| { | |
| "best_metric": 0.9707943925233645, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-lora-medmnistv2/checkpoint-1870", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1870, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 4.650041580200195, | |
| "learning_rate": 0.004973262032085562, | |
| "loss": 1.5063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 3.0658373832702637, | |
| "learning_rate": 0.004946524064171123, | |
| "loss": 0.8711, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16042780748663102, | |
| "grad_norm": 2.9676272869110107, | |
| "learning_rate": 0.004919786096256685, | |
| "loss": 0.8, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 2.5159189701080322, | |
| "learning_rate": 0.004893048128342246, | |
| "loss": 0.7794, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26737967914438504, | |
| "grad_norm": 2.4576735496520996, | |
| "learning_rate": 0.004868983957219251, | |
| "loss": 0.8748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 1.9533675909042358, | |
| "learning_rate": 0.004842245989304813, | |
| "loss": 0.6213, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37433155080213903, | |
| "grad_norm": 3.91825795173645, | |
| "learning_rate": 0.004815508021390374, | |
| "loss": 0.6883, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "grad_norm": 3.228422164916992, | |
| "learning_rate": 0.004788770053475936, | |
| "loss": 0.7019, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.48128342245989303, | |
| "grad_norm": 4.45206356048584, | |
| "learning_rate": 0.004762032085561497, | |
| "loss": 0.5394, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5347593582887701, | |
| "grad_norm": 2.184957504272461, | |
| "learning_rate": 0.004735294117647059, | |
| "loss": 0.5543, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 2.246079206466675, | |
| "learning_rate": 0.00470855614973262, | |
| "loss": 0.5738, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "grad_norm": 2.6914820671081543, | |
| "learning_rate": 0.004681818181818182, | |
| "loss": 0.6209, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6951871657754011, | |
| "grad_norm": 2.5458545684814453, | |
| "learning_rate": 0.0046550802139037435, | |
| "loss": 0.5597, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7486631016042781, | |
| "grad_norm": 2.676391363143921, | |
| "learning_rate": 0.004628342245989305, | |
| "loss": 0.5273, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8021390374331551, | |
| "grad_norm": 2.5059385299682617, | |
| "learning_rate": 0.0046016042780748665, | |
| "loss": 0.5199, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": 1.451249122619629, | |
| "learning_rate": 0.004574866310160428, | |
| "loss": 0.5509, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 2.5957276821136475, | |
| "learning_rate": 0.00454812834224599, | |
| "loss": 0.5336, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9625668449197861, | |
| "grad_norm": 2.4229955673217773, | |
| "learning_rate": 0.004521390374331551, | |
| "loss": 0.4657, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9094626168224299, | |
| "eval_f1": 0.8972949130385568, | |
| "eval_loss": 0.2451503425836563, | |
| "eval_precision": 0.8964084875867973, | |
| "eval_recall": 0.9082806506629539, | |
| "eval_runtime": 10.2386, | |
| "eval_samples_per_second": 167.21, | |
| "eval_steps_per_second": 10.451, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.0160427807486632, | |
| "grad_norm": 2.3994851112365723, | |
| "learning_rate": 0.004494652406417113, | |
| "loss": 0.4772, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0695187165775402, | |
| "grad_norm": 1.985571265220642, | |
| "learning_rate": 0.004467914438502674, | |
| "loss": 0.5995, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1229946524064172, | |
| "grad_norm": 2.3798632621765137, | |
| "learning_rate": 0.004441176470588235, | |
| "loss": 0.5686, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 3.1128406524658203, | |
| "learning_rate": 0.004414438502673797, | |
| "loss": 0.4984, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2299465240641712, | |
| "grad_norm": 2.8572049140930176, | |
| "learning_rate": 0.004387700534759359, | |
| "loss": 0.5027, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.2834224598930482, | |
| "grad_norm": 5.178213119506836, | |
| "learning_rate": 0.00436096256684492, | |
| "loss": 0.4864, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3368983957219251, | |
| "grad_norm": 1.9515773057937622, | |
| "learning_rate": 0.004334224598930481, | |
| "loss": 0.4528, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.3903743315508021, | |
| "grad_norm": 3.023959159851074, | |
| "learning_rate": 0.0043074866310160425, | |
| "loss": 0.5513, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4438502673796791, | |
| "grad_norm": 2.371218204498291, | |
| "learning_rate": 0.004280748663101605, | |
| "loss": 0.442, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4973262032085561, | |
| "grad_norm": 2.111191987991333, | |
| "learning_rate": 0.004254010695187166, | |
| "loss": 0.6163, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.5508021390374331, | |
| "grad_norm": 2.123419761657715, | |
| "learning_rate": 0.004227272727272727, | |
| "loss": 0.5522, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.6042780748663101, | |
| "grad_norm": 1.6425999402999878, | |
| "learning_rate": 0.004200534759358289, | |
| "loss": 0.4601, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6577540106951871, | |
| "grad_norm": 3.847395420074463, | |
| "learning_rate": 0.00417379679144385, | |
| "loss": 0.5434, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7112299465240641, | |
| "grad_norm": 1.8732799291610718, | |
| "learning_rate": 0.004147058823529412, | |
| "loss": 0.4952, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 1.4881893396377563, | |
| "learning_rate": 0.004120320855614973, | |
| "loss": 0.4926, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.9936500787734985, | |
| "learning_rate": 0.004093582887700535, | |
| "loss": 0.4582, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8716577540106951, | |
| "grad_norm": 4.784737586975098, | |
| "learning_rate": 0.004066844919786096, | |
| "loss": 0.4839, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.9251336898395723, | |
| "grad_norm": 2.403982162475586, | |
| "learning_rate": 0.004040106951871658, | |
| "loss": 0.5868, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9786096256684491, | |
| "grad_norm": 1.7464922666549683, | |
| "learning_rate": 0.004013368983957219, | |
| "loss": 0.4327, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9182242990654206, | |
| "eval_f1": 0.9007413709436916, | |
| "eval_loss": 0.21109923720359802, | |
| "eval_precision": 0.9299210483133126, | |
| "eval_recall": 0.8921235393972065, | |
| "eval_runtime": 10.4332, | |
| "eval_samples_per_second": 164.091, | |
| "eval_steps_per_second": 10.256, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 2.0320855614973263, | |
| "grad_norm": 1.444707989692688, | |
| "learning_rate": 0.003986631016042781, | |
| "loss": 0.478, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.085561497326203, | |
| "grad_norm": 1.4123905897140503, | |
| "learning_rate": 0.003959893048128342, | |
| "loss": 0.5, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1390374331550803, | |
| "grad_norm": 2.96335768699646, | |
| "learning_rate": 0.003933155080213904, | |
| "loss": 0.5348, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.192513368983957, | |
| "grad_norm": 1.4397529363632202, | |
| "learning_rate": 0.0039064171122994654, | |
| "loss": 0.4571, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2459893048128343, | |
| "grad_norm": 1.821366548538208, | |
| "learning_rate": 0.0038796791443850265, | |
| "loss": 0.4982, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.299465240641711, | |
| "grad_norm": 2.112130641937256, | |
| "learning_rate": 0.0038529411764705885, | |
| "loss": 0.4343, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 1.942734956741333, | |
| "learning_rate": 0.00382620320855615, | |
| "loss": 0.5078, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.406417112299465, | |
| "grad_norm": 2.774502754211426, | |
| "learning_rate": 0.003799465240641711, | |
| "loss": 0.4016, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4598930481283423, | |
| "grad_norm": 2.139463424682617, | |
| "learning_rate": 0.0037727272727272726, | |
| "loss": 0.5415, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.5133689839572195, | |
| "grad_norm": 1.9148341417312622, | |
| "learning_rate": 0.003745989304812834, | |
| "loss": 0.4417, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.5668449197860963, | |
| "grad_norm": 1.9109567403793335, | |
| "learning_rate": 0.003719251336898396, | |
| "loss": 0.4273, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.620320855614973, | |
| "grad_norm": 2.2219059467315674, | |
| "learning_rate": 0.0036925133689839572, | |
| "loss": 0.5218, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6737967914438503, | |
| "grad_norm": 3.378606081008911, | |
| "learning_rate": 0.0036657754010695188, | |
| "loss": 0.4318, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 1.668760061264038, | |
| "learning_rate": 0.0036390374331550803, | |
| "loss": 0.4447, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.7807486631016043, | |
| "grad_norm": 1.830342411994934, | |
| "learning_rate": 0.0036122994652406414, | |
| "loss": 0.4507, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.834224598930481, | |
| "grad_norm": 2.2146425247192383, | |
| "learning_rate": 0.0035855614973262034, | |
| "loss": 0.4127, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8877005347593583, | |
| "grad_norm": 1.3959295749664307, | |
| "learning_rate": 0.003558823529411765, | |
| "loss": 0.4353, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 1.844604253768921, | |
| "learning_rate": 0.0035320855614973264, | |
| "loss": 0.3488, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9946524064171123, | |
| "grad_norm": 1.421885371208191, | |
| "learning_rate": 0.0035053475935828875, | |
| "loss": 0.3977, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9339953271028038, | |
| "eval_f1": 0.924420495312186, | |
| "eval_loss": 0.17427141964435577, | |
| "eval_precision": 0.9228598461246502, | |
| "eval_recall": 0.928247943129569, | |
| "eval_runtime": 9.981, | |
| "eval_samples_per_second": 171.527, | |
| "eval_steps_per_second": 10.72, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 3.0481283422459895, | |
| "grad_norm": 2.2883894443511963, | |
| "learning_rate": 0.003478609625668449, | |
| "loss": 0.3909, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.1016042780748663, | |
| "grad_norm": 2.4753079414367676, | |
| "learning_rate": 0.003451871657754011, | |
| "loss": 0.4352, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.1550802139037435, | |
| "grad_norm": 2.298736572265625, | |
| "learning_rate": 0.0034251336898395725, | |
| "loss": 0.4641, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.2085561497326203, | |
| "grad_norm": 1.4368634223937988, | |
| "learning_rate": 0.0033983957219251336, | |
| "loss": 0.4225, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.2620320855614975, | |
| "grad_norm": 1.462842583656311, | |
| "learning_rate": 0.003371657754010695, | |
| "loss": 0.3958, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.3155080213903743, | |
| "grad_norm": 2.449066638946533, | |
| "learning_rate": 0.0033449197860962567, | |
| "loss": 0.3784, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.3689839572192515, | |
| "grad_norm": 1.5616710186004639, | |
| "learning_rate": 0.0033181818181818186, | |
| "loss": 0.4476, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.4224598930481283, | |
| "grad_norm": 2.284454345703125, | |
| "learning_rate": 0.0032914438502673797, | |
| "loss": 0.3725, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.4759358288770055, | |
| "grad_norm": 1.5143663883209229, | |
| "learning_rate": 0.0032647058823529413, | |
| "loss": 0.4597, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 1.6112128496170044, | |
| "learning_rate": 0.003237967914438503, | |
| "loss": 0.4198, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.5828877005347595, | |
| "grad_norm": 1.2612804174423218, | |
| "learning_rate": 0.003211229946524064, | |
| "loss": 0.4785, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 2.0233500003814697, | |
| "learning_rate": 0.0031844919786096254, | |
| "loss": 0.4276, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.6898395721925135, | |
| "grad_norm": 1.2161093950271606, | |
| "learning_rate": 0.0031577540106951874, | |
| "loss": 0.3865, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.7433155080213902, | |
| "grad_norm": 1.835656762123108, | |
| "learning_rate": 0.003131016042780749, | |
| "loss": 0.3202, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.7967914438502675, | |
| "grad_norm": 2.9908785820007324, | |
| "learning_rate": 0.00310427807486631, | |
| "loss": 0.3879, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.8502673796791442, | |
| "grad_norm": 1.587223768234253, | |
| "learning_rate": 0.0030775401069518715, | |
| "loss": 0.3682, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.9037433155080214, | |
| "grad_norm": 2.0039021968841553, | |
| "learning_rate": 0.003050802139037433, | |
| "loss": 0.4148, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.9572192513368982, | |
| "grad_norm": 1.8037409782409668, | |
| "learning_rate": 0.003024064171122995, | |
| "loss": 0.3318, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9351635514018691, | |
| "eval_f1": 0.928485806906975, | |
| "eval_loss": 0.17756415903568268, | |
| "eval_precision": 0.9248343621199285, | |
| "eval_recall": 0.9352570988138212, | |
| "eval_runtime": 10.1719, | |
| "eval_samples_per_second": 168.307, | |
| "eval_steps_per_second": 10.519, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 4.010695187165775, | |
| "grad_norm": 2.230004072189331, | |
| "learning_rate": 0.002997326203208556, | |
| "loss": 0.4071, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.064171122994653, | |
| "grad_norm": 2.1018853187561035, | |
| "learning_rate": 0.0029705882352941177, | |
| "loss": 0.3498, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 1.6814857721328735, | |
| "learning_rate": 0.002943850267379679, | |
| "loss": 0.4085, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.171122994652406, | |
| "grad_norm": 2.0869903564453125, | |
| "learning_rate": 0.0029171122994652403, | |
| "loss": 0.4481, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.224598930481283, | |
| "grad_norm": 1.4043067693710327, | |
| "learning_rate": 0.0028903743315508022, | |
| "loss": 0.3234, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.278074866310161, | |
| "grad_norm": 2.0766959190368652, | |
| "learning_rate": 0.0028636363636363638, | |
| "loss": 0.3719, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.331550802139038, | |
| "grad_norm": 1.85934317111969, | |
| "learning_rate": 0.0028368983957219253, | |
| "loss": 0.4784, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.385026737967914, | |
| "grad_norm": 2.3728232383728027, | |
| "learning_rate": 0.0028101604278074864, | |
| "loss": 0.3704, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.438502673796791, | |
| "grad_norm": 1.2759883403778076, | |
| "learning_rate": 0.002783422459893048, | |
| "loss": 0.3283, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.491978609625669, | |
| "grad_norm": 1.2006633281707764, | |
| "learning_rate": 0.00275668449197861, | |
| "loss": 0.3792, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 2.0884652137756348, | |
| "learning_rate": 0.0027299465240641714, | |
| "loss": 0.4041, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.598930481283422, | |
| "grad_norm": 1.281827688217163, | |
| "learning_rate": 0.0027032085561497325, | |
| "loss": 0.352, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.652406417112299, | |
| "grad_norm": 1.7143138647079468, | |
| "learning_rate": 0.002676470588235294, | |
| "loss": 0.3896, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 2.069678544998169, | |
| "learning_rate": 0.0026497326203208556, | |
| "loss": 0.335, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.759358288770054, | |
| "grad_norm": 1.6988319158554077, | |
| "learning_rate": 0.0026229946524064175, | |
| "loss": 0.3693, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.81283422459893, | |
| "grad_norm": 1.6188457012176514, | |
| "learning_rate": 0.0025962566844919786, | |
| "loss": 0.337, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.866310160427807, | |
| "grad_norm": 2.0478222370147705, | |
| "learning_rate": 0.00256951871657754, | |
| "loss": 0.3156, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.919786096256685, | |
| "grad_norm": 1.7088401317596436, | |
| "learning_rate": 0.0025427807486631017, | |
| "loss": 0.3414, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.973262032085562, | |
| "grad_norm": 1.161230444908142, | |
| "learning_rate": 0.002516042780748663, | |
| "loss": 0.3461, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9380841121495327, | |
| "eval_f1": 0.9304948103477649, | |
| "eval_loss": 0.17028363049030304, | |
| "eval_precision": 0.9311071354745837, | |
| "eval_recall": 0.9344001562456381, | |
| "eval_runtime": 10.2604, | |
| "eval_samples_per_second": 166.855, | |
| "eval_steps_per_second": 10.428, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 5.026737967914438, | |
| "grad_norm": 1.723848819732666, | |
| "learning_rate": 0.0024893048128342248, | |
| "loss": 0.3622, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.080213903743315, | |
| "grad_norm": 2.0140602588653564, | |
| "learning_rate": 0.002462566844919786, | |
| "loss": 0.3973, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.133689839572193, | |
| "grad_norm": 1.5653032064437866, | |
| "learning_rate": 0.002435828877005348, | |
| "loss": 0.3106, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.18716577540107, | |
| "grad_norm": 1.7829616069793701, | |
| "learning_rate": 0.002409090909090909, | |
| "loss": 0.3723, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.240641711229946, | |
| "grad_norm": 0.9940521717071533, | |
| "learning_rate": 0.0023823529411764704, | |
| "loss": 0.3453, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.294117647058823, | |
| "grad_norm": 1.1114059686660767, | |
| "learning_rate": 0.002355614973262032, | |
| "loss": 0.3769, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.347593582887701, | |
| "grad_norm": 0.9444433450698853, | |
| "learning_rate": 0.0023288770053475935, | |
| "loss": 0.3489, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.401069518716578, | |
| "grad_norm": 2.0856947898864746, | |
| "learning_rate": 0.002302139037433155, | |
| "loss": 0.374, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 1.679477572441101, | |
| "learning_rate": 0.0022754010695187166, | |
| "loss": 0.3738, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.508021390374331, | |
| "grad_norm": 1.3019518852233887, | |
| "learning_rate": 0.002248663101604278, | |
| "loss": 0.3634, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.561497326203209, | |
| "grad_norm": 1.467846155166626, | |
| "learning_rate": 0.0022219251336898396, | |
| "loss": 0.3457, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.614973262032086, | |
| "grad_norm": 1.6348631381988525, | |
| "learning_rate": 0.002195187165775401, | |
| "loss": 0.3216, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.668449197860962, | |
| "grad_norm": 1.158215880393982, | |
| "learning_rate": 0.0021684491978609627, | |
| "loss": 0.3033, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.721925133689839, | |
| "grad_norm": 0.8872423768043518, | |
| "learning_rate": 0.002141711229946524, | |
| "loss": 0.2919, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.775401069518717, | |
| "grad_norm": 1.9146243333816528, | |
| "learning_rate": 0.0021149732620320857, | |
| "loss": 0.3228, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.828877005347594, | |
| "grad_norm": 1.7084169387817383, | |
| "learning_rate": 0.0020882352941176473, | |
| "loss": 0.2754, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 1.0626111030578613, | |
| "learning_rate": 0.0020614973262032084, | |
| "loss": 0.3165, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.935828877005347, | |
| "grad_norm": 1.8155293464660645, | |
| "learning_rate": 0.00203475935828877, | |
| "loss": 0.2815, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.989304812834225, | |
| "grad_norm": 1.8623782396316528, | |
| "learning_rate": 0.0020080213903743314, | |
| "loss": 0.3309, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9369158878504673, | |
| "eval_f1": 0.9334719219156348, | |
| "eval_loss": 0.19556888937950134, | |
| "eval_precision": 0.9335706750233659, | |
| "eval_recall": 0.9396740716392903, | |
| "eval_runtime": 10.2767, | |
| "eval_samples_per_second": 166.591, | |
| "eval_steps_per_second": 10.412, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 6.042780748663102, | |
| "grad_norm": 1.1055293083190918, | |
| "learning_rate": 0.001981283422459893, | |
| "loss": 0.3202, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.096256684491979, | |
| "grad_norm": 1.7265422344207764, | |
| "learning_rate": 0.0019545454545454545, | |
| "loss": 0.2973, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.149732620320855, | |
| "grad_norm": 2.0242912769317627, | |
| "learning_rate": 0.001927807486631016, | |
| "loss": 0.302, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.2032085561497325, | |
| "grad_norm": 1.0210644006729126, | |
| "learning_rate": 0.0019010695187165775, | |
| "loss": 0.2785, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.25668449197861, | |
| "grad_norm": 1.5111178159713745, | |
| "learning_rate": 0.001874331550802139, | |
| "loss": 0.2873, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.310160427807487, | |
| "grad_norm": 1.060488224029541, | |
| "learning_rate": 0.0018475935828877006, | |
| "loss": 0.321, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.363636363636363, | |
| "grad_norm": 1.0627189874649048, | |
| "learning_rate": 0.0018208556149732621, | |
| "loss": 0.2682, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.4171122994652405, | |
| "grad_norm": 1.1237576007843018, | |
| "learning_rate": 0.0017941176470588236, | |
| "loss": 0.2383, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.470588235294118, | |
| "grad_norm": 1.6101592779159546, | |
| "learning_rate": 0.001767379679144385, | |
| "loss": 0.3197, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.524064171122995, | |
| "grad_norm": 0.6864691972732544, | |
| "learning_rate": 0.0017406417112299467, | |
| "loss": 0.2307, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.577540106951871, | |
| "grad_norm": 1.339308500289917, | |
| "learning_rate": 0.001713903743315508, | |
| "loss": 0.2534, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 6.6310160427807485, | |
| "grad_norm": 1.3319642543792725, | |
| "learning_rate": 0.0016871657754010698, | |
| "loss": 0.32, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.684491978609626, | |
| "grad_norm": 1.4089816808700562, | |
| "learning_rate": 0.001660427807486631, | |
| "loss": 0.285, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.737967914438503, | |
| "grad_norm": 1.212084174156189, | |
| "learning_rate": 0.0016336898395721924, | |
| "loss": 0.2217, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.791443850267379, | |
| "grad_norm": 1.6609482765197754, | |
| "learning_rate": 0.0016069518716577541, | |
| "loss": 0.2952, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 6.8449197860962565, | |
| "grad_norm": 1.060892105102539, | |
| "learning_rate": 0.0015802139037433154, | |
| "loss": 0.2524, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 6.898395721925134, | |
| "grad_norm": 1.3365124464035034, | |
| "learning_rate": 0.001553475935828877, | |
| "loss": 0.2694, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 6.951871657754011, | |
| "grad_norm": 1.1521918773651123, | |
| "learning_rate": 0.0015267379679144385, | |
| "loss": 0.3088, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9532710280373832, | |
| "eval_f1": 0.9461125894090557, | |
| "eval_loss": 0.11792106181383133, | |
| "eval_precision": 0.9426583892398479, | |
| "eval_recall": 0.952515495389921, | |
| "eval_runtime": 10.3853, | |
| "eval_samples_per_second": 164.849, | |
| "eval_steps_per_second": 10.303, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 7.005347593582887, | |
| "grad_norm": 0.8682220578193665, | |
| "learning_rate": 0.0015, | |
| "loss": 0.2627, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 2.279827356338501, | |
| "learning_rate": 0.0014732620320855616, | |
| "loss": 0.2796, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.112299465240642, | |
| "grad_norm": 1.3697049617767334, | |
| "learning_rate": 0.001446524064171123, | |
| "loss": 0.2369, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.165775401069519, | |
| "grad_norm": 0.8857790231704712, | |
| "learning_rate": 0.0014197860962566844, | |
| "loss": 0.2648, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.219251336898395, | |
| "grad_norm": 2.053224802017212, | |
| "learning_rate": 0.0013930481283422461, | |
| "loss": 0.212, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 1.619578242301941, | |
| "learning_rate": 0.0013663101604278075, | |
| "loss": 0.2229, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.32620320855615, | |
| "grad_norm": 1.3765966892242432, | |
| "learning_rate": 0.0013395721925133692, | |
| "loss": 0.2311, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.379679144385027, | |
| "grad_norm": 1.2967066764831543, | |
| "learning_rate": 0.0013128342245989305, | |
| "loss": 0.2402, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.433155080213904, | |
| "grad_norm": 1.2961163520812988, | |
| "learning_rate": 0.0012860962566844918, | |
| "loss": 0.2318, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 7.4866310160427805, | |
| "grad_norm": 1.6240290403366089, | |
| "learning_rate": 0.0012593582887700536, | |
| "loss": 0.2669, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.540106951871658, | |
| "grad_norm": 1.1457808017730713, | |
| "learning_rate": 0.0012326203208556149, | |
| "loss": 0.2887, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 7.593582887700535, | |
| "grad_norm": 1.303931474685669, | |
| "learning_rate": 0.0012058823529411764, | |
| "loss": 0.2862, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 7.647058823529412, | |
| "grad_norm": 0.9429693222045898, | |
| "learning_rate": 0.001179144385026738, | |
| "loss": 0.2282, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 7.7005347593582885, | |
| "grad_norm": 1.349269986152649, | |
| "learning_rate": 0.0011524064171122995, | |
| "loss": 0.2414, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 7.754010695187166, | |
| "grad_norm": 1.185160517692566, | |
| "learning_rate": 0.001125668449197861, | |
| "loss": 0.219, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.807486631016043, | |
| "grad_norm": 1.5935460329055786, | |
| "learning_rate": 0.0010989304812834225, | |
| "loss": 0.2109, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 7.86096256684492, | |
| "grad_norm": 1.4563795328140259, | |
| "learning_rate": 0.001072192513368984, | |
| "loss": 0.2943, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 7.9144385026737964, | |
| "grad_norm": 1.2570650577545166, | |
| "learning_rate": 0.0010454545454545454, | |
| "loss": 0.2275, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 7.967914438502674, | |
| "grad_norm": 0.6930679082870483, | |
| "learning_rate": 0.001018716577540107, | |
| "loss": 0.2129, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9637850467289719, | |
| "eval_f1": 0.9610548371575116, | |
| "eval_loss": 0.09920904040336609, | |
| "eval_precision": 0.9569323583080014, | |
| "eval_recall": 0.9673920345290172, | |
| "eval_runtime": 10.543, | |
| "eval_samples_per_second": 162.382, | |
| "eval_steps_per_second": 10.149, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 8.02139037433155, | |
| "grad_norm": 1.4018137454986572, | |
| "learning_rate": 0.0009919786096256684, | |
| "loss": 0.2638, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.074866310160427, | |
| "grad_norm": 1.2713522911071777, | |
| "learning_rate": 0.00096524064171123, | |
| "loss": 0.2099, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 8.128342245989305, | |
| "grad_norm": 1.004296064376831, | |
| "learning_rate": 0.0009385026737967915, | |
| "loss": 0.1801, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.181818181818182, | |
| "grad_norm": 0.7041844129562378, | |
| "learning_rate": 0.0009117647058823529, | |
| "loss": 0.1829, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 8.235294117647058, | |
| "grad_norm": 1.3204301595687866, | |
| "learning_rate": 0.0008850267379679144, | |
| "loss": 0.2444, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.288770053475936, | |
| "grad_norm": 1.261974573135376, | |
| "learning_rate": 0.000858288770053476, | |
| "loss": 0.2431, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.342245989304812, | |
| "grad_norm": 0.9899649024009705, | |
| "learning_rate": 0.0008315508021390375, | |
| "loss": 0.1808, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 8.39572192513369, | |
| "grad_norm": 1.150225281715393, | |
| "learning_rate": 0.0008048128342245989, | |
| "loss": 0.2048, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 8.449197860962567, | |
| "grad_norm": 0.9454184770584106, | |
| "learning_rate": 0.0007780748663101605, | |
| "loss": 0.1919, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 8.502673796791443, | |
| "grad_norm": 1.26669442653656, | |
| "learning_rate": 0.000751336898395722, | |
| "loss": 0.1837, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 8.556149732620321, | |
| "grad_norm": 0.8547130823135376, | |
| "learning_rate": 0.0007245989304812835, | |
| "loss": 0.1774, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.609625668449198, | |
| "grad_norm": 1.8781049251556396, | |
| "learning_rate": 0.000697860962566845, | |
| "loss": 0.2202, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 8.663101604278076, | |
| "grad_norm": 0.7876987457275391, | |
| "learning_rate": 0.0006711229946524064, | |
| "loss": 0.1781, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 8.716577540106952, | |
| "grad_norm": 1.2137806415557861, | |
| "learning_rate": 0.0006443850267379679, | |
| "loss": 0.1722, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 8.770053475935828, | |
| "grad_norm": 1.6328903436660767, | |
| "learning_rate": 0.0006176470588235294, | |
| "loss": 0.2085, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 0.9435901641845703, | |
| "learning_rate": 0.0005909090909090909, | |
| "loss": 0.2335, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 8.877005347593583, | |
| "grad_norm": 1.1905876398086548, | |
| "learning_rate": 0.0005641711229946525, | |
| "loss": 0.2387, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 8.93048128342246, | |
| "grad_norm": 0.8758776783943176, | |
| "learning_rate": 0.0005374331550802139, | |
| "loss": 0.2265, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 8.983957219251337, | |
| "grad_norm": 1.3745719194412231, | |
| "learning_rate": 0.0005106951871657754, | |
| "loss": 0.2049, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.967873831775701, | |
| "eval_f1": 0.9651132770824573, | |
| "eval_loss": 0.08469934016466141, | |
| "eval_precision": 0.9626628225985181, | |
| "eval_recall": 0.9683070024371949, | |
| "eval_runtime": 10.3829, | |
| "eval_samples_per_second": 164.887, | |
| "eval_steps_per_second": 10.305, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 9.037433155080214, | |
| "grad_norm": 0.9230683445930481, | |
| "learning_rate": 0.0004839572192513369, | |
| "loss": 0.1654, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 0.8362302184104919, | |
| "learning_rate": 0.0004572192513368984, | |
| "loss": 0.1918, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.144385026737968, | |
| "grad_norm": 1.3025470972061157, | |
| "learning_rate": 0.0004304812834224599, | |
| "loss": 0.1497, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.197860962566844, | |
| "grad_norm": 0.8339858055114746, | |
| "learning_rate": 0.00040374331550802143, | |
| "loss": 0.196, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 9.251336898395722, | |
| "grad_norm": 1.3273382186889648, | |
| "learning_rate": 0.00037700534759358285, | |
| "loss": 0.1912, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 9.304812834224599, | |
| "grad_norm": 0.5822441577911377, | |
| "learning_rate": 0.0003502673796791444, | |
| "loss": 0.1452, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 9.358288770053475, | |
| "grad_norm": 0.8451639413833618, | |
| "learning_rate": 0.0003235294117647059, | |
| "loss": 0.1877, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.0270066261291504, | |
| "learning_rate": 0.0002967914438502674, | |
| "loss": 0.1964, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.46524064171123, | |
| "grad_norm": 1.0621460676193237, | |
| "learning_rate": 0.00027005347593582886, | |
| "loss": 0.2015, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 9.518716577540108, | |
| "grad_norm": 0.9587564468383789, | |
| "learning_rate": 0.00024331550802139036, | |
| "loss": 0.1962, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 9.572192513368984, | |
| "grad_norm": 0.719536304473877, | |
| "learning_rate": 0.00021657754010695186, | |
| "loss": 0.1389, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 9.62566844919786, | |
| "grad_norm": 0.89113450050354, | |
| "learning_rate": 0.0001898395721925134, | |
| "loss": 0.1783, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.679144385026738, | |
| "grad_norm": 0.8831282258033752, | |
| "learning_rate": 0.0001631016042780749, | |
| "loss": 0.1871, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 9.732620320855615, | |
| "grad_norm": 0.6015557646751404, | |
| "learning_rate": 0.00013636363636363637, | |
| "loss": 0.1414, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 9.786096256684491, | |
| "grad_norm": 1.1582796573638916, | |
| "learning_rate": 0.00010962566844919787, | |
| "loss": 0.2408, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 9.83957219251337, | |
| "grad_norm": 0.7856789231300354, | |
| "learning_rate": 8.288770053475936e-05, | |
| "loss": 0.145, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 9.893048128342246, | |
| "grad_norm": 1.1010181903839111, | |
| "learning_rate": 5.614973262032086e-05, | |
| "loss": 0.1758, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 9.946524064171124, | |
| "grad_norm": 0.7676904797554016, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.1683, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.4464507102966309, | |
| "learning_rate": 2.6737967914438504e-06, | |
| "loss": 0.2007, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9707943925233645, | |
| "eval_f1": 0.9697517307733657, | |
| "eval_loss": 0.07853860408067703, | |
| "eval_precision": 0.9668363312878312, | |
| "eval_recall": 0.9737482240908748, | |
| "eval_runtime": 10.3924, | |
| "eval_samples_per_second": 164.735, | |
| "eval_steps_per_second": 10.296, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1870, | |
| "total_flos": 9.328175742872125e+18, | |
| "train_loss": 0.3662890907277398, | |
| "train_runtime": 1600.7009, | |
| "train_samples_per_second": 74.711, | |
| "train_steps_per_second": 1.168 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1870, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 9.328175742872125e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |