| { | |
| "best_metric": 0.44989213347435, | |
| "best_model_checkpoint": "sea_animals_image_detection/checkpoint-6840", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 6840, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7951719092904169, | |
| "eval_loss": 2.152780294418335, | |
| "eval_runtime": 27.056, | |
| "eval_samples_per_second": 101.05, | |
| "eval_steps_per_second": 12.64, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.470588235294119e-06, | |
| "loss": 2.4104, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8555230431602048, | |
| "eval_loss": 1.5588719844818115, | |
| "eval_runtime": 26.6265, | |
| "eval_samples_per_second": 102.68, | |
| "eval_steps_per_second": 12.844, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.88235294117647e-06, | |
| "loss": 1.4121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8822238478419897, | |
| "eval_loss": 1.2037461996078491, | |
| "eval_runtime": 26.9677, | |
| "eval_samples_per_second": 101.381, | |
| "eval_steps_per_second": 12.682, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8935625457205559, | |
| "eval_loss": 0.9822039008140564, | |
| "eval_runtime": 26.4016, | |
| "eval_samples_per_second": 103.555, | |
| "eval_steps_per_second": 12.954, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 8.294117647058825e-06, | |
| "loss": 0.9335, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9041697147037308, | |
| "eval_loss": 0.8228352665901184, | |
| "eval_runtime": 27.2507, | |
| "eval_samples_per_second": 100.328, | |
| "eval_steps_per_second": 12.55, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 7.705882352941178e-06, | |
| "loss": 0.6607, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9012435991221653, | |
| "eval_loss": 0.7257607579231262, | |
| "eval_runtime": 26.6826, | |
| "eval_samples_per_second": 102.464, | |
| "eval_steps_per_second": 12.817, | |
| "step": 2052 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9030724213606437, | |
| "eval_loss": 0.6461441516876221, | |
| "eval_runtime": 26.5418, | |
| "eval_samples_per_second": 103.007, | |
| "eval_steps_per_second": 12.885, | |
| "step": 2394 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 7.11764705882353e-06, | |
| "loss": 0.485, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9034381858083395, | |
| "eval_loss": 0.5806209444999695, | |
| "eval_runtime": 28.3386, | |
| "eval_samples_per_second": 96.476, | |
| "eval_steps_per_second": 12.068, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 6.529411764705883e-06, | |
| "loss": 0.3676, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8994147768836869, | |
| "eval_loss": 0.5495482087135315, | |
| "eval_runtime": 28.0784, | |
| "eval_samples_per_second": 97.37, | |
| "eval_steps_per_second": 12.18, | |
| "step": 3078 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9019751280175567, | |
| "eval_loss": 0.5101125240325928, | |
| "eval_runtime": 26.8282, | |
| "eval_samples_per_second": 101.908, | |
| "eval_steps_per_second": 12.748, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 5.941176470588236e-06, | |
| "loss": 0.2796, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8997805413313826, | |
| "eval_loss": 0.4954698383808136, | |
| "eval_runtime": 29.3485, | |
| "eval_samples_per_second": 93.156, | |
| "eval_steps_per_second": 11.653, | |
| "step": 3762 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 5.352941176470589e-06, | |
| "loss": 0.2236, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9012435991221653, | |
| "eval_loss": 0.4771639108657837, | |
| "eval_runtime": 26.8132, | |
| "eval_samples_per_second": 101.965, | |
| "eval_steps_per_second": 12.755, | |
| "step": 4104 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8979517190929042, | |
| "eval_loss": 0.47096940875053406, | |
| "eval_runtime": 27.6019, | |
| "eval_samples_per_second": 99.051, | |
| "eval_steps_per_second": 12.39, | |
| "step": 4446 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 4.764705882352941e-06, | |
| "loss": 0.1847, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8986832479882956, | |
| "eval_loss": 0.46488723158836365, | |
| "eval_runtime": 28.4412, | |
| "eval_samples_per_second": 96.128, | |
| "eval_steps_per_second": 12.025, | |
| "step": 4788 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 4.176470588235295e-06, | |
| "loss": 0.1505, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9008778346744697, | |
| "eval_loss": 0.455506831407547, | |
| "eval_runtime": 27.2614, | |
| "eval_samples_per_second": 100.288, | |
| "eval_steps_per_second": 12.545, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8990490124359912, | |
| "eval_loss": 0.4557651877403259, | |
| "eval_runtime": 26.9577, | |
| "eval_samples_per_second": 101.418, | |
| "eval_steps_per_second": 12.687, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 3.5882352941176475e-06, | |
| "loss": 0.129, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9023408924652524, | |
| "eval_loss": 0.45066457986831665, | |
| "eval_runtime": 27.4851, | |
| "eval_samples_per_second": 99.472, | |
| "eval_steps_per_second": 12.443, | |
| "step": 5814 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1116, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8983174835405998, | |
| "eval_loss": 0.4530565142631531, | |
| "eval_runtime": 27.2399, | |
| "eval_samples_per_second": 100.368, | |
| "eval_steps_per_second": 12.555, | |
| "step": 6156 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8986832479882956, | |
| "eval_loss": 0.45476871728897095, | |
| "eval_runtime": 27.1006, | |
| "eval_samples_per_second": 100.883, | |
| "eval_steps_per_second": 12.62, | |
| "step": 6498 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.411764705882353e-06, | |
| "loss": 0.0964, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8997805413313826, | |
| "eval_loss": 0.44989213347435, | |
| "eval_runtime": 27.224, | |
| "eval_samples_per_second": 100.426, | |
| "eval_steps_per_second": 12.562, | |
| "step": 6840 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8550, | |
| "num_train_epochs": 25, | |
| "save_steps": 500, | |
| "total_flos": 1.6946037530587791e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |