| { | |
| "best_metric": 0.8791124713083397, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-aoe-hyper/run-5/checkpoint-654", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 654, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03058103975535168, | |
| "grad_norm": 1.6833314895629883, | |
| "learning_rate": 1.1436264471337766e-05, | |
| "loss": 0.6513, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06116207951070336, | |
| "grad_norm": 1.33408784866333, | |
| "learning_rate": 1.1258682724888423e-05, | |
| "loss": 0.5141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": 2.2130067348480225, | |
| "learning_rate": 1.1081100978439079e-05, | |
| "loss": 0.4869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12232415902140673, | |
| "grad_norm": 2.5281882286071777, | |
| "learning_rate": 1.0903519231989732e-05, | |
| "loss": 0.4489, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1529051987767584, | |
| "grad_norm": 1.898231029510498, | |
| "learning_rate": 1.072593748554039e-05, | |
| "loss": 0.4336, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "grad_norm": 3.3090434074401855, | |
| "learning_rate": 1.0548355739091045e-05, | |
| "loss": 0.4298, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21406727828746178, | |
| "grad_norm": 2.3698971271514893, | |
| "learning_rate": 1.03707739926417e-05, | |
| "loss": 0.4439, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24464831804281345, | |
| "grad_norm": 4.222820281982422, | |
| "learning_rate": 1.0193192246192358e-05, | |
| "loss": 0.4223, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27522935779816515, | |
| "grad_norm": 1.8396034240722656, | |
| "learning_rate": 1.0015610499743013e-05, | |
| "loss": 0.3714, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3058103975535168, | |
| "grad_norm": 8.237236976623535, | |
| "learning_rate": 9.838028753293667e-06, | |
| "loss": 0.4295, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3363914373088685, | |
| "grad_norm": 5.705390453338623, | |
| "learning_rate": 9.660447006844324e-06, | |
| "loss": 0.3417, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 6.750524520874023, | |
| "learning_rate": 9.48286526039498e-06, | |
| "loss": 0.3364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39755351681957185, | |
| "grad_norm": 5.750469207763672, | |
| "learning_rate": 9.305283513945636e-06, | |
| "loss": 0.2918, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42813455657492355, | |
| "grad_norm": 3.8485758304595947, | |
| "learning_rate": 9.127701767496293e-06, | |
| "loss": 0.3611, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "grad_norm": 5.908198356628418, | |
| "learning_rate": 8.950120021046948e-06, | |
| "loss": 0.3353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4892966360856269, | |
| "grad_norm": 7.6231184005737305, | |
| "learning_rate": 8.772538274597602e-06, | |
| "loss": 0.3719, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5198776758409785, | |
| "grad_norm": 6.425923824310303, | |
| "learning_rate": 8.59495652814826e-06, | |
| "loss": 0.3461, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "grad_norm": 4.749773025512695, | |
| "learning_rate": 8.417374781698915e-06, | |
| "loss": 0.3298, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.581039755351682, | |
| "grad_norm": 3.624875783920288, | |
| "learning_rate": 8.23979303524957e-06, | |
| "loss": 0.3178, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6116207951070336, | |
| "grad_norm": 2.93977952003479, | |
| "learning_rate": 8.062211288800228e-06, | |
| "loss": 0.337, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6422018348623854, | |
| "grad_norm": 9.312886238098145, | |
| "learning_rate": 7.884629542350883e-06, | |
| "loss": 0.3139, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.672782874617737, | |
| "grad_norm": 4.528453350067139, | |
| "learning_rate": 7.707047795901539e-06, | |
| "loss": 0.2572, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7033639143730887, | |
| "grad_norm": 12.262564659118652, | |
| "learning_rate": 7.529466049452193e-06, | |
| "loss": 0.2924, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 4.399960517883301, | |
| "learning_rate": 7.35188430300285e-06, | |
| "loss": 0.285, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.764525993883792, | |
| "grad_norm": 2.8317487239837646, | |
| "learning_rate": 7.174302556553505e-06, | |
| "loss": 0.2616, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7951070336391437, | |
| "grad_norm": 14.594043731689453, | |
| "learning_rate": 6.9967208101041615e-06, | |
| "loss": 0.3415, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8256880733944955, | |
| "grad_norm": 3.254194736480713, | |
| "learning_rate": 6.819139063654818e-06, | |
| "loss": 0.2571, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8562691131498471, | |
| "grad_norm": 3.7313687801361084, | |
| "learning_rate": 6.641557317205473e-06, | |
| "loss": 0.2529, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8868501529051988, | |
| "grad_norm": 5.240476608276367, | |
| "learning_rate": 6.463975570756128e-06, | |
| "loss": 0.3422, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 4.861540794372559, | |
| "learning_rate": 6.2863938243067844e-06, | |
| "loss": 0.3243, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9480122324159022, | |
| "grad_norm": 8.03921890258789, | |
| "learning_rate": 6.10881207785744e-06, | |
| "loss": 0.3244, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9785932721712538, | |
| "grad_norm": 3.031550645828247, | |
| "learning_rate": 5.931230331408096e-06, | |
| "loss": 0.2426, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8768171384850804, | |
| "eval_f1": 0.7480438184663537, | |
| "eval_loss": 0.29354020953178406, | |
| "eval_precision": 0.7308868501529052, | |
| "eval_recall": 0.7660256410256411, | |
| "eval_runtime": 4.9072, | |
| "eval_samples_per_second": 266.342, | |
| "eval_steps_per_second": 16.71, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.0091743119266054, | |
| "grad_norm": 12.193892478942871, | |
| "learning_rate": 5.753648584958752e-06, | |
| "loss": 0.3332, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.039755351681957, | |
| "grad_norm": 5.682682037353516, | |
| "learning_rate": 5.576066838509407e-06, | |
| "loss": 0.2385, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.070336391437309, | |
| "grad_norm": 18.050596237182617, | |
| "learning_rate": 5.398485092060064e-06, | |
| "loss": 0.2123, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "grad_norm": 5.985245704650879, | |
| "learning_rate": 5.220903345610719e-06, | |
| "loss": 0.1935, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1314984709480123, | |
| "grad_norm": 3.5328218936920166, | |
| "learning_rate": 5.043321599161375e-06, | |
| "loss": 0.268, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.162079510703364, | |
| "grad_norm": 4.972208023071289, | |
| "learning_rate": 4.865739852712031e-06, | |
| "loss": 0.1793, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1926605504587156, | |
| "grad_norm": 6.088878154754639, | |
| "learning_rate": 4.688158106262687e-06, | |
| "loss": 0.1993, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 4.503061294555664, | |
| "learning_rate": 4.510576359813342e-06, | |
| "loss": 0.2092, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2538226299694188, | |
| "grad_norm": 4.567380428314209, | |
| "learning_rate": 4.3329946133639985e-06, | |
| "loss": 0.2834, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2844036697247707, | |
| "grad_norm": 6.611799716949463, | |
| "learning_rate": 4.155412866914654e-06, | |
| "loss": 0.2832, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.3149847094801224, | |
| "grad_norm": 8.199454307556152, | |
| "learning_rate": 3.97783112046531e-06, | |
| "loss": 0.3619, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.345565749235474, | |
| "grad_norm": 10.987822532653809, | |
| "learning_rate": 3.800249374015966e-06, | |
| "loss": 0.3282, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3761467889908257, | |
| "grad_norm": 9.002391815185547, | |
| "learning_rate": 3.622667627566622e-06, | |
| "loss": 0.1932, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.4067278287461773, | |
| "grad_norm": 9.500117301940918, | |
| "learning_rate": 3.445085881117277e-06, | |
| "loss": 0.3071, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.4373088685015292, | |
| "grad_norm": 3.1432082653045654, | |
| "learning_rate": 3.2675041346679334e-06, | |
| "loss": 0.2714, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 5.107339859008789, | |
| "learning_rate": 3.0899223882185893e-06, | |
| "loss": 0.2005, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.4984709480122325, | |
| "grad_norm": 5.789766311645508, | |
| "learning_rate": 2.9123406417692444e-06, | |
| "loss": 0.2696, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.529051987767584, | |
| "grad_norm": 6.676187515258789, | |
| "learning_rate": 2.7347588953199003e-06, | |
| "loss": 0.2581, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5596330275229358, | |
| "grad_norm": 9.344066619873047, | |
| "learning_rate": 2.5571771488705567e-06, | |
| "loss": 0.2441, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5902140672782874, | |
| "grad_norm": 5.086206912994385, | |
| "learning_rate": 2.3795954024212122e-06, | |
| "loss": 0.2883, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.620795107033639, | |
| "grad_norm": 4.854761123657227, | |
| "learning_rate": 2.2020136559718677e-06, | |
| "loss": 0.3288, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6513761467889907, | |
| "grad_norm": 5.0419158935546875, | |
| "learning_rate": 2.024431909522524e-06, | |
| "loss": 0.1916, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6819571865443423, | |
| "grad_norm": 3.6190755367279053, | |
| "learning_rate": 1.8468501630731796e-06, | |
| "loss": 0.2405, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.7125382262996942, | |
| "grad_norm": 2.2586376667022705, | |
| "learning_rate": 1.6692684166238354e-06, | |
| "loss": 0.2336, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7431192660550459, | |
| "grad_norm": 0.9094193577766418, | |
| "learning_rate": 1.4916866701744913e-06, | |
| "loss": 0.3062, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7737003058103975, | |
| "grad_norm": 5.636134147644043, | |
| "learning_rate": 1.314104923725147e-06, | |
| "loss": 0.2616, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.8042813455657494, | |
| "grad_norm": 8.59340763092041, | |
| "learning_rate": 1.1365231772758028e-06, | |
| "loss": 0.2395, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 6.957756042480469, | |
| "learning_rate": 9.589414308264587e-07, | |
| "loss": 0.2656, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8654434250764527, | |
| "grad_norm": 6.419522285461426, | |
| "learning_rate": 7.813596843771144e-07, | |
| "loss": 0.3393, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8960244648318043, | |
| "grad_norm": 2.6836931705474854, | |
| "learning_rate": 6.037779379277703e-07, | |
| "loss": 0.2229, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.926605504587156, | |
| "grad_norm": 5.273196697235107, | |
| "learning_rate": 4.261961914784261e-07, | |
| "loss": 0.2025, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9571865443425076, | |
| "grad_norm": 5.824622631072998, | |
| "learning_rate": 2.4861444502908185e-07, | |
| "loss": 0.2995, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9877675840978593, | |
| "grad_norm": 18.051441192626953, | |
| "learning_rate": 7.103269857973767e-08, | |
| "loss": 0.303, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8791124713083397, | |
| "eval_f1": 0.7554179566563467, | |
| "eval_loss": 0.2987494468688965, | |
| "eval_precision": 0.7305389221556886, | |
| "eval_recall": 0.782051282051282, | |
| "eval_runtime": 4.9837, | |
| "eval_samples_per_second": 262.254, | |
| "eval_steps_per_second": 16.454, | |
| "step": 654 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 654, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1377131076427776.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.161384621778711e-05, | |
| "num_train_epochs": 2, | |
| "per_device_train_batch_size": 16, | |
| "seed": 28 | |
| } | |
| } | |