| { | |
| "best_metric": 0.8588235294117647, | |
| "best_model_checkpoint": "beit-base-patch16-384-finetuned-waifu-cafe/checkpoint-22", | |
| "epoch": 4.0, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.5588235294117647, | |
| "eval_loss": 0.7163116931915283, | |
| "eval_runtime": 12.9255, | |
| "eval_samples_per_second": 26.305, | |
| "eval_steps_per_second": 0.155, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.6882352941176471, | |
| "eval_loss": 0.839873731136322, | |
| "eval_runtime": 12.9227, | |
| "eval_samples_per_second": 26.31, | |
| "eval_steps_per_second": 0.155, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.7970588235294118, | |
| "eval_loss": 0.44704675674438477, | |
| "eval_runtime": 12.8511, | |
| "eval_samples_per_second": 26.457, | |
| "eval_steps_per_second": 0.156, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.638235294117647, | |
| "eval_loss": 0.5900296568870544, | |
| "eval_runtime": 12.861, | |
| "eval_samples_per_second": 26.437, | |
| "eval_steps_per_second": 0.156, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.7671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.8264705882352941, | |
| "eval_loss": 0.4393908679485321, | |
| "eval_runtime": 12.9335, | |
| "eval_samples_per_second": 26.288, | |
| "eval_steps_per_second": 0.155, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.3851720094680786, | |
| "eval_runtime": 12.8822, | |
| "eval_samples_per_second": 26.393, | |
| "eval_steps_per_second": 0.155, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.8264705882352941, | |
| "eval_loss": 0.367575466632843, | |
| "eval_runtime": 12.8552, | |
| "eval_samples_per_second": 26.448, | |
| "eval_steps_per_second": 0.156, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8411764705882353, | |
| "eval_loss": 0.344406396150589, | |
| "eval_runtime": 12.892, | |
| "eval_samples_per_second": 26.373, | |
| "eval_steps_per_second": 0.155, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.8264705882352941, | |
| "eval_loss": 0.34714558720588684, | |
| "eval_runtime": 12.9147, | |
| "eval_samples_per_second": 26.327, | |
| "eval_steps_per_second": 0.155, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.3832, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.8470588235294118, | |
| "eval_loss": 0.325613796710968, | |
| "eval_runtime": 12.891, | |
| "eval_samples_per_second": 26.375, | |
| "eval_steps_per_second": 0.155, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_accuracy": 0.8588235294117647, | |
| "eval_loss": 0.3240058124065399, | |
| "eval_runtime": 12.9745, | |
| "eval_samples_per_second": 26.205, | |
| "eval_steps_per_second": 0.154, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8411764705882353, | |
| "eval_loss": 0.3178284466266632, | |
| "eval_runtime": 13.0, | |
| "eval_samples_per_second": 26.154, | |
| "eval_steps_per_second": 0.154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.3322012424468994, | |
| "eval_runtime": 13.3231, | |
| "eval_samples_per_second": 25.52, | |
| "eval_steps_per_second": 0.15, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.8382352941176471, | |
| "eval_loss": 0.32616716623306274, | |
| "eval_runtime": 12.9394, | |
| "eval_samples_per_second": 26.276, | |
| "eval_steps_per_second": 0.155, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.3014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_accuracy": 0.8470588235294118, | |
| "eval_loss": 0.3135005831718445, | |
| "eval_runtime": 12.9318, | |
| "eval_samples_per_second": 26.292, | |
| "eval_steps_per_second": 0.155, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8588235294117647, | |
| "eval_loss": 0.3113703429698944, | |
| "eval_runtime": 12.9695, | |
| "eval_samples_per_second": 26.215, | |
| "eval_steps_per_second": 0.154, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 32, | |
| "total_flos": 2.787689868572492e+18, | |
| "train_loss": 0.47138625010848045, | |
| "train_runtime": 752.897, | |
| "train_samples_per_second": 16.225, | |
| "train_steps_per_second": 0.043 | |
| } | |
| ], | |
| "max_steps": 32, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.787689868572492e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |