| { | |
| "best_metric": 0.0946127399802208, | |
| "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": 0.00019794117647058826, | |
| "loss": 1.9655, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000195, | |
| "loss": 1.7836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001920588235294118, | |
| "loss": 1.5744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018911764705882353, | |
| "loss": 1.3903, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00018617647058823532, | |
| "loss": 1.3596, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00018323529411764706, | |
| "loss": 1.3915, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00018029411764705885, | |
| "loss": 1.2525, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00017735294117647059, | |
| "loss": 1.167, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00017441176470588235, | |
| "loss": 1.0339, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00017147058823529412, | |
| "loss": 0.9733, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.7255639097744361, | |
| "eval_loss": 0.8894439339637756, | |
| "eval_runtime": 2.491, | |
| "eval_samples_per_second": 106.783, | |
| "eval_steps_per_second": 13.649, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00016852941176470588, | |
| "loss": 0.9561, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.00016558823529411765, | |
| "loss": 0.9493, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0001626470588235294, | |
| "loss": 0.8258, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0001597058823529412, | |
| "loss": 0.8111, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00015676470588235294, | |
| "loss": 0.9361, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 0.00015382352941176473, | |
| "loss": 0.7733, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00015088235294117647, | |
| "loss": 0.5113, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.00014794117647058826, | |
| "loss": 0.7088, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.000145, | |
| "loss": 0.6652, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.00014205882352941177, | |
| "loss": 0.7184, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_accuracy": 0.7293233082706767, | |
| "eval_loss": 0.7875903248786926, | |
| "eval_runtime": 2.5205, | |
| "eval_samples_per_second": 105.533, | |
| "eval_steps_per_second": 13.489, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00013911764705882353, | |
| "loss": 0.9143, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.0001361764705882353, | |
| "loss": 0.7709, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00013323529411764706, | |
| "loss": 0.5797, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 0.00013029411764705883, | |
| "loss": 0.5424, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.0001273529411764706, | |
| "loss": 0.6525, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.00012441176470588236, | |
| "loss": 0.3516, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 0.00012147058823529412, | |
| "loss": 0.4829, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 0.00011852941176470589, | |
| "loss": 0.5154, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00011558823529411764, | |
| "loss": 0.3485, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.00011264705882352942, | |
| "loss": 0.5299, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_accuracy": 0.8609022556390977, | |
| "eval_loss": 0.5183172821998596, | |
| "eval_runtime": 2.8712, | |
| "eval_samples_per_second": 92.644, | |
| "eval_steps_per_second": 11.842, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 0.0001097058823529412, | |
| "loss": 0.5263, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.00010676470588235295, | |
| "loss": 0.4048, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.00010382352941176472, | |
| "loss": 0.4386, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00010088235294117648, | |
| "loss": 0.4728, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 9.794117647058824e-05, | |
| "loss": 0.379, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.4361, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 9.205882352941177e-05, | |
| "loss": 0.2929, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 8.911764705882354e-05, | |
| "loss": 0.2848, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 8.61764705882353e-05, | |
| "loss": 0.4282, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 8.323529411764707e-05, | |
| "loss": 0.3991, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "eval_accuracy": 0.8947368421052632, | |
| "eval_loss": 0.31206753849983215, | |
| "eval_runtime": 2.9634, | |
| "eval_samples_per_second": 89.761, | |
| "eval_steps_per_second": 11.473, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 8.029411764705883e-05, | |
| "loss": 0.3552, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 7.73529411764706e-05, | |
| "loss": 0.2886, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 7.441176470588236e-05, | |
| "loss": 0.2809, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 7.147058823529412e-05, | |
| "loss": 0.3627, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 6.852941176470589e-05, | |
| "loss": 0.3137, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 6.558823529411765e-05, | |
| "loss": 0.198, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 6.264705882352942e-05, | |
| "loss": 0.3268, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 5.970588235294118e-05, | |
| "loss": 0.256, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 5.676470588235294e-05, | |
| "loss": 0.2544, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 5.382352941176471e-05, | |
| "loss": 0.2263, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "eval_accuracy": 0.9548872180451128, | |
| "eval_loss": 0.13367173075675964, | |
| "eval_runtime": 2.4729, | |
| "eval_samples_per_second": 107.566, | |
| "eval_steps_per_second": 13.749, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.088235294117647e-05, | |
| "loss": 0.4011, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 4.794117647058824e-05, | |
| "loss": 0.2051, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.2563, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 4.205882352941177e-05, | |
| "loss": 0.2428, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 3.911764705882353e-05, | |
| "loss": 0.189, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 16.47, | |
| "learning_rate": 3.61764705882353e-05, | |
| "loss": 0.19, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 3.3235294117647056e-05, | |
| "loss": 0.1696, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 3.0294117647058824e-05, | |
| "loss": 0.1336, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 2.7352941176470593e-05, | |
| "loss": 0.1532, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 2.4411764705882354e-05, | |
| "loss": 0.1782, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "eval_accuracy": 0.9624060150375939, | |
| "eval_loss": 0.0946127399802208, | |
| "eval_runtime": 2.8201, | |
| "eval_samples_per_second": 94.322, | |
| "eval_steps_per_second": 12.056, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "learning_rate": 2.1470588235294116e-05, | |
| "loss": 0.1511, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 1.8529411764705884e-05, | |
| "loss": 0.0837, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 1.558823529411765e-05, | |
| "loss": 0.1084, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 1.2647058823529412e-05, | |
| "loss": 0.1313, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 9.705882352941177e-06, | |
| "loss": 0.1135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 6.7647058823529414e-06, | |
| "loss": 0.0844, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 3.823529411764706e-06, | |
| "loss": 0.1765, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 8.823529411764706e-07, | |
| "loss": 0.1745, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 680, | |
| "total_flos": 1.6434612963230515e+18, | |
| "train_loss": 0.5515072485103326, | |
| "train_runtime": 465.2023, | |
| "train_samples_per_second": 45.658, | |
| "train_steps_per_second": 1.462 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 680, | |
| "num_train_epochs": 20, | |
| "save_steps": 100, | |
| "total_flos": 1.6434612963230515e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |