| { |
| "best_metric": 0.05951835587620735, |
| "best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600", |
| "epoch": 20.0, |
| "eval_steps": 100, |
| "global_step": 680, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00019705882352941177, |
| "loss": 1.5799, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.00019441176470588235, |
| "loss": 1.1614, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00019147058823529414, |
| "loss": 0.8677, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00018882352941176472, |
| "loss": 0.7303, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.00018588235294117648, |
| "loss": 0.4837, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00018294117647058825, |
| "loss": 0.4625, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 0.00018029411764705885, |
| "loss": 0.3693, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 0.00017735294117647059, |
| "loss": 0.331, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 0.00017441176470588235, |
| "loss": 0.2914, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 0.00017147058823529412, |
| "loss": 0.2926, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.94, |
| "eval_accuracy": 0.943609022556391, |
| "eval_loss": 0.15237735211849213, |
| "eval_runtime": 1.9186, |
| "eval_samples_per_second": 138.643, |
| "eval_steps_per_second": 17.721, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 0.00016852941176470588, |
| "loss": 0.2343, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 0.00016558823529411765, |
| "loss": 0.2078, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 0.0001626470588235294, |
| "loss": 0.2448, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 0.0001597058823529412, |
| "loss": 0.2146, |
| "step": 140 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 0.00015676470588235294, |
| "loss": 0.2086, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.71, |
| "learning_rate": 0.00015382352941176473, |
| "loss": 0.1924, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.00015088235294117647, |
| "loss": 0.0882, |
| "step": 170 |
| }, |
| { |
| "epoch": 5.29, |
| "learning_rate": 0.00014794117647058826, |
| "loss": 0.1726, |
| "step": 180 |
| }, |
| { |
| "epoch": 5.59, |
| "learning_rate": 0.000145, |
| "loss": 0.1193, |
| "step": 190 |
| }, |
| { |
| "epoch": 5.88, |
| "learning_rate": 0.00014205882352941177, |
| "loss": 0.1844, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.88, |
| "eval_accuracy": 0.943609022556391, |
| "eval_loss": 0.1717682033777237, |
| "eval_runtime": 2.2294, |
| "eval_samples_per_second": 119.314, |
| "eval_steps_per_second": 15.251, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.18, |
| "learning_rate": 0.00013911764705882353, |
| "loss": 0.31, |
| "step": 210 |
| }, |
| { |
| "epoch": 6.47, |
| "learning_rate": 0.0001361764705882353, |
| "loss": 0.1387, |
| "step": 220 |
| }, |
| { |
| "epoch": 6.76, |
| "learning_rate": 0.00013323529411764706, |
| "loss": 0.2172, |
| "step": 230 |
| }, |
| { |
| "epoch": 7.06, |
| "learning_rate": 0.00013029411764705883, |
| "loss": 0.1062, |
| "step": 240 |
| }, |
| { |
| "epoch": 7.35, |
| "learning_rate": 0.0001273529411764706, |
| "loss": 0.1055, |
| "step": 250 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 0.00012441176470588236, |
| "loss": 0.087, |
| "step": 260 |
| }, |
| { |
| "epoch": 7.94, |
| "learning_rate": 0.00012147058823529412, |
| "loss": 0.0817, |
| "step": 270 |
| }, |
| { |
| "epoch": 8.24, |
| "learning_rate": 0.00011852941176470589, |
| "loss": 0.0727, |
| "step": 280 |
| }, |
| { |
| "epoch": 8.53, |
| "learning_rate": 0.00011558823529411764, |
| "loss": 0.0561, |
| "step": 290 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 0.00011264705882352942, |
| "loss": 0.1189, |
| "step": 300 |
| }, |
| { |
| "epoch": 8.82, |
| "eval_accuracy": 0.9661654135338346, |
| "eval_loss": 0.08863785862922668, |
| "eval_runtime": 1.8695, |
| "eval_samples_per_second": 142.285, |
| "eval_steps_per_second": 18.187, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.12, |
| "learning_rate": 0.0001097058823529412, |
| "loss": 0.0705, |
| "step": 310 |
| }, |
| { |
| "epoch": 9.41, |
| "learning_rate": 0.00010676470588235295, |
| "loss": 0.147, |
| "step": 320 |
| }, |
| { |
| "epoch": 9.71, |
| "learning_rate": 0.00010382352941176472, |
| "loss": 0.0612, |
| "step": 330 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.00010088235294117648, |
| "loss": 0.0926, |
| "step": 340 |
| }, |
| { |
| "epoch": 10.29, |
| "learning_rate": 9.794117647058824e-05, |
| "loss": 0.0977, |
| "step": 350 |
| }, |
| { |
| "epoch": 10.59, |
| "learning_rate": 9.5e-05, |
| "loss": 0.1104, |
| "step": 360 |
| }, |
| { |
| "epoch": 10.88, |
| "learning_rate": 9.205882352941177e-05, |
| "loss": 0.0834, |
| "step": 370 |
| }, |
| { |
| "epoch": 11.18, |
| "learning_rate": 8.911764705882354e-05, |
| "loss": 0.0831, |
| "step": 380 |
| }, |
| { |
| "epoch": 11.47, |
| "learning_rate": 8.61764705882353e-05, |
| "loss": 0.0464, |
| "step": 390 |
| }, |
| { |
| "epoch": 11.76, |
| "learning_rate": 8.323529411764707e-05, |
| "loss": 0.0682, |
| "step": 400 |
| }, |
| { |
| "epoch": 11.76, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.09778111428022385, |
| "eval_runtime": 2.3942, |
| "eval_samples_per_second": 111.103, |
| "eval_steps_per_second": 14.201, |
| "step": 400 |
| }, |
| { |
| "epoch": 12.06, |
| "learning_rate": 8.029411764705883e-05, |
| "loss": 0.0504, |
| "step": 410 |
| }, |
| { |
| "epoch": 12.35, |
| "learning_rate": 7.73529411764706e-05, |
| "loss": 0.0379, |
| "step": 420 |
| }, |
| { |
| "epoch": 12.65, |
| "learning_rate": 7.441176470588236e-05, |
| "loss": 0.0261, |
| "step": 430 |
| }, |
| { |
| "epoch": 12.94, |
| "learning_rate": 7.147058823529412e-05, |
| "loss": 0.0838, |
| "step": 440 |
| }, |
| { |
| "epoch": 13.24, |
| "learning_rate": 6.852941176470589e-05, |
| "loss": 0.0262, |
| "step": 450 |
| }, |
| { |
| "epoch": 13.53, |
| "learning_rate": 6.558823529411765e-05, |
| "loss": 0.0232, |
| "step": 460 |
| }, |
| { |
| "epoch": 13.82, |
| "learning_rate": 6.264705882352942e-05, |
| "loss": 0.0403, |
| "step": 470 |
| }, |
| { |
| "epoch": 14.12, |
| "learning_rate": 5.970588235294118e-05, |
| "loss": 0.049, |
| "step": 480 |
| }, |
| { |
| "epoch": 14.41, |
| "learning_rate": 5.676470588235294e-05, |
| "loss": 0.0606, |
| "step": 490 |
| }, |
| { |
| "epoch": 14.71, |
| "learning_rate": 5.382352941176471e-05, |
| "loss": 0.0439, |
| "step": 500 |
| }, |
| { |
| "epoch": 14.71, |
| "eval_accuracy": 0.9736842105263158, |
| "eval_loss": 0.08120405673980713, |
| "eval_runtime": 1.897, |
| "eval_samples_per_second": 140.22, |
| "eval_steps_per_second": 17.923, |
| "step": 500 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 5.088235294117647e-05, |
| "loss": 0.0495, |
| "step": 510 |
| }, |
| { |
| "epoch": 15.29, |
| "learning_rate": 4.794117647058824e-05, |
| "loss": 0.0337, |
| "step": 520 |
| }, |
| { |
| "epoch": 15.59, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0987, |
| "step": 530 |
| }, |
| { |
| "epoch": 15.88, |
| "learning_rate": 4.205882352941177e-05, |
| "loss": 0.0218, |
| "step": 540 |
| }, |
| { |
| "epoch": 16.18, |
| "learning_rate": 3.911764705882353e-05, |
| "loss": 0.0324, |
| "step": 550 |
| }, |
| { |
| "epoch": 16.47, |
| "learning_rate": 3.61764705882353e-05, |
| "loss": 0.0364, |
| "step": 560 |
| }, |
| { |
| "epoch": 16.76, |
| "learning_rate": 3.3235294117647056e-05, |
| "loss": 0.0284, |
| "step": 570 |
| }, |
| { |
| "epoch": 17.06, |
| "learning_rate": 3.0294117647058824e-05, |
| "loss": 0.0306, |
| "step": 580 |
| }, |
| { |
| "epoch": 17.35, |
| "learning_rate": 2.7352941176470593e-05, |
| "loss": 0.0535, |
| "step": 590 |
| }, |
| { |
| "epoch": 17.65, |
| "learning_rate": 2.4411764705882354e-05, |
| "loss": 0.0544, |
| "step": 600 |
| }, |
| { |
| "epoch": 17.65, |
| "eval_accuracy": 0.981203007518797, |
| "eval_loss": 0.05951835587620735, |
| "eval_runtime": 1.8559, |
| "eval_samples_per_second": 143.327, |
| "eval_steps_per_second": 18.32, |
| "step": 600 |
| }, |
| { |
| "epoch": 17.94, |
| "learning_rate": 2.1470588235294116e-05, |
| "loss": 0.0121, |
| "step": 610 |
| }, |
| { |
| "epoch": 18.24, |
| "learning_rate": 1.8529411764705884e-05, |
| "loss": 0.0049, |
| "step": 620 |
| }, |
| { |
| "epoch": 18.53, |
| "learning_rate": 1.558823529411765e-05, |
| "loss": 0.0086, |
| "step": 630 |
| }, |
| { |
| "epoch": 18.82, |
| "learning_rate": 1.2647058823529412e-05, |
| "loss": 0.0102, |
| "step": 640 |
| }, |
| { |
| "epoch": 19.12, |
| "learning_rate": 9.705882352941177e-06, |
| "loss": 0.0342, |
| "step": 650 |
| }, |
| { |
| "epoch": 19.41, |
| "learning_rate": 6.7647058823529414e-06, |
| "loss": 0.0367, |
| "step": 660 |
| }, |
| { |
| "epoch": 19.71, |
| "learning_rate": 3.823529411764706e-06, |
| "loss": 0.0313, |
| "step": 670 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 8.823529411764706e-07, |
| "loss": 0.0465, |
| "step": 680 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 680, |
| "total_flos": 5.337848001643315e+17, |
| "train_loss": 0.17142059330773704, |
| "train_runtime": 289.6781, |
| "train_samples_per_second": 73.323, |
| "train_steps_per_second": 2.347 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 680, |
| "num_train_epochs": 20, |
| "save_steps": 100, |
| "total_flos": 5.337848001643315e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
