_per_second": 43.874, | |
| "eval_steps_per_second": 6.01, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 32.674418604651166, | |
| "grad_norm": 0.003246536012738943, | |
| "learning_rate": 3.662790697674418e-05, | |
| "loss": 0.0027, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 32.7906976744186, | |
| "grad_norm": 0.0032464447431266308, | |
| "learning_rate": 3.604651162790698e-05, | |
| "loss": 0.0033, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 32.906976744186046, | |
| "grad_norm": 0.002286577830091119, | |
| "learning_rate": 3.5465116279069774e-05, | |
| "loss": 0.0029, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 33.02325581395349, | |
| "grad_norm": 0.0027776581700891256, | |
| "learning_rate": 3.488372093023256e-05, | |
| "loss": 0.003, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 33.13953488372093, | |
| "grad_norm": 0.0025106158573180437, | |
| "learning_rate": 3.430232558139535e-05, | |
| "loss": 0.0027, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 33.25581395348837, | |
| "grad_norm": 0.0026736510917544365, | |
| "learning_rate": 3.372093023255814e-05, | |
| "loss": 0.0029, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 33.372093023255815, | |
| "grad_norm": 0.002507059136405587, | |
| "learning_rate": 3.313953488372093e-05, | |
| "loss": 0.0025, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 33.48837209302326, | |
| "grad_norm": 0.0028928928077220917, | |
| "learning_rate": 3.2558139534883724e-05, | |
| "loss": 0.0031, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 33.604651162790695, | |
| "grad_norm": 0.0032647838816046715, | |
| "learning_rate": 3.197674418604651e-05, | |
| "loss": 0.0028, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 33.72093023255814, | |
| "grad_norm": 0.0033728063572198153, | |
| "learning_rate": 3.13953488372093e-05, | |
| "loss": 0.0033, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 33.72093023255814, | |
| "eval_f1": 0.08447488584474885, | |
| "eval_loss": 0.008075451478362083, | |
| "eval_runtime": 1.6844, | |
| "eval_samples_per_second": 43.339, | |
| "eval_steps_per_second": 5.937, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 33.83720930232558, | |
| "grad_norm": 0.0026662382297217846, | |
| "learning_rate": 3.081395348837209e-05, | |
| "loss": 0.0031, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 33.95348837209303, | |
| "grad_norm": 0.0025568390265107155, | |
| "learning_rate": 3.0232558139534883e-05, | |
| "loss": 0.0028, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 34.06976744186046, | |
| "grad_norm": 0.002340954029932618, | |
| "learning_rate": 2.9651162790697678e-05, | |
| "loss": 0.0026, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 34.18604651162791, | |
| "grad_norm": 0.0033266523387283087, | |
| "learning_rate": 2.9069767441860467e-05, | |
| "loss": 0.0031, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 34.30232558139535, | |
| "grad_norm": 0.0023587134201079607, | |
| "learning_rate": 2.848837209302326e-05, | |
| "loss": 0.0027, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 34.41860465116279, | |
| "grad_norm": 0.002229692181572318, | |
| "learning_rate": 2.7906976744186048e-05, | |
| "loss": 0.0029, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 34.53488372093023, | |
| "grad_norm": 0.0029290826059877872, | |
| "learning_rate": 2.7325581395348836e-05, | |
| "loss": 0.0026, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 34.651162790697676, | |
| "grad_norm": 0.0030265513341873884, | |
| "learning_rate": 2.674418604651163e-05, | |
| "loss": 0.0026, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 34.76744186046512, | |
| "grad_norm": 0.0028545409440994263, | |
| "learning_rate": 2.616279069767442e-05, | |
| "loss": 0.0032, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 34.883720930232556, | |
| "grad_norm": 0.002398886950686574, | |
| "learning_rate": 2.5581395348837212e-05, | |
| "loss": 0.0029, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 34.883720930232556, | |
| "eval_f1": 0.12557077625570776, | |
| "eval_loss": 0.008088447153568268, | |
| "eval_runtime": 1.6856, | |
| "eval_samples_per_second": 43.309, | |
| "eval_steps_per_second": 5.933, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "grad_norm": 0.00287942448630929, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0026, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 35.116279069767444, | |
| "grad_norm": 0.0025614567566663027, | |
| "learning_rate": 2.441860465116279e-05, | |
| "loss": 0.0024, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 35.23255813953488, | |
| "grad_norm": 0.002899142215028405, | |
| "learning_rate": 2.3837209302325582e-05, | |
| "loss": 0.0028, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 35.348837209302324, | |
| "grad_norm": 0.003214885015040636, | |
| "learning_rate": 2.3255813953488374e-05, | |
| "loss": 0.0032, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 35.46511627906977, | |
| "grad_norm": 0.003339228220283985, | |
| "learning_rate": 2.2674418604651163e-05, | |
| "loss": 0.0027, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 35.58139534883721, | |
| "grad_norm": 0.0030185177456587553, | |
| "learning_rate": 2.2093023255813955e-05, | |
| "loss": 0.0028, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 35.69767441860465, | |
| "grad_norm": 0.00310333538800478, | |
| "learning_rate": 2.1511627906976744e-05, | |
| "loss": 0.0026, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 35.81395348837209, | |
| "grad_norm": 0.0028332043439149857, | |
| "learning_rate": 2.0930232558139536e-05, | |
| "loss": 0.0026, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 35.93023255813954, | |
| "grad_norm": 0.0021240401547402143, | |
| "learning_rate": 2.0348837209302328e-05, | |
| "loss": 0.0028, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 36.04651162790697, | |
| "grad_norm": 0.0028554806485772133, | |
| "learning_rate": 1.9767441860465116e-05, | |
| "loss": 0.0025, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 36.04651162790697, | |
| "eval_f1": 0.13470319634703196, | |
| "eval_loss": 0.008070297539234161, | |
| "eval_runtime": 1.8154, | |
| "eval_samples_per_second": 40.211, | |
| "eval_steps_per_second": 5.508, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 36.16279069767442, | |
| "grad_norm": 0.0031274755019694567, | |
| "learning_rate": 1.918604651162791e-05, | |
| "loss": 0.0029, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 36.27906976744186, | |
| "grad_norm": 0.0016608175355941057, | |
| "learning_rate": 1.8604651162790697e-05, | |
| "loss": 0.0026, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 36.395348837209305, | |
| "grad_norm": 0.0023403004743158817, | |
| "learning_rate": 1.802325581395349e-05, | |
| "loss": 0.0025, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 36.51162790697674, | |
| "grad_norm": 0.0022207223810255527, | |
| "learning_rate": 1.744186046511628e-05, | |
| "loss": 0.0028, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 36.627906976744185, | |
| "grad_norm": 0.0019355164840817451, | |
| "learning_rate": 1.686046511627907e-05, | |
| "loss": 0.0025, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 36.74418604651163, | |
| "grad_norm": 0.00238374387845397, | |
| "learning_rate": 1.6279069767441862e-05, | |
| "loss": 0.0026, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 36.86046511627907, | |
| "grad_norm": 0.002908985363319516, | |
| "learning_rate": 1.569767441860465e-05, | |
| "loss": 0.0028, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 36.97674418604651, | |
| "grad_norm": 0.002507247030735016, | |
| "learning_rate": 1.5116279069767441e-05, | |
| "loss": 0.0025, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 37.093023255813954, | |
| "grad_norm": 0.0024845688603818417, | |
| "learning_rate": 1.4534883720930233e-05, | |
| "loss": 0.0028, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 37.2093023255814, | |
| "grad_norm": 0.0021229905541986227, | |
| "learning_rate": 1.3953488372093024e-05, | |
| "loss": 0.0027, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 37.2093023255814, | |
| "eval_f1": 0.1324200913242009, | |
| "eval_loss": 0.008123889565467834, | |
| "eval_runtime": 1.6983, | |
| "eval_samples_per_second": 42.985, | |
| "eval_steps_per_second": 5.888, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 37.325581395348834, | |
| "grad_norm": 0.0020165506284683943, | |
| "learning_rate": 1.3372093023255814e-05, | |
| "loss": 0.0024, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 37.44186046511628, | |
| "grad_norm": 0.00225025019608438, | |
| "learning_rate": 1.2790697674418606e-05, | |
| "loss": 0.0024, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 37.55813953488372, | |
| "grad_norm": 0.002410660730674863, | |
| "learning_rate": 1.2209302325581395e-05, | |
| "loss": 0.0025, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 37.674418604651166, | |
| "grad_norm": 0.0022259822580963373, | |
| "learning_rate": 1.1627906976744187e-05, | |
| "loss": 0.0026, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 37.7906976744186, | |
| "grad_norm": 0.002472145715728402, | |
| "learning_rate": 1.1046511627906977e-05, | |
| "loss": 0.0028, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 37.906976744186046, | |
| "grad_norm": 0.002238726709038019, | |
| "learning_rate": 1.0465116279069768e-05, | |
| "loss": 0.0024, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 38.02325581395349, | |
| "grad_norm": 0.0025766075123101473, | |
| "learning_rate": 9.883720930232558e-06, | |
| "loss": 0.0027, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 38.13953488372093, | |
| "grad_norm": 0.002669785637408495, | |
| "learning_rate": 9.302325581395349e-06, | |
| "loss": 0.0027, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 38.25581395348837, | |
| "grad_norm": 0.0023648098576813936, | |
| "learning_rate": 8.72093023255814e-06, | |
| "loss": 0.0028, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 38.372093023255815, | |
| "grad_norm": 0.0019695968367159367, | |
| "learning_rate": 8.139534883720931e-06, | |
| "loss": 0.0028, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 38.372093023255815, | |
| "eval_f1": 0.1324200913242009, | |
| "eval_loss": 0.008158449083566666, | |
| "eval_runtime": 1.8249, | |
| "eval_samples_per_second": 40.002, | |
| "eval_steps_per_second": 5.48, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 38.48837209302326, | |
| "grad_norm": 0.0023280028253793716, | |
| "learning_rate": 7.558139534883721e-06, | |
| "loss": 0.0024, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 38.604651162790695, | |
| "grad_norm": 0.0030140073504298925, | |
| "learning_rate": 6.976744186046512e-06, | |
| "loss": 0.0026, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 38.72093023255814, | |
| "grad_norm": 0.0024626152589917183, | |
| "learning_rate": 6.395348837209303e-06, | |
| "loss": 0.0024, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 38.83720930232558, | |
| "grad_norm": 0.0027184640057384968, | |
| "learning_rate": 5.8139534883720935e-06, | |
| "loss": 0.0022, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 38.95348837209303, | |
| "grad_norm": 0.002258691005408764, | |
| "learning_rate": 5.232558139534884e-06, | |
| "loss": 0.0027, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 39.06976744186046, | |
| "grad_norm": 0.0015635826857760549, | |
| "learning_rate": 4.651162790697674e-06, | |
| "loss": 0.0025, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 39.18604651162791, | |
| "grad_norm": 0.0014281744370236993, | |
| "learning_rate": 4.0697674418604655e-06, | |
| "loss": 0.0025, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 39.30232558139535, | |
| "grad_norm": 0.0019795901607722044, | |
| "learning_rate": 3.488372093023256e-06, | |
| "loss": 0.0024, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 39.41860465116279, | |
| "grad_norm": 0.00274649984203279, | |
| "learning_rate": 2.9069767441860468e-06, | |
| "loss": 0.0028, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 39.53488372093023, | |
| "grad_norm": 0.0021044183522462845, | |
| "learning_rate": 2.325581395348837e-06, | |
| "loss": 0.0023, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 39.53488372093023, | |
| "eval_f1": 0.1324200913242009, | |
| "eval_loss": 0.008160348981618881, | |
| "eval_runtime": 1.7392, | |
| "eval_samples_per_second": 41.972, | |
| "eval_steps_per_second": 5.75, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 39.651162790697676, | |
| "grad_norm": 0.0022693907376378775, | |
| "learning_rate": 1.744186046511628e-06, | |
| "loss": 0.0025, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 39.76744186046512, | |
| "grad_norm": 0.0020165799651294947, | |
| "learning_rate": 1.1627906976744186e-06, | |
| "loss": 0.0027, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 39.883720930232556, | |
| "grad_norm": 0.0023625025060027838, | |
| "learning_rate": 5.813953488372093e-07, | |
| "loss": 0.0022, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.0031698495149612427, | |
| "learning_rate": 0.0, | |
| "loss": 0.0029, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 3440, | |
| "total_flos": 4.2863407148659507e+18, | |
| "train_loss": 0.015139733321509908, | |
| "train_runtime": 1940.273, | |
| "train_samples_per_second": 28.285, | |
| "train_steps_per_second": 1.773 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 100, | |
| "total_flos": 4.2863407148659507e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |