| { | |
| "best_metric": 0.19604873657226562, | |
| "best_model_checkpoint": "trained-params/segformer-b5-miic-tl\\checkpoint-3300", | |
| "epoch": 48.75, | |
| "eval_steps": 100, | |
| "global_step": 3900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5.85e-05, | |
| "loss": 0.6335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy_circuit": 0.3880364398760599, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.24241378903388977, | |
| "eval_iou_circuit": 0.3880364398760599, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.4939822256565094, | |
| "eval_mean_accuracy": 0.3880364398760599, | |
| "eval_mean_iou": 0.19401821993802995, | |
| "eval_overall_accuracy": 0.3880364398760599, | |
| "eval_runtime": 1.8415, | |
| "eval_samples_per_second": 5.43, | |
| "eval_steps_per_second": 2.715, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.55, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy_circuit": 0.8800740846647581, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.763485312461853, | |
| "eval_iou_circuit": 0.8800740846647581, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.3936663568019867, | |
| "eval_mean_accuracy": 0.8800740846647581, | |
| "eval_mean_iou": 0.44003704233237906, | |
| "eval_overall_accuracy": 0.8800740846647581, | |
| "eval_runtime": 1.9006, | |
| "eval_samples_per_second": 5.262, | |
| "eval_steps_per_second": 2.631, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 5.550000000000001e-05, | |
| "loss": 0.553, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_accuracy_circuit": 0.8640216796962398, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7592071294784546, | |
| "eval_iou_circuit": 0.8640216796962398, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.3638363480567932, | |
| "eval_mean_accuracy": 0.8640216796962398, | |
| "eval_mean_iou": 0.4320108398481199, | |
| "eval_overall_accuracy": 0.8640216796962398, | |
| "eval_runtime": 1.8486, | |
| "eval_samples_per_second": 5.409, | |
| "eval_steps_per_second": 2.705, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.5158, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy_circuit": 0.7826529687890519, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.709518313407898, | |
| "eval_iou_circuit": 0.7826529687890519, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.303494393825531, | |
| "eval_mean_accuracy": 0.7826529687890519, | |
| "eval_mean_iou": 0.39132648439452594, | |
| "eval_overall_accuracy": 0.7826529687890519, | |
| "eval_runtime": 1.8534, | |
| "eval_samples_per_second": 5.396, | |
| "eval_steps_per_second": 2.698, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 5.25e-05, | |
| "loss": 0.4876, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy_circuit": 0.720841168721603, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.6600955724716187, | |
| "eval_iou_circuit": 0.720841168721603, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.3579980432987213, | |
| "eval_mean_accuracy": 0.720841168721603, | |
| "eval_mean_iou": 0.3604205843608015, | |
| "eval_overall_accuracy": 0.720841168721603, | |
| "eval_runtime": 1.8586, | |
| "eval_samples_per_second": 5.381, | |
| "eval_steps_per_second": 2.69, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 5.1e-05, | |
| "loss": 0.4716, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_accuracy_circuit": 0.830260114881435, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7596594095230103, | |
| "eval_iou_circuit": 0.830260114881435, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2591872811317444, | |
| "eval_mean_accuracy": 0.830260114881435, | |
| "eval_mean_iou": 0.4151300574407175, | |
| "eval_overall_accuracy": 0.830260114881435, | |
| "eval_runtime": 1.8886, | |
| "eval_samples_per_second": 5.295, | |
| "eval_steps_per_second": 2.647, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.95e-05, | |
| "loss": 0.4555, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "eval_accuracy_circuit": 0.9281712722196696, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7989642024040222, | |
| "eval_iou_circuit": 0.9281712722196696, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2810139060020447, | |
| "eval_mean_accuracy": 0.9281712722196696, | |
| "eval_mean_iou": 0.4640856361098348, | |
| "eval_overall_accuracy": 0.9281712722196696, | |
| "eval_runtime": 1.8951, | |
| "eval_samples_per_second": 5.277, | |
| "eval_steps_per_second": 2.638, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.4174, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy_circuit": 0.8431605382379681, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7649561762809753, | |
| "eval_iou_circuit": 0.8431605382379681, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.350821316242218, | |
| "eval_mean_accuracy": 0.8431605382379681, | |
| "eval_mean_iou": 0.42158026911898405, | |
| "eval_overall_accuracy": 0.8431605382379681, | |
| "eval_runtime": 1.8632, | |
| "eval_samples_per_second": 5.367, | |
| "eval_steps_per_second": 2.684, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 0.4348, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "eval_accuracy_circuit": 0.8319266924165811, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7888613939285278, | |
| "eval_iou_circuit": 0.8319266924165811, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.22976386547088623, | |
| "eval_mean_accuracy": 0.8319266924165811, | |
| "eval_mean_iou": 0.41596334620829056, | |
| "eval_overall_accuracy": 0.8319266924165811, | |
| "eval_runtime": 1.8732, | |
| "eval_samples_per_second": 5.338, | |
| "eval_steps_per_second": 2.669, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.4215, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_accuracy_circuit": 0.7035958565848367, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7077653408050537, | |
| "eval_iou_circuit": 0.7035958565848367, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.246572807431221, | |
| "eval_mean_accuracy": 0.7035958565848367, | |
| "eval_mean_iou": 0.35179792829241835, | |
| "eval_overall_accuracy": 0.7035958565848367, | |
| "eval_runtime": 1.8657, | |
| "eval_samples_per_second": 5.36, | |
| "eval_steps_per_second": 2.68, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 4.35e-05, | |
| "loss": 0.3917, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "eval_accuracy_circuit": 0.8747709410869753, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.817740797996521, | |
| "eval_iou_circuit": 0.8747709410869753, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.21436497569084167, | |
| "eval_mean_accuracy": 0.8747709410869753, | |
| "eval_mean_iou": 0.43738547054348764, | |
| "eval_overall_accuracy": 0.8747709410869753, | |
| "eval_runtime": 1.9253, | |
| "eval_samples_per_second": 5.194, | |
| "eval_steps_per_second": 2.597, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.3965, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy_circuit": 0.8348472958769941, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7990642786026001, | |
| "eval_iou_circuit": 0.8348472958769941, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.22340206801891327, | |
| "eval_mean_accuracy": 0.8348472958769941, | |
| "eval_mean_iou": 0.41742364793849707, | |
| "eval_overall_accuracy": 0.8348472958769941, | |
| "eval_runtime": 1.865, | |
| "eval_samples_per_second": 5.362, | |
| "eval_steps_per_second": 2.681, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 4.05e-05, | |
| "loss": 0.3685, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "eval_accuracy_circuit": 0.9429696512629209, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.846348762512207, | |
| "eval_iou_circuit": 0.9429696512629209, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2239874303340912, | |
| "eval_mean_accuracy": 0.9429696512629209, | |
| "eval_mean_iou": 0.47148482563146044, | |
| "eval_overall_accuracy": 0.9429696512629209, | |
| "eval_runtime": 1.9367, | |
| "eval_samples_per_second": 5.163, | |
| "eval_steps_per_second": 2.582, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 3.9e-05, | |
| "loss": 0.3774, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "eval_accuracy_circuit": 0.8867163838650847, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8314148783683777, | |
| "eval_iou_circuit": 0.8867163838650847, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2103152573108673, | |
| "eval_mean_accuracy": 0.8867163838650847, | |
| "eval_mean_iou": 0.44335819193254233, | |
| "eval_overall_accuracy": 0.8867163838650847, | |
| "eval_runtime": 1.8595, | |
| "eval_samples_per_second": 5.378, | |
| "eval_steps_per_second": 2.689, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.3546, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "eval_accuracy_circuit": 0.8007233841455762, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7820441126823425, | |
| "eval_iou_circuit": 0.8007233841455762, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2279864251613617, | |
| "eval_mean_accuracy": 0.8007233841455762, | |
| "eval_mean_iou": 0.4003616920727881, | |
| "eval_overall_accuracy": 0.8007233841455762, | |
| "eval_runtime": 1.8688, | |
| "eval_samples_per_second": 5.351, | |
| "eval_steps_per_second": 2.676, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.3405, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy_circuit": 0.7007658398535769, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7185879945755005, | |
| "eval_iou_circuit": 0.7007658398535769, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2274409830570221, | |
| "eval_mean_accuracy": 0.7007658398535769, | |
| "eval_mean_iou": 0.35038291992678844, | |
| "eval_overall_accuracy": 0.7007658398535769, | |
| "eval_runtime": 1.8599, | |
| "eval_samples_per_second": 5.377, | |
| "eval_steps_per_second": 2.688, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 3.45e-05, | |
| "loss": 0.3448, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "eval_accuracy_circuit": 0.7553961859712808, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7602112889289856, | |
| "eval_iou_circuit": 0.7553961859712808, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2249414026737213, | |
| "eval_mean_accuracy": 0.7553961859712808, | |
| "eval_mean_iou": 0.3776980929856404, | |
| "eval_overall_accuracy": 0.7553961859712808, | |
| "eval_runtime": 1.8349, | |
| "eval_samples_per_second": 5.45, | |
| "eval_steps_per_second": 2.725, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.3378, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "eval_accuracy_circuit": 0.7865372840788912, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.776802122592926, | |
| "eval_iou_circuit": 0.7865372840788912, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.21100302040576935, | |
| "eval_mean_accuracy": 0.7865372840788912, | |
| "eval_mean_iou": 0.3932686420394456, | |
| "eval_overall_accuracy": 0.7865372840788912, | |
| "eval_runtime": 1.8753, | |
| "eval_samples_per_second": 5.332, | |
| "eval_steps_per_second": 2.666, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 3.15e-05, | |
| "loss": 0.3274, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "eval_accuracy_circuit": 0.7718644167688041, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7673341631889343, | |
| "eval_iou_circuit": 0.7718644167688041, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.21237103641033173, | |
| "eval_mean_accuracy": 0.7718644167688041, | |
| "eval_mean_iou": 0.38593220838440206, | |
| "eval_overall_accuracy": 0.7718644167688041, | |
| "eval_runtime": 1.8789, | |
| "eval_samples_per_second": 5.322, | |
| "eval_steps_per_second": 2.661, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3185, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy_circuit": 0.8367168749979537, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8104449510574341, | |
| "eval_iou_circuit": 0.8367168749979537, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.20555877685546875, | |
| "eval_mean_accuracy": 0.8367168749979537, | |
| "eval_mean_iou": 0.41835843749897683, | |
| "eval_overall_accuracy": 0.8367168749979537, | |
| "eval_runtime": 1.8857, | |
| "eval_samples_per_second": 5.303, | |
| "eval_steps_per_second": 2.652, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 0.3225, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "eval_accuracy_circuit": 0.825157790076715, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8050472140312195, | |
| "eval_iou_circuit": 0.825157790076715, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2054174840450287, | |
| "eval_mean_accuracy": 0.825157790076715, | |
| "eval_mean_iou": 0.4125788950383575, | |
| "eval_overall_accuracy": 0.825157790076715, | |
| "eval_runtime": 1.8934, | |
| "eval_samples_per_second": 5.281, | |
| "eval_steps_per_second": 2.641, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.3095, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "eval_accuracy_circuit": 0.7891293742203266, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7862051725387573, | |
| "eval_iou_circuit": 0.7891293742203266, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2073349505662918, | |
| "eval_mean_accuracy": 0.7891293742203266, | |
| "eval_mean_iou": 0.3945646871101633, | |
| "eval_overall_accuracy": 0.7891293742203266, | |
| "eval_runtime": 1.9031, | |
| "eval_samples_per_second": 5.255, | |
| "eval_steps_per_second": 2.627, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 2.55e-05, | |
| "loss": 0.3038, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "eval_accuracy_circuit": 0.8850978282104537, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8418375849723816, | |
| "eval_iou_circuit": 0.8850978282104537, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19880831241607666, | |
| "eval_mean_accuracy": 0.8850978282104537, | |
| "eval_mean_iou": 0.44254891410522684, | |
| "eval_overall_accuracy": 0.8850978282104537, | |
| "eval_runtime": 1.8755, | |
| "eval_samples_per_second": 5.332, | |
| "eval_steps_per_second": 2.666, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.2933, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy_circuit": 0.8413717231887838, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8135576248168945, | |
| "eval_iou_circuit": 0.8413717231887838, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.20930209755897522, | |
| "eval_mean_accuracy": 0.8413717231887838, | |
| "eval_mean_iou": 0.4206858615943919, | |
| "eval_overall_accuracy": 0.8413717231887838, | |
| "eval_runtime": 1.8492, | |
| "eval_samples_per_second": 5.408, | |
| "eval_steps_per_second": 2.704, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.289, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "eval_accuracy_circuit": 0.7590698598306792, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7699534296989441, | |
| "eval_iou_circuit": 0.7590698598306792, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2080351561307907, | |
| "eval_mean_accuracy": 0.7590698598306792, | |
| "eval_mean_iou": 0.3795349299153396, | |
| "eval_overall_accuracy": 0.7590698598306792, | |
| "eval_runtime": 1.8538, | |
| "eval_samples_per_second": 5.394, | |
| "eval_steps_per_second": 2.697, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.3045, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "eval_accuracy_circuit": 0.755483498481308, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7673963904380798, | |
| "eval_iou_circuit": 0.755483498481308, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2087668925523758, | |
| "eval_mean_accuracy": 0.755483498481308, | |
| "eval_mean_iou": 0.377741749240654, | |
| "eval_overall_accuracy": 0.755483498481308, | |
| "eval_runtime": 1.8506, | |
| "eval_samples_per_second": 5.404, | |
| "eval_steps_per_second": 2.702, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 1.95e-05, | |
| "loss": 0.2842, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "eval_accuracy_circuit": 0.8520740541053796, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8262351751327515, | |
| "eval_iou_circuit": 0.8520740541053796, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19945015013217926, | |
| "eval_mean_accuracy": 0.8520740541053796, | |
| "eval_mean_iou": 0.4260370270526898, | |
| "eval_overall_accuracy": 0.8520740541053796, | |
| "eval_runtime": 1.8567, | |
| "eval_samples_per_second": 5.386, | |
| "eval_steps_per_second": 2.693, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.2761, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy_circuit": 0.8814885473272004, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8395698666572571, | |
| "eval_iou_circuit": 0.8814885473272004, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19794146716594696, | |
| "eval_mean_accuracy": 0.8814885473272004, | |
| "eval_mean_iou": 0.4407442736636002, | |
| "eval_overall_accuracy": 0.8814885473272004, | |
| "eval_runtime": 1.9067, | |
| "eval_samples_per_second": 5.245, | |
| "eval_steps_per_second": 2.622, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 1.65e-05, | |
| "loss": 0.2846, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "eval_accuracy_circuit": 0.8062491746239286, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7988327741622925, | |
| "eval_iou_circuit": 0.8062491746239286, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19883993268013, | |
| "eval_mean_accuracy": 0.8062491746239286, | |
| "eval_mean_iou": 0.4031245873119643, | |
| "eval_overall_accuracy": 0.8062491746239286, | |
| "eval_runtime": 1.855, | |
| "eval_samples_per_second": 5.391, | |
| "eval_steps_per_second": 2.695, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2722, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "eval_accuracy_circuit": 0.8571108945275793, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.827845573425293, | |
| "eval_iou_circuit": 0.8571108945275793, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.196430042386055, | |
| "eval_mean_accuracy": 0.8571108945275793, | |
| "eval_mean_iou": 0.42855544726378964, | |
| "eval_overall_accuracy": 0.8571108945275793, | |
| "eval_runtime": 1.8615, | |
| "eval_samples_per_second": 5.372, | |
| "eval_steps_per_second": 2.686, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.2913, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "eval_accuracy_circuit": 0.7619489898488293, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7747573852539062, | |
| "eval_iou_circuit": 0.7619489898488293, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.2070605456829071, | |
| "eval_mean_accuracy": 0.7619489898488293, | |
| "eval_mean_iou": 0.38097449492441465, | |
| "eval_overall_accuracy": 0.7619489898488293, | |
| "eval_runtime": 1.8551, | |
| "eval_samples_per_second": 5.391, | |
| "eval_steps_per_second": 2.695, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2631, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy_circuit": 0.822477296018877, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8101258277893066, | |
| "eval_iou_circuit": 0.822477296018877, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19885489344596863, | |
| "eval_mean_accuracy": 0.822477296018877, | |
| "eval_mean_iou": 0.4112386480094385, | |
| "eval_overall_accuracy": 0.822477296018877, | |
| "eval_runtime": 1.8822, | |
| "eval_samples_per_second": 5.313, | |
| "eval_steps_per_second": 2.656, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.2649, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "eval_accuracy_circuit": 0.8814001434107978, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8404178619384766, | |
| "eval_iou_circuit": 0.8814001434107978, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19604873657226562, | |
| "eval_mean_accuracy": 0.8814001434107978, | |
| "eval_mean_iou": 0.4407000717053989, | |
| "eval_overall_accuracy": 0.8814001434107978, | |
| "eval_runtime": 1.9145, | |
| "eval_samples_per_second": 5.223, | |
| "eval_steps_per_second": 2.612, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 9e-06, | |
| "loss": 0.2812, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "eval_accuracy_circuit": 0.8107686884242166, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8038872480392456, | |
| "eval_iou_circuit": 0.8107686884242166, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19998733699321747, | |
| "eval_mean_accuracy": 0.8107686884242166, | |
| "eval_mean_iou": 0.4053843442121083, | |
| "eval_overall_accuracy": 0.8107686884242166, | |
| "eval_runtime": 1.8241, | |
| "eval_samples_per_second": 5.482, | |
| "eval_steps_per_second": 2.741, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.2522, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "eval_accuracy_circuit": 0.8161209452888898, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.806645393371582, | |
| "eval_iou_circuit": 0.8161209452888898, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19722411036491394, | |
| "eval_mean_accuracy": 0.8161209452888898, | |
| "eval_mean_iou": 0.4080604726444449, | |
| "eval_overall_accuracy": 0.8161209452888898, | |
| "eval_runtime": 1.8752, | |
| "eval_samples_per_second": 5.333, | |
| "eval_steps_per_second": 2.666, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 6e-06, | |
| "loss": 0.264, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy_circuit": 0.8064063371419777, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8012853860855103, | |
| "eval_iou_circuit": 0.8064063371419777, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19993409514427185, | |
| "eval_mean_accuracy": 0.8064063371419777, | |
| "eval_mean_iou": 0.40320316857098887, | |
| "eval_overall_accuracy": 0.8064063371419777, | |
| "eval_runtime": 1.8665, | |
| "eval_samples_per_second": 5.358, | |
| "eval_steps_per_second": 2.679, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2604, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "eval_accuracy_circuit": 0.8446448509084321, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8228257894515991, | |
| "eval_iou_circuit": 0.8446448509084321, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.19786684215068817, | |
| "eval_mean_accuracy": 0.8446448509084321, | |
| "eval_mean_iou": 0.42232242545421605, | |
| "eval_overall_accuracy": 0.8446448509084321, | |
| "eval_runtime": 1.9162, | |
| "eval_samples_per_second": 5.219, | |
| "eval_steps_per_second": 2.609, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 3e-06, | |
| "loss": 0.2555, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "eval_accuracy_circuit": 0.8151583248658388, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.8071210980415344, | |
| "eval_iou_circuit": 0.8151583248658388, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.1972045600414276, | |
| "eval_mean_accuracy": 0.8151583248658388, | |
| "eval_mean_iou": 0.4075791624329194, | |
| "eval_overall_accuracy": 0.8151583248658388, | |
| "eval_runtime": 1.8971, | |
| "eval_samples_per_second": 5.271, | |
| "eval_steps_per_second": 2.636, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.2804, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "eval_accuracy_circuit": 0.7769918439201571, | |
| "eval_accuracy_unlabeled": NaN, | |
| "eval_dice_coefficient": 0.7854458093643188, | |
| "eval_iou_circuit": 0.7769918439201571, | |
| "eval_iou_unlabeled": 0.0, | |
| "eval_loss": 0.20280936360359192, | |
| "eval_mean_accuracy": 0.7769918439201571, | |
| "eval_mean_iou": 0.38849592196007854, | |
| "eval_overall_accuracy": 0.7769918439201571, | |
| "eval_runtime": 1.8601, | |
| "eval_samples_per_second": 5.376, | |
| "eval_steps_per_second": 2.688, | |
| "step": 3900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 100, | |
| "total_flos": 3.113516120879923e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |