| { | |
| "best_metric": 0.5625, | |
| "best_model_checkpoint": "vit-base-patch16-224-finetuned-Visual-Emotional/checkpoint-132", | |
| "epoch": 27.82608695652174, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.15, | |
| "eval_loss": 2.141930341720581, | |
| "eval_runtime": 1.0932, | |
| "eval_samples_per_second": 73.177, | |
| "eval_steps_per_second": 2.744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.1722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_accuracy": 0.1625, | |
| "eval_loss": 2.038079023361206, | |
| "eval_runtime": 1.0792, | |
| "eval_samples_per_second": 74.126, | |
| "eval_steps_per_second": 2.78, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.3, | |
| "eval_loss": 1.8728723526000977, | |
| "eval_runtime": 1.0061, | |
| "eval_samples_per_second": 79.518, | |
| "eval_steps_per_second": 2.982, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.8696, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3625, | |
| "eval_loss": 1.6683166027069092, | |
| "eval_runtime": 1.0334, | |
| "eval_samples_per_second": 77.411, | |
| "eval_steps_per_second": 2.903, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.5172284841537476, | |
| "eval_runtime": 1.0518, | |
| "eval_samples_per_second": 76.061, | |
| "eval_steps_per_second": 2.852, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.4531, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.4625, | |
| "eval_loss": 1.3959767818450928, | |
| "eval_runtime": 1.1351, | |
| "eval_samples_per_second": 70.478, | |
| "eval_steps_per_second": 2.643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.1483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.45, | |
| "eval_loss": 1.378754734992981, | |
| "eval_runtime": 1.1386, | |
| "eval_samples_per_second": 70.26, | |
| "eval_steps_per_second": 2.635, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5125, | |
| "eval_loss": 1.318593144416809, | |
| "eval_runtime": 1.0875, | |
| "eval_samples_per_second": 73.565, | |
| "eval_steps_per_second": 2.759, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.955, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "eval_accuracy": 0.475, | |
| "eval_loss": 1.2741286754608154, | |
| "eval_runtime": 1.0684, | |
| "eval_samples_per_second": 74.879, | |
| "eval_steps_per_second": 2.808, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.2990485429763794, | |
| "eval_runtime": 1.0705, | |
| "eval_samples_per_second": 74.731, | |
| "eval_steps_per_second": 2.802, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.7894, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_accuracy": 0.475, | |
| "eval_loss": 1.246220588684082, | |
| "eval_runtime": 1.0689, | |
| "eval_samples_per_second": 74.845, | |
| "eval_steps_per_second": 2.807, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.308982491493225, | |
| "eval_runtime": 1.1406, | |
| "eval_samples_per_second": 70.141, | |
| "eval_steps_per_second": 2.63, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.6769, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "eval_accuracy": 0.5125, | |
| "eval_loss": 1.2809442281723022, | |
| "eval_runtime": 1.0624, | |
| "eval_samples_per_second": 75.301, | |
| "eval_steps_per_second": 2.824, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5958, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.30197274684906, | |
| "eval_runtime": 1.0687, | |
| "eval_samples_per_second": 74.857, | |
| "eval_steps_per_second": 2.807, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.3032042980194092, | |
| "eval_runtime": 1.1451, | |
| "eval_samples_per_second": 69.863, | |
| "eval_steps_per_second": 2.62, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.5179, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.2624261379241943, | |
| "eval_runtime": 1.0678, | |
| "eval_samples_per_second": 74.923, | |
| "eval_steps_per_second": 2.81, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.2776085138320923, | |
| "eval_runtime": 1.0697, | |
| "eval_samples_per_second": 74.787, | |
| "eval_steps_per_second": 2.805, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.4808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.2705215215682983, | |
| "eval_runtime": 1.0793, | |
| "eval_samples_per_second": 74.121, | |
| "eval_steps_per_second": 2.78, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "eval_accuracy": 0.5125, | |
| "eval_loss": 1.2791962623596191, | |
| "eval_runtime": 1.1606, | |
| "eval_samples_per_second": 68.927, | |
| "eval_steps_per_second": 2.585, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.4025, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.2922601699829102, | |
| "eval_runtime": 1.0786, | |
| "eval_samples_per_second": 74.168, | |
| "eval_steps_per_second": 2.781, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 20.87, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3908, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 20.87, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.3156249523162842, | |
| "eval_runtime": 1.0785, | |
| "eval_samples_per_second": 74.178, | |
| "eval_steps_per_second": 2.782, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.3289515972137451, | |
| "eval_runtime": 1.067, | |
| "eval_samples_per_second": 74.979, | |
| "eval_steps_per_second": 2.812, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.3384, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_accuracy": 0.5625, | |
| "eval_loss": 1.314065933227539, | |
| "eval_runtime": 1.0756, | |
| "eval_samples_per_second": 74.377, | |
| "eval_steps_per_second": 2.789, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.3252638578414917, | |
| "eval_runtime": 1.0776, | |
| "eval_samples_per_second": 74.236, | |
| "eval_steps_per_second": 2.784, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3428, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.350243330001831, | |
| "eval_runtime": 1.1571, | |
| "eval_samples_per_second": 69.139, | |
| "eval_steps_per_second": 2.593, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.349756121635437, | |
| "eval_runtime": 1.0754, | |
| "eval_samples_per_second": 74.39, | |
| "eval_steps_per_second": 2.79, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.3236, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "eval_accuracy": 0.525, | |
| "eval_loss": 1.3449714183807373, | |
| "eval_runtime": 1.0921, | |
| "eval_samples_per_second": 73.256, | |
| "eval_steps_per_second": 2.747, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "learning_rate": 0.0, | |
| "loss": 0.2951, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "eval_accuracy": 0.5375, | |
| "eval_loss": 1.3424607515335083, | |
| "eval_runtime": 1.0784, | |
| "eval_samples_per_second": 74.181, | |
| "eval_steps_per_second": 2.782, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 27.83, | |
| "step": 160, | |
| "total_flos": 1.5536429521628037e+18, | |
| "train_loss": 0.7970057874917984, | |
| "train_runtime": 905.2766, | |
| "train_samples_per_second": 25.451, | |
| "train_steps_per_second": 0.177 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 160, | |
| "num_train_epochs": 32, | |
| "save_steps": 500, | |
| "total_flos": 1.5536429521628037e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |