| { | |
| "best_metric": 0.9916765755053508, | |
| "best_model_checkpoint": "/home/user/Desktop/ViT/MalImg/vit_finetuned/checkpoint-2271", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 3785, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06605019815059446, | |
| "grad_norm": 5.9336066246032715, | |
| "learning_rate": 1.9735799207397622e-05, | |
| "loss": 1.3733, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13210039630118892, | |
| "grad_norm": 4.252811908721924, | |
| "learning_rate": 1.9471598414795246e-05, | |
| "loss": 0.4773, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19815059445178335, | |
| "grad_norm": 1.3301128149032593, | |
| "learning_rate": 1.9207397622192866e-05, | |
| "loss": 0.2271, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26420079260237783, | |
| "grad_norm": 0.1664501279592514, | |
| "learning_rate": 1.894319682959049e-05, | |
| "loss": 0.133, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33025099075297226, | |
| "grad_norm": 13.456730842590332, | |
| "learning_rate": 1.8678996036988114e-05, | |
| "loss": 0.1293, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3963011889035667, | |
| "grad_norm": 0.6937832832336426, | |
| "learning_rate": 1.8414795244385734e-05, | |
| "loss": 0.0888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4623513870541612, | |
| "grad_norm": 0.14598596096038818, | |
| "learning_rate": 1.8150594451783358e-05, | |
| "loss": 0.0692, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5284015852047557, | |
| "grad_norm": 0.15269458293914795, | |
| "learning_rate": 1.7886393659180978e-05, | |
| "loss": 0.0578, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5944517833553501, | |
| "grad_norm": 0.07667677849531174, | |
| "learning_rate": 1.76221928665786e-05, | |
| "loss": 0.0573, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6605019815059445, | |
| "grad_norm": 0.3432880640029907, | |
| "learning_rate": 1.7357992073976226e-05, | |
| "loss": 0.0464, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.726552179656539, | |
| "grad_norm": 6.246374130249023, | |
| "learning_rate": 1.7093791281373846e-05, | |
| "loss": 0.0523, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7926023778071334, | |
| "grad_norm": 0.09200052171945572, | |
| "learning_rate": 1.6829590488771467e-05, | |
| "loss": 0.071, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8586525759577279, | |
| "grad_norm": 0.8642477989196777, | |
| "learning_rate": 1.656538969616909e-05, | |
| "loss": 0.0382, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9247027741083224, | |
| "grad_norm": 0.06948922574520111, | |
| "learning_rate": 1.630118890356671e-05, | |
| "loss": 0.0275, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.9907529722589168, | |
| "grad_norm": 0.15016400814056396, | |
| "learning_rate": 1.6036988110964335e-05, | |
| "loss": 0.0471, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9797859690844233, | |
| "eval_loss": 0.052647557109594345, | |
| "eval_runtime": 49.7302, | |
| "eval_samples_per_second": 16.911, | |
| "eval_steps_per_second": 4.243, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.0568031704095113, | |
| "grad_norm": 0.7207925319671631, | |
| "learning_rate": 1.5772787318361958e-05, | |
| "loss": 0.0358, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1228533685601056, | |
| "grad_norm": 0.022695371881127357, | |
| "learning_rate": 1.550858652575958e-05, | |
| "loss": 0.0142, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.1889035667107002, | |
| "grad_norm": 0.01373555138707161, | |
| "learning_rate": 1.52443857331572e-05, | |
| "loss": 0.0678, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2549537648612945, | |
| "grad_norm": 0.02284625917673111, | |
| "learning_rate": 1.4980184940554823e-05, | |
| "loss": 0.0174, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.321003963011889, | |
| "grad_norm": 0.03625660389661789, | |
| "learning_rate": 1.4715984147952445e-05, | |
| "loss": 0.0198, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.3870541611624834, | |
| "grad_norm": 8.791983604431152, | |
| "learning_rate": 1.4451783355350067e-05, | |
| "loss": 0.0181, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.453104359313078, | |
| "grad_norm": 10.266106605529785, | |
| "learning_rate": 1.418758256274769e-05, | |
| "loss": 0.0166, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.5191545574636725, | |
| "grad_norm": 0.08618652075529099, | |
| "learning_rate": 1.3923381770145313e-05, | |
| "loss": 0.0216, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.5852047556142668, | |
| "grad_norm": 0.020607857033610344, | |
| "learning_rate": 1.3659180977542933e-05, | |
| "loss": 0.0166, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6512549537648613, | |
| "grad_norm": 0.008363209664821625, | |
| "learning_rate": 1.3394980184940555e-05, | |
| "loss": 0.011, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.7173051519154559, | |
| "grad_norm": 8.230094909667969, | |
| "learning_rate": 1.3130779392338177e-05, | |
| "loss": 0.0391, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.7833553500660502, | |
| "grad_norm": 0.2879900634288788, | |
| "learning_rate": 1.28665785997358e-05, | |
| "loss": 0.0281, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.8494055482166445, | |
| "grad_norm": 0.6117168068885803, | |
| "learning_rate": 1.2602377807133423e-05, | |
| "loss": 0.0275, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9154557463672393, | |
| "grad_norm": 0.04467739537358284, | |
| "learning_rate": 1.2338177014531045e-05, | |
| "loss": 0.0301, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.9815059445178336, | |
| "grad_norm": 0.017908189445734024, | |
| "learning_rate": 1.2073976221928667e-05, | |
| "loss": 0.0178, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9881093935790726, | |
| "eval_loss": 0.03636582940816879, | |
| "eval_runtime": 47.4743, | |
| "eval_samples_per_second": 17.715, | |
| "eval_steps_per_second": 4.445, | |
| "step": 1514 | |
| }, | |
| { | |
| "epoch": 2.047556142668428, | |
| "grad_norm": 0.036849573254585266, | |
| "learning_rate": 1.180977542932629e-05, | |
| "loss": 0.0187, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.1136063408190227, | |
| "grad_norm": 0.04460464045405388, | |
| "learning_rate": 1.1545574636723912e-05, | |
| "loss": 0.0067, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.179656538969617, | |
| "grad_norm": 0.009667308069765568, | |
| "learning_rate": 1.1281373844121532e-05, | |
| "loss": 0.0238, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.2457067371202113, | |
| "grad_norm": 0.03686352074146271, | |
| "learning_rate": 1.1017173051519154e-05, | |
| "loss": 0.0022, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.3117569352708056, | |
| "grad_norm": 0.031481340527534485, | |
| "learning_rate": 1.0752972258916778e-05, | |
| "loss": 0.0026, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.3778071334214004, | |
| "grad_norm": 0.011794793419539928, | |
| "learning_rate": 1.04887714663144e-05, | |
| "loss": 0.0116, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4438573315719947, | |
| "grad_norm": 0.010463342070579529, | |
| "learning_rate": 1.0224570673712022e-05, | |
| "loss": 0.001, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.509907529722589, | |
| "grad_norm": 0.015383273363113403, | |
| "learning_rate": 9.960369881109644e-06, | |
| "loss": 0.0228, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.5759577278731838, | |
| "grad_norm": 0.013397900387644768, | |
| "learning_rate": 9.696169088507266e-06, | |
| "loss": 0.0089, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.642007926023778, | |
| "grad_norm": 0.00911177322268486, | |
| "learning_rate": 9.431968295904888e-06, | |
| "loss": 0.02, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.7080581241743724, | |
| "grad_norm": 0.02440851554274559, | |
| "learning_rate": 9.16776750330251e-06, | |
| "loss": 0.0013, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.7741083223249667, | |
| "grad_norm": 0.009484563954174519, | |
| "learning_rate": 8.903566710700134e-06, | |
| "loss": 0.0194, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8401585204755615, | |
| "grad_norm": 0.006213477812707424, | |
| "learning_rate": 8.639365918097754e-06, | |
| "loss": 0.0029, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.906208718626156, | |
| "grad_norm": 0.0294838547706604, | |
| "learning_rate": 8.375165125495377e-06, | |
| "loss": 0.0155, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.9722589167767506, | |
| "grad_norm": 0.004683547653257847, | |
| "learning_rate": 8.110964332893e-06, | |
| "loss": 0.0012, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9916765755053508, | |
| "eval_loss": 0.03940876945853233, | |
| "eval_runtime": 46.7804, | |
| "eval_samples_per_second": 17.978, | |
| "eval_steps_per_second": 4.51, | |
| "step": 2271 | |
| }, | |
| { | |
| "epoch": 3.038309114927345, | |
| "grad_norm": 0.012384450994431973, | |
| "learning_rate": 7.846763540290622e-06, | |
| "loss": 0.0023, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.104359313077939, | |
| "grad_norm": 0.01143250335007906, | |
| "learning_rate": 7.582562747688244e-06, | |
| "loss": 0.0016, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.1704095112285335, | |
| "grad_norm": 0.011226821690797806, | |
| "learning_rate": 7.318361955085866e-06, | |
| "loss": 0.0015, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.2364597093791283, | |
| "grad_norm": 0.1874089390039444, | |
| "learning_rate": 7.054161162483489e-06, | |
| "loss": 0.0048, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.3025099075297226, | |
| "grad_norm": 0.005090535152703524, | |
| "learning_rate": 6.78996036988111e-06, | |
| "loss": 0.0006, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.368560105680317, | |
| "grad_norm": 5.946714401245117, | |
| "learning_rate": 6.525759577278732e-06, | |
| "loss": 0.0039, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 3.4346103038309117, | |
| "grad_norm": 0.015056404285132885, | |
| "learning_rate": 6.261558784676355e-06, | |
| "loss": 0.0039, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.500660501981506, | |
| "grad_norm": 0.09337496757507324, | |
| "learning_rate": 5.997357992073977e-06, | |
| "loss": 0.0008, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.5667107001321003, | |
| "grad_norm": 0.02832830883562565, | |
| "learning_rate": 5.733157199471598e-06, | |
| "loss": 0.0017, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.6327608982826947, | |
| "grad_norm": 0.003939814865589142, | |
| "learning_rate": 5.468956406869221e-06, | |
| "loss": 0.0006, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.6988110964332894, | |
| "grad_norm": 0.009257273748517036, | |
| "learning_rate": 5.204755614266843e-06, | |
| "loss": 0.01, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.7648612945838837, | |
| "grad_norm": 0.03735257685184479, | |
| "learning_rate": 4.940554821664465e-06, | |
| "loss": 0.0007, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.830911492734478, | |
| "grad_norm": 0.013488363474607468, | |
| "learning_rate": 4.676354029062087e-06, | |
| "loss": 0.0064, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.896961690885073, | |
| "grad_norm": 0.03222118690609932, | |
| "learning_rate": 4.412153236459709e-06, | |
| "loss": 0.0024, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.963011889035667, | |
| "grad_norm": 0.007759902160614729, | |
| "learning_rate": 4.147952443857332e-06, | |
| "loss": 0.0007, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9916765755053508, | |
| "eval_loss": 0.030070677399635315, | |
| "eval_runtime": 47.0985, | |
| "eval_samples_per_second": 17.856, | |
| "eval_steps_per_second": 4.48, | |
| "step": 3028 | |
| }, | |
| { | |
| "epoch": 4.0290620871862615, | |
| "grad_norm": 0.005042864475399256, | |
| "learning_rate": 3.8837516512549536e-06, | |
| "loss": 0.0004, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.095112285336856, | |
| "grad_norm": 0.020858343690633774, | |
| "learning_rate": 3.619550858652576e-06, | |
| "loss": 0.0004, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.16116248348745, | |
| "grad_norm": 0.006172764115035534, | |
| "learning_rate": 3.3553500660501986e-06, | |
| "loss": 0.0007, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 4.227212681638045, | |
| "grad_norm": 0.0033390983007848263, | |
| "learning_rate": 3.0911492734478207e-06, | |
| "loss": 0.0009, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.29326287978864, | |
| "grad_norm": 0.015372613444924355, | |
| "learning_rate": 2.8269484808454427e-06, | |
| "loss": 0.0006, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 4.359313077939234, | |
| "grad_norm": 0.006469820160418749, | |
| "learning_rate": 2.5627476882430652e-06, | |
| "loss": 0.0004, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.425363276089828, | |
| "grad_norm": 0.011778703890740871, | |
| "learning_rate": 2.298546895640687e-06, | |
| "loss": 0.0004, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 4.491413474240423, | |
| "grad_norm": 0.006380158942192793, | |
| "learning_rate": 2.0343461030383094e-06, | |
| "loss": 0.0004, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.557463672391017, | |
| "grad_norm": 0.0013477399479597807, | |
| "learning_rate": 1.7701453104359315e-06, | |
| "loss": 0.0004, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 4.623513870541611, | |
| "grad_norm": 0.006167972926050425, | |
| "learning_rate": 1.5059445178335536e-06, | |
| "loss": 0.0042, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.689564068692206, | |
| "grad_norm": 0.013963188044726849, | |
| "learning_rate": 1.2417437252311758e-06, | |
| "loss": 0.0008, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 4.755614266842801, | |
| "grad_norm": 0.027660081163048744, | |
| "learning_rate": 9.77542932628798e-07, | |
| "loss": 0.0004, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.821664464993395, | |
| "grad_norm": 0.004752615932375193, | |
| "learning_rate": 7.133421400264201e-07, | |
| "loss": 0.0004, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 4.887714663143989, | |
| "grad_norm": 0.009864550083875656, | |
| "learning_rate": 4.4914134742404235e-07, | |
| "loss": 0.0004, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 4.953764861294584, | |
| "grad_norm": 0.020459244027733803, | |
| "learning_rate": 1.849405548216645e-07, | |
| "loss": 0.0003, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9892984542211652, | |
| "eval_loss": 0.035547275096178055, | |
| "eval_runtime": 47.2255, | |
| "eval_samples_per_second": 17.808, | |
| "eval_steps_per_second": 4.468, | |
| "step": 3785 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 3785, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 2.9313511964758426e+18, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |