| { | |
| "best_metric": 0.08701933920383453, | |
| "best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-300", | |
| "epoch": 10.0, | |
| "eval_steps": 100, | |
| "global_step": 340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00019411764705882354, | |
| "loss": 0.5837, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018823529411764707, | |
| "loss": 0.2956, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001823529411764706, | |
| "loss": 0.279, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.1566, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00017058823529411766, | |
| "loss": 0.1042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001647058823529412, | |
| "loss": 0.176, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0001588235294117647, | |
| "loss": 0.1231, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00015294117647058822, | |
| "loss": 0.0952, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00014705882352941178, | |
| "loss": 0.1003, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 0.1606, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.9511278195488722, | |
| "eval_loss": 0.18294382095336914, | |
| "eval_runtime": 2.8739, | |
| "eval_samples_per_second": 92.556, | |
| "eval_steps_per_second": 11.83, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00013529411764705884, | |
| "loss": 0.2204, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.00012941176470588237, | |
| "loss": 0.2845, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0001235294117647059, | |
| "loss": 0.2104, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 0.2029, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00011176470588235294, | |
| "loss": 0.1105, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 0.00010588235294117647, | |
| "loss": 0.177, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1881, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.1445, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.0891, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.1895, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "eval_accuracy": 0.9661654135338346, | |
| "eval_loss": 0.14408943057060242, | |
| "eval_runtime": 2.3757, | |
| "eval_samples_per_second": 111.968, | |
| "eval_steps_per_second": 14.312, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 7.647058823529411e-05, | |
| "loss": 0.1095, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.1908, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.470588235294118e-05, | |
| "loss": 0.1118, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.0461, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 5.294117647058824e-05, | |
| "loss": 0.1002, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.082, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 0.0712, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.0565, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.0702, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 0.0423, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_accuracy": 0.9774436090225563, | |
| "eval_loss": 0.08701933920383453, | |
| "eval_runtime": 2.414, | |
| "eval_samples_per_second": 110.19, | |
| "eval_steps_per_second": 14.084, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.0652, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.027, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.0633, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.055, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 340, | |
| "total_flos": 8.230018095787622e+17, | |
| "train_loss": 0.1465345554492053, | |
| "train_runtime": 221.0307, | |
| "train_samples_per_second": 48.048, | |
| "train_steps_per_second": 1.538 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 340, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "total_flos": 8.230018095787622e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |