| { | |
| "best_metric": 0.7254901960784313, | |
| "best_model_checkpoint": "vit-base-patch16-224-ve-Ub\\checkpoint-63", | |
| "epoch": 45.714285714285715, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.09803921568627451, | |
| "eval_loss": 1.3862946033477783, | |
| "eval_runtime": 0.7706, | |
| "eval_samples_per_second": 66.182, | |
| "eval_steps_per_second": 2.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.381344199180603, | |
| "eval_runtime": 0.7881, | |
| "eval_samples_per_second": 64.714, | |
| "eval_steps_per_second": 2.538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.368581771850586, | |
| "eval_runtime": 0.7663, | |
| "eval_samples_per_second": 66.551, | |
| "eval_steps_per_second": 2.61, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.347954273223877, | |
| "eval_runtime": 0.7685, | |
| "eval_samples_per_second": 66.363, | |
| "eval_steps_per_second": 2.602, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.3345353603363037, | |
| "eval_runtime": 0.7796, | |
| "eval_samples_per_second": 65.42, | |
| "eval_steps_per_second": 2.565, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.3658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.304049015045166, | |
| "eval_runtime": 0.7926, | |
| "eval_samples_per_second": 64.342, | |
| "eval_steps_per_second": 2.523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.47058823529411764, | |
| "eval_loss": 1.2754029035568237, | |
| "eval_runtime": 0.8003, | |
| "eval_samples_per_second": 63.726, | |
| "eval_steps_per_second": 2.499, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.49019607843137253, | |
| "eval_loss": 1.2477165460586548, | |
| "eval_runtime": 0.7776, | |
| "eval_samples_per_second": 65.59, | |
| "eval_steps_per_second": 2.572, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_accuracy": 0.5294117647058824, | |
| "eval_loss": 1.2347149848937988, | |
| "eval_runtime": 0.762, | |
| "eval_samples_per_second": 66.926, | |
| "eval_steps_per_second": 2.625, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "eval_accuracy": 0.5490196078431373, | |
| "eval_loss": 1.2109137773513794, | |
| "eval_runtime": 0.7942, | |
| "eval_samples_per_second": 64.215, | |
| "eval_steps_per_second": 2.518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.6078431372549019, | |
| "eval_loss": 1.1888847351074219, | |
| "eval_runtime": 0.7771, | |
| "eval_samples_per_second": 65.629, | |
| "eval_steps_per_second": 2.574, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2512, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6274509803921569, | |
| "eval_loss": 1.1671414375305176, | |
| "eval_runtime": 0.8252, | |
| "eval_samples_per_second": 61.806, | |
| "eval_steps_per_second": 2.424, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "eval_accuracy": 0.6078431372549019, | |
| "eval_loss": 1.1560198068618774, | |
| "eval_runtime": 0.8006, | |
| "eval_samples_per_second": 63.699, | |
| "eval_steps_per_second": 2.498, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "eval_accuracy": 0.6470588235294118, | |
| "eval_loss": 1.1310560703277588, | |
| "eval_runtime": 0.8047, | |
| "eval_samples_per_second": 63.376, | |
| "eval_steps_per_second": 2.485, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.6274509803921569, | |
| "eval_loss": 1.1128166913986206, | |
| "eval_runtime": 0.7724, | |
| "eval_samples_per_second": 66.031, | |
| "eval_steps_per_second": 2.589, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0873538255691528, | |
| "eval_runtime": 0.7769, | |
| "eval_samples_per_second": 65.648, | |
| "eval_steps_per_second": 2.574, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_loss": 1.0828280448913574, | |
| "eval_runtime": 0.7846, | |
| "eval_samples_per_second": 64.999, | |
| "eval_steps_per_second": 2.549, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 1.1299, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0585854053497314, | |
| "eval_runtime": 0.7897, | |
| "eval_samples_per_second": 64.579, | |
| "eval_steps_per_second": 2.533, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0361896753311157, | |
| "eval_runtime": 0.7852, | |
| "eval_samples_per_second": 64.955, | |
| "eval_steps_per_second": 2.547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_loss": 1.0172666311264038, | |
| "eval_runtime": 0.7638, | |
| "eval_samples_per_second": 66.769, | |
| "eval_steps_per_second": 2.618, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0064767599105835, | |
| "eval_runtime": 0.7647, | |
| "eval_samples_per_second": 66.691, | |
| "eval_steps_per_second": 2.615, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.71, | |
| "eval_accuracy": 0.6470588235294118, | |
| "eval_loss": 1.007025957107544, | |
| "eval_runtime": 0.8066, | |
| "eval_samples_per_second": 63.232, | |
| "eval_steps_per_second": 2.48, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.0212, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9791509509086609, | |
| "eval_runtime": 0.775, | |
| "eval_samples_per_second": 65.808, | |
| "eval_steps_per_second": 2.581, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9611671566963196, | |
| "eval_runtime": 0.7739, | |
| "eval_samples_per_second": 65.903, | |
| "eval_steps_per_second": 2.584, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "eval_accuracy": 0.6470588235294118, | |
| "eval_loss": 0.9584113955497742, | |
| "eval_runtime": 0.79, | |
| "eval_samples_per_second": 64.559, | |
| "eval_steps_per_second": 2.532, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9494024515151978, | |
| "eval_runtime": 0.7674, | |
| "eval_samples_per_second": 66.461, | |
| "eval_steps_per_second": 2.606, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9293842911720276, | |
| "eval_runtime": 0.8021, | |
| "eval_samples_per_second": 63.584, | |
| "eval_steps_per_second": 2.493, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.919573962688446, | |
| "eval_runtime": 0.8029, | |
| "eval_samples_per_second": 63.516, | |
| "eval_steps_per_second": 2.491, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.9222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.9100386500358582, | |
| "eval_runtime": 0.7579, | |
| "eval_samples_per_second": 67.287, | |
| "eval_steps_per_second": 2.639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.71, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_loss": 0.9060911536216736, | |
| "eval_runtime": 0.7886, | |
| "eval_samples_per_second": 64.672, | |
| "eval_steps_per_second": 2.536, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8903732895851135, | |
| "eval_runtime": 0.8095, | |
| "eval_samples_per_second": 63.005, | |
| "eval_steps_per_second": 2.471, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8797234892845154, | |
| "eval_runtime": 0.7783, | |
| "eval_samples_per_second": 65.531, | |
| "eval_steps_per_second": 2.57, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_loss": 0.8747111558914185, | |
| "eval_runtime": 0.8011, | |
| "eval_samples_per_second": 63.663, | |
| "eval_steps_per_second": 2.497, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.71, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_loss": 0.8690942525863647, | |
| "eval_runtime": 0.7795, | |
| "eval_samples_per_second": 65.424, | |
| "eval_steps_per_second": 2.566, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.8419, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8549560904502869, | |
| "eval_runtime": 0.854, | |
| "eval_samples_per_second": 59.715, | |
| "eval_steps_per_second": 2.342, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.8469617366790771, | |
| "eval_runtime": 0.7796, | |
| "eval_samples_per_second": 65.415, | |
| "eval_steps_per_second": 2.565, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.8430066704750061, | |
| "eval_runtime": 0.7729, | |
| "eval_samples_per_second": 65.989, | |
| "eval_steps_per_second": 2.588, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8388990759849548, | |
| "eval_runtime": 0.8337, | |
| "eval_samples_per_second": 61.174, | |
| "eval_steps_per_second": 2.399, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.8297919631004333, | |
| "eval_runtime": 0.7574, | |
| "eval_samples_per_second": 67.332, | |
| "eval_steps_per_second": 2.64, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.7865, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.826995849609375, | |
| "eval_runtime": 0.7696, | |
| "eval_samples_per_second": 66.265, | |
| "eval_steps_per_second": 2.599, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.8258256912231445, | |
| "eval_runtime": 0.7911, | |
| "eval_samples_per_second": 64.471, | |
| "eval_steps_per_second": 2.528, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.71, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8234664797782898, | |
| "eval_runtime": 0.7812, | |
| "eval_samples_per_second": 65.285, | |
| "eval_steps_per_second": 2.56, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8210938572883606, | |
| "eval_runtime": 0.7884, | |
| "eval_samples_per_second": 64.687, | |
| "eval_steps_per_second": 2.537, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8188748359680176, | |
| "eval_runtime": 0.7819, | |
| "eval_samples_per_second": 65.225, | |
| "eval_steps_per_second": 2.558, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.8188669681549072, | |
| "eval_runtime": 0.783, | |
| "eval_samples_per_second": 65.134, | |
| "eval_steps_per_second": 2.554, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 0.0, | |
| "loss": 0.7555, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.81866455078125, | |
| "eval_runtime": 0.7693, | |
| "eval_samples_per_second": 66.291, | |
| "eval_steps_per_second": 2.6, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "step": 80, | |
| "total_flos": 7.203009548954419e+17, | |
| "train_loss": 1.0092584133148192, | |
| "train_runtime": 365.7142, | |
| "train_samples_per_second": 44.406, | |
| "train_steps_per_second": 0.219 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 7.203009548954419e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |