| { | |
| "best_metric": 0.9787695402282305, | |
| "best_model_checkpoint": "./outputs/convnextv2-nano-22k-384-boulderspot-vN/checkpoint-609", | |
| "epoch": 4.993849938499385, | |
| "eval_steps": 500, | |
| "global_step": 1015, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 28.485111236572266, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 0.8997, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 14.031352043151855, | |
| "learning_rate": 7.84313725490196e-06, | |
| "loss": 0.5136, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 5.687072277069092, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.2446, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 4.7356672286987305, | |
| "learning_rate": 1.568627450980392e-05, | |
| "loss": 0.1611, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 14.7470121383667, | |
| "learning_rate": 1.9607843137254903e-05, | |
| "loss": 0.1333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 9.882979393005371, | |
| "learning_rate": 1.9995698998770955e-05, | |
| "loss": 0.1203, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 2.200605869293213, | |
| "learning_rate": 1.998083609002402e-05, | |
| "loss": 0.0866, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 9.529250144958496, | |
| "learning_rate": 1.995537395500004e-05, | |
| "loss": 0.0825, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 4.56328010559082, | |
| "learning_rate": 1.9919339633410737e-05, | |
| "loss": 0.0757, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 8.917645454406738, | |
| "learning_rate": 1.9872771392183334e-05, | |
| "loss": 0.1336, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 4.956594944000244, | |
| "learning_rate": 1.981571868482269e-05, | |
| "loss": 0.0986, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 9.08370590209961, | |
| "learning_rate": 1.974824209889377e-05, | |
| "loss": 0.0839, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 12.914963722229004, | |
| "learning_rate": 1.9670413291680223e-05, | |
| "loss": 0.0909, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 3.6358766555786133, | |
| "learning_rate": 1.9582314914087344e-05, | |
| "loss": 0.064, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 7.188825607299805, | |
| "learning_rate": 1.9484040522870333e-05, | |
| "loss": 0.0969, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 16.197107315063477, | |
| "learning_rate": 1.9375694481280965e-05, | |
| "loss": 0.0871, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 11.690835952758789, | |
| "learning_rate": 1.9257391848238212e-05, | |
| "loss": 0.0726, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 3.613584280014038, | |
| "learning_rate": 1.9129258256140556e-05, | |
| "loss": 0.0703, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 6.19437313079834, | |
| "learning_rate": 1.8991429777449674e-05, | |
| "loss": 0.0939, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 11.514800071716309, | |
| "learning_rate": 1.884405278018722e-05, | |
| "loss": 0.068, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9707602339181286, | |
| "eval_f1": 0.9722762986965865, | |
| "eval_loss": 0.07348757982254028, | |
| "eval_matthews_correlation": 0.8017394581463343, | |
| "eval_precision": 0.9754056100703739, | |
| "eval_recall": 0.9707602339181286, | |
| "eval_runtime": 5.7659, | |
| "eval_samples_per_second": 118.628, | |
| "eval_steps_per_second": 7.458, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 10.175304412841797, | |
| "learning_rate": 1.8687283772498205e-05, | |
| "loss": 0.0845, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 2.231261968612671, | |
| "learning_rate": 1.852128923644593e-05, | |
| "loss": 0.0563, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 9.75424861907959, | |
| "learning_rate": 1.8346245451215068e-05, | |
| "loss": 0.0791, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 9.436419486999512, | |
| "learning_rate": 1.8162338305910636e-05, | |
| "loss": 0.0751, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 5.413998126983643, | |
| "learning_rate": 1.79697631021516e-05, | |
| "loss": 0.0571, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 10.832895278930664, | |
| "learning_rate": 1.776872434666882e-05, | |
| "loss": 0.0903, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 14.028545379638672, | |
| "learning_rate": 1.7559435534127534e-05, | |
| "loss": 0.0924, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 6.962947368621826, | |
| "learning_rate": 1.7342118920405035e-05, | |
| "loss": 0.1018, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 12.277998924255371, | |
| "learning_rate": 1.7117005286564344e-05, | |
| "loss": 0.0651, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 3.5764994621276855, | |
| "learning_rate": 1.688433369377444e-05, | |
| "loss": 0.0811, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 6.763672351837158, | |
| "learning_rate": 1.6644351229437416e-05, | |
| "loss": 0.0785, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 3.3835597038269043, | |
| "learning_rate": 1.63973127447921e-05, | |
| "loss": 0.0482, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 6.173498153686523, | |
| "learning_rate": 1.6143480584272794e-05, | |
| "loss": 0.0593, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 7.676692008972168, | |
| "learning_rate": 1.5883124306910563e-05, | |
| "loss": 0.0678, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 2.495035171508789, | |
| "learning_rate": 1.5616520400072963e-05, | |
| "loss": 0.0572, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 16.871797561645508, | |
| "learning_rate": 1.5343951985846096e-05, | |
| "loss": 0.0756, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 2.3725368976593018, | |
| "learning_rate": 1.5065708520370943e-05, | |
| "loss": 0.0711, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 12.699337005615234, | |
| "learning_rate": 1.4782085486453155e-05, | |
| "loss": 0.0769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.583565890789032, | |
| "learning_rate": 1.4493384079772815e-05, | |
| "loss": 0.0612, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 6.7856550216674805, | |
| "learning_rate": 1.4199910889027335e-05, | |
| "loss": 0.057, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.9728689575025272, | |
| "eval_loss": 0.06863868236541748, | |
| "eval_matthews_correlation": 0.7943272582319131, | |
| "eval_precision": 0.9738281672617116, | |
| "eval_recall": 0.9722222222222222, | |
| "eval_runtime": 5.5104, | |
| "eval_samples_per_second": 124.128, | |
| "eval_steps_per_second": 7.803, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 2.3636648654937744, | |
| "learning_rate": 1.390197757034721e-05, | |
| "loss": 0.0745, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 21.622703552246094, | |
| "learning_rate": 1.3599900516330382e-05, | |
| "loss": 0.0724, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 11.821688652038574, | |
| "learning_rate": 1.3294000520046666e-05, | |
| "loss": 0.069, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 7.000888347625732, | |
| "learning_rate": 1.2984602434369058e-05, | |
| "loss": 0.0714, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 4.6769256591796875, | |
| "learning_rate": 1.2672034826993716e-05, | |
| "loss": 0.0509, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 1.7955386638641357, | |
| "learning_rate": 1.235662963151493e-05, | |
| "loss": 0.0512, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 22.078067779541016, | |
| "learning_rate": 1.2038721794925689e-05, | |
| "loss": 0.064, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 6.917346000671387, | |
| "learning_rate": 1.1718648921918112e-05, | |
| "loss": 0.0701, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": 8.970315933227539, | |
| "learning_rate": 1.1396750916361526e-05, | |
| "loss": 0.0915, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 13.326787948608398, | |
| "learning_rate": 1.1073369620338928e-05, | |
| "loss": 0.078, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 5.894493103027344, | |
| "learning_rate": 1.074884845112512e-05, | |
| "loss": 0.0636, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 5.459946155548096, | |
| "learning_rate": 1.0423532036492077e-05, | |
| "loss": 0.0711, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 8.83890151977539, | |
| "learning_rate": 1.0097765848728825e-05, | |
| "loss": 0.079, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 2.340186357498169, | |
| "learning_rate": 9.771895837764438e-06, | |
| "loss": 0.0449, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 11.93194580078125, | |
| "learning_rate": 9.446268063783853e-06, | |
| "loss": 0.0794, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 6.638481616973877, | |
| "learning_rate": 9.121228329726563e-06, | |
| "loss": 0.0614, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 5.963674068450928, | |
| "learning_rate": 8.797121814058502e-06, | |
| "loss": 0.0449, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 7.2139506340026855, | |
| "learning_rate": 8.474292704207095e-06, | |
| "loss": 0.0752, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 2.9632108211517334, | |
| "learning_rate": 8.153083831048772e-06, | |
| "loss": 0.0575, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 3.8059580326080322, | |
| "learning_rate": 7.833836304837022e-06, | |
| "loss": 0.046, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9780701754385965, | |
| "eval_f1": 0.9787695402282305, | |
| "eval_loss": 0.05532665178179741, | |
| "eval_matthews_correlation": 0.8420667383515437, | |
| "eval_precision": 0.9800898852068441, | |
| "eval_recall": 0.9780701754385965, | |
| "eval_runtime": 5.6675, | |
| "eval_samples_per_second": 120.688, | |
| "eval_steps_per_second": 7.587, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.808079719543457, | |
| "learning_rate": 7.516889152957744e-06, | |
| "loss": 0.074, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 2.9367547035217285, | |
| "learning_rate": 7.202578959896491e-06, | |
| "loss": 0.0646, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 15.483344078063965, | |
| "learning_rate": 6.891239509799932e-06, | |
| "loss": 0.0835, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "grad_norm": 8.343765258789062, | |
| "learning_rate": 6.583201432011217e-06, | |
| "loss": 0.0609, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 2.9499011039733887, | |
| "learning_rate": 6.278791849955583e-06, | |
| "loss": 0.0669, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "grad_norm": 4.759853363037109, | |
| "learning_rate": 5.978334033749076e-06, | |
| "loss": 0.0434, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 3.5021698474884033, | |
| "learning_rate": 5.682147056899361e-06, | |
| "loss": 0.0389, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "grad_norm": 8.20483112335205, | |
| "learning_rate": 5.390545457463134e-06, | |
| "loss": 0.0512, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "grad_norm": 15.760091781616211, | |
| "learning_rate": 5.103838904019993e-06, | |
| "loss": 0.082, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 5.340324878692627, | |
| "learning_rate": 4.822331866817478e-06, | |
| "loss": 0.0412, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "grad_norm": 2.386610507965088, | |
| "learning_rate": 4.546323294436556e-06, | |
| "loss": 0.0764, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "grad_norm": 2.604590892791748, | |
| "learning_rate": 4.276106296320828e-06, | |
| "loss": 0.0322, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "grad_norm": 2.6730122566223145, | |
| "learning_rate": 4.0119678315067025e-06, | |
| "loss": 0.0532, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 11.014791488647461, | |
| "learning_rate": 3.754188403885013e-06, | |
| "loss": 0.0788, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "grad_norm": 2.279393196105957, | |
| "learning_rate": 3.5030417643177416e-06, | |
| "loss": 0.0465, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "grad_norm": 7.80838680267334, | |
| "learning_rate": 3.258794619926159e-06, | |
| "loss": 0.0441, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "grad_norm": 5.728611946105957, | |
| "learning_rate": 3.021706350859147e-06, | |
| "loss": 0.0476, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 2.4311773777008057, | |
| "learning_rate": 2.792028734842418e-06, | |
| "loss": 0.0421, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "grad_norm": 19.25046730041504, | |
| "learning_rate": 2.5700056798012164e-06, | |
| "loss": 0.0829, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "grad_norm": 16.992164611816406, | |
| "learning_rate": 2.3558729648404065e-06, | |
| "loss": 0.0694, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "grad_norm": 1.1272871494293213, | |
| "learning_rate": 2.1498579898570228e-06, | |
| "loss": 0.0571, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9780701754385965, | |
| "eval_f1": 0.9777344542006784, | |
| "eval_loss": 0.05015131086111069, | |
| "eval_matthews_correlation": 0.8239461397313993, | |
| "eval_precision": 0.9775337669457737, | |
| "eval_recall": 0.9780701754385965, | |
| "eval_runtime": 5.516, | |
| "eval_samples_per_second": 124.003, | |
| "eval_steps_per_second": 7.796, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "grad_norm": 20.361764907836914, | |
| "learning_rate": 1.952179534051183e-06, | |
| "loss": 0.0545, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 12.892123222351074, | |
| "learning_rate": 1.763047523591831e-06, | |
| "loss": 0.0507, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "grad_norm": 4.696685791015625, | |
| "learning_rate": 1.5826628086839968e-06, | |
| "loss": 0.0635, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "grad_norm": 10.167694091796875, | |
| "learning_rate": 1.41121695027438e-06, | |
| "loss": 0.0547, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "grad_norm": 4.277148723602295, | |
| "learning_rate": 1.2488920166217034e-06, | |
| "loss": 0.059, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "grad_norm": 15.234513282775879, | |
| "learning_rate": 1.095860389947928e-06, | |
| "loss": 0.068, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "grad_norm": 5.693934440612793, | |
| "learning_rate": 9.522845833756001e-07, | |
| "loss": 0.0451, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "grad_norm": 10.728283882141113, | |
| "learning_rate": 8.183170683457986e-07, | |
| "loss": 0.0468, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "grad_norm": 8.146360397338867, | |
| "learning_rate": 6.941001126998892e-07, | |
| "loss": 0.0378, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 3.4322080612182617, | |
| "learning_rate": 5.797656295970955e-07, | |
| "loss": 0.0418, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "grad_norm": 3.0174903869628906, | |
| "learning_rate": 4.754350374283001e-07, | |
| "loss": 0.0441, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "grad_norm": 16.416744232177734, | |
| "learning_rate": 3.8121913087483033e-07, | |
| "loss": 0.0495, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "grad_norm": 12.529999732971191, | |
| "learning_rate": 2.972179632491989e-07, | |
| "loss": 0.0747, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "grad_norm": 1.2379523515701294, | |
| "learning_rate": 2.23520740242712e-07, | |
| "loss": 0.0583, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 5.813112735748291, | |
| "learning_rate": 1.602057251927891e-07, | |
| "loss": 0.0612, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "grad_norm": 9.207404136657715, | |
| "learning_rate": 1.0734015597060222e-07, | |
| "loss": 0.0462, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "grad_norm": 10.823348999023438, | |
| "learning_rate": 6.498017357731035e-08, | |
| "loss": 0.0653, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "grad_norm": 1.9045536518096924, | |
| "learning_rate": 3.317076252467133e-08, | |
| "loss": 0.0487, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "grad_norm": 10.43856430053711, | |
| "learning_rate": 1.1945703063402925e-08, | |
| "loss": 0.0449, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "grad_norm": 4.215317249298096, | |
| "learning_rate": 1.327535309979533e-09, | |
| "loss": 0.0491, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9766081871345029, | |
| "eval_f1": 0.9755931812139886, | |
| "eval_loss": 0.04963676258921623, | |
| "eval_matthews_correlation": 0.8055620626992487, | |
| "eval_precision": 0.9756262052467682, | |
| "eval_recall": 0.9766081871345029, | |
| "eval_runtime": 5.7281, | |
| "eval_samples_per_second": 119.41, | |
| "eval_steps_per_second": 7.507, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "step": 1015, | |
| "total_flos": 2.581447650539471e+18, | |
| "train_loss": 0.08238832812591139, | |
| "train_runtime": 705.5168, | |
| "train_samples_per_second": 92.096, | |
| "train_steps_per_second": 1.439 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1015, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.581447650539471e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |