| { |
| "best_metric": 0.65, |
| "best_model_checkpoint": "vit-base-patch16-224-finetuned-Visual-Emotional/checkpoint-80", |
| "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": 0.8695652173913043, |
| "eval_accuracy": 0.1125, |
| "eval_loss": 2.1917917728424072, |
| "eval_runtime": 1.032, |
| "eval_samples_per_second": 77.522, |
| "eval_steps_per_second": 2.907, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 2.838568925857544, |
| "learning_rate": 3.125e-05, |
| "loss": 2.1428, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.9130434782608696, |
| "eval_accuracy": 0.1625, |
| "eval_loss": 2.101666212081909, |
| "eval_runtime": 0.9957, |
| "eval_samples_per_second": 80.347, |
| "eval_steps_per_second": 3.013, |
| "step": 11 |
| }, |
| { |
| "epoch": 2.9565217391304346, |
| "eval_accuracy": 0.1875, |
| "eval_loss": 1.9293110370635986, |
| "eval_runtime": 0.9676, |
| "eval_samples_per_second": 82.676, |
| "eval_steps_per_second": 3.1, |
| "step": 17 |
| }, |
| { |
| "epoch": 3.4782608695652173, |
| "grad_norm": 3.008185625076294, |
| "learning_rate": 4.8611111111111115e-05, |
| "loss": 1.8582, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.325, |
| "eval_loss": 1.7163105010986328, |
| "eval_runtime": 0.9814, |
| "eval_samples_per_second": 81.515, |
| "eval_steps_per_second": 3.057, |
| "step": 23 |
| }, |
| { |
| "epoch": 4.869565217391305, |
| "eval_accuracy": 0.375, |
| "eval_loss": 1.57766592502594, |
| "eval_runtime": 0.9599, |
| "eval_samples_per_second": 83.345, |
| "eval_steps_per_second": 3.125, |
| "step": 28 |
| }, |
| { |
| "epoch": 5.217391304347826, |
| "grad_norm": 2.5160739421844482, |
| "learning_rate": 4.5138888888888894e-05, |
| "loss": 1.4818, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.913043478260869, |
| "eval_accuracy": 0.45, |
| "eval_loss": 1.4302526712417603, |
| "eval_runtime": 0.9609, |
| "eval_samples_per_second": 83.254, |
| "eval_steps_per_second": 3.122, |
| "step": 34 |
| }, |
| { |
| "epoch": 6.956521739130435, |
| "grad_norm": 2.911851167678833, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.1661, |
| "step": 40 |
| }, |
| { |
| "epoch": 6.956521739130435, |
| "eval_accuracy": 0.475, |
| "eval_loss": 1.3146251440048218, |
| "eval_runtime": 1.0402, |
| "eval_samples_per_second": 76.907, |
| "eval_steps_per_second": 2.884, |
| "step": 40 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.525, |
| "eval_loss": 1.2159875631332397, |
| "eval_runtime": 0.9769, |
| "eval_samples_per_second": 81.894, |
| "eval_steps_per_second": 3.071, |
| "step": 46 |
| }, |
| { |
| "epoch": 8.695652173913043, |
| "grad_norm": 2.484781503677368, |
| "learning_rate": 3.8194444444444444e-05, |
| "loss": 0.9421, |
| "step": 50 |
| }, |
| { |
| "epoch": 8.869565217391305, |
| "eval_accuracy": 0.55, |
| "eval_loss": 1.209563970565796, |
| "eval_runtime": 0.9673, |
| "eval_samples_per_second": 82.707, |
| "eval_steps_per_second": 3.102, |
| "step": 51 |
| }, |
| { |
| "epoch": 9.91304347826087, |
| "eval_accuracy": 0.5875, |
| "eval_loss": 1.1362488269805908, |
| "eval_runtime": 1.0043, |
| "eval_samples_per_second": 79.655, |
| "eval_steps_per_second": 2.987, |
| "step": 57 |
| }, |
| { |
| "epoch": 10.434782608695652, |
| "grad_norm": 2.093989372253418, |
| "learning_rate": 3.472222222222222e-05, |
| "loss": 0.8003, |
| "step": 60 |
| }, |
| { |
| "epoch": 10.956521739130435, |
| "eval_accuracy": 0.525, |
| "eval_loss": 1.1597870588302612, |
| "eval_runtime": 1.0454, |
| "eval_samples_per_second": 76.527, |
| "eval_steps_per_second": 2.87, |
| "step": 63 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.6, |
| "eval_loss": 1.0878427028656006, |
| "eval_runtime": 0.9687, |
| "eval_samples_per_second": 82.585, |
| "eval_steps_per_second": 3.097, |
| "step": 69 |
| }, |
| { |
| "epoch": 12.173913043478262, |
| "grad_norm": 2.420057535171509, |
| "learning_rate": 3.125e-05, |
| "loss": 0.678, |
| "step": 70 |
| }, |
| { |
| "epoch": 12.869565217391305, |
| "eval_accuracy": 0.6375, |
| "eval_loss": 1.0940086841583252, |
| "eval_runtime": 0.9727, |
| "eval_samples_per_second": 82.245, |
| "eval_steps_per_second": 3.084, |
| "step": 74 |
| }, |
| { |
| "epoch": 13.91304347826087, |
| "grad_norm": 2.3461201190948486, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.5888, |
| "step": 80 |
| }, |
| { |
| "epoch": 13.91304347826087, |
| "eval_accuracy": 0.65, |
| "eval_loss": 1.08188796043396, |
| "eval_runtime": 1.057, |
| "eval_samples_per_second": 75.684, |
| "eval_steps_per_second": 2.838, |
| "step": 80 |
| }, |
| { |
| "epoch": 14.956521739130435, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.0699741840362549, |
| "eval_runtime": 0.9658, |
| "eval_samples_per_second": 82.834, |
| "eval_steps_per_second": 3.106, |
| "step": 86 |
| }, |
| { |
| "epoch": 15.652173913043478, |
| "grad_norm": 2.324725866317749, |
| "learning_rate": 2.4305555555555558e-05, |
| "loss": 0.5086, |
| "step": 90 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.0758376121520996, |
| "eval_runtime": 0.962, |
| "eval_samples_per_second": 83.157, |
| "eval_steps_per_second": 3.118, |
| "step": 92 |
| }, |
| { |
| "epoch": 16.869565217391305, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.0804483890533447, |
| "eval_runtime": 0.9885, |
| "eval_samples_per_second": 80.934, |
| "eval_steps_per_second": 3.035, |
| "step": 97 |
| }, |
| { |
| "epoch": 17.391304347826086, |
| "grad_norm": 2.26944637298584, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 0.4454, |
| "step": 100 |
| }, |
| { |
| "epoch": 17.91304347826087, |
| "eval_accuracy": 0.6, |
| "eval_loss": 1.070368766784668, |
| "eval_runtime": 0.957, |
| "eval_samples_per_second": 83.597, |
| "eval_steps_per_second": 3.135, |
| "step": 103 |
| }, |
| { |
| "epoch": 18.956521739130434, |
| "eval_accuracy": 0.575, |
| "eval_loss": 1.1110748052597046, |
| "eval_runtime": 1.0435, |
| "eval_samples_per_second": 76.663, |
| "eval_steps_per_second": 2.875, |
| "step": 109 |
| }, |
| { |
| "epoch": 19.130434782608695, |
| "grad_norm": 2.693624496459961, |
| "learning_rate": 1.736111111111111e-05, |
| "loss": 0.3758, |
| "step": 110 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.5875, |
| "eval_loss": 1.061907172203064, |
| "eval_runtime": 0.9829, |
| "eval_samples_per_second": 81.391, |
| "eval_steps_per_second": 3.052, |
| "step": 115 |
| }, |
| { |
| "epoch": 20.869565217391305, |
| "grad_norm": 1.8855605125427246, |
| "learning_rate": 1.388888888888889e-05, |
| "loss": 0.3402, |
| "step": 120 |
| }, |
| { |
| "epoch": 20.869565217391305, |
| "eval_accuracy": 0.6125, |
| "eval_loss": 1.0845550298690796, |
| "eval_runtime": 0.9695, |
| "eval_samples_per_second": 82.516, |
| "eval_steps_per_second": 3.094, |
| "step": 120 |
| }, |
| { |
| "epoch": 21.91304347826087, |
| "eval_accuracy": 0.6125, |
| "eval_loss": 1.10416841506958, |
| "eval_runtime": 0.9765, |
| "eval_samples_per_second": 81.924, |
| "eval_steps_per_second": 3.072, |
| "step": 126 |
| }, |
| { |
| "epoch": 22.608695652173914, |
| "grad_norm": 2.082228660583496, |
| "learning_rate": 1.0416666666666668e-05, |
| "loss": 0.3247, |
| "step": 130 |
| }, |
| { |
| "epoch": 22.956521739130434, |
| "eval_accuracy": 0.6375, |
| "eval_loss": 1.0925999879837036, |
| "eval_runtime": 0.9933, |
| "eval_samples_per_second": 80.543, |
| "eval_steps_per_second": 3.02, |
| "step": 132 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.0907846689224243, |
| "eval_runtime": 0.9665, |
| "eval_samples_per_second": 82.776, |
| "eval_steps_per_second": 3.104, |
| "step": 138 |
| }, |
| { |
| "epoch": 24.347826086956523, |
| "grad_norm": 2.033785820007324, |
| "learning_rate": 6.944444444444445e-06, |
| "loss": 0.3142, |
| "step": 140 |
| }, |
| { |
| "epoch": 24.869565217391305, |
| "eval_accuracy": 0.6, |
| "eval_loss": 1.0963592529296875, |
| "eval_runtime": 1.0846, |
| "eval_samples_per_second": 73.76, |
| "eval_steps_per_second": 2.766, |
| "step": 143 |
| }, |
| { |
| "epoch": 25.91304347826087, |
| "eval_accuracy": 0.6125, |
| "eval_loss": 1.0998541116714478, |
| "eval_runtime": 0.9863, |
| "eval_samples_per_second": 81.114, |
| "eval_steps_per_second": 3.042, |
| "step": 149 |
| }, |
| { |
| "epoch": 26.08695652173913, |
| "grad_norm": 2.2728283405303955, |
| "learning_rate": 3.4722222222222224e-06, |
| "loss": 0.3081, |
| "step": 150 |
| }, |
| { |
| "epoch": 26.956521739130434, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.1035715341567993, |
| "eval_runtime": 1.0517, |
| "eval_samples_per_second": 76.066, |
| "eval_steps_per_second": 2.852, |
| "step": 155 |
| }, |
| { |
| "epoch": 27.82608695652174, |
| "grad_norm": 2.251145124435425, |
| "learning_rate": 0.0, |
| "loss": 0.276, |
| "step": 160 |
| }, |
| { |
| "epoch": 27.82608695652174, |
| "eval_accuracy": 0.625, |
| "eval_loss": 1.1019446849822998, |
| "eval_runtime": 1.1355, |
| "eval_samples_per_second": 70.456, |
| "eval_steps_per_second": 2.642, |
| "step": 160 |
| }, |
| { |
| "epoch": 27.82608695652174, |
| "step": 160, |
| "total_flos": 1.5536429521628037e+18, |
| "train_loss": 0.7844582810997963, |
| "train_runtime": 1191.464, |
| "train_samples_per_second": 19.338, |
| "train_steps_per_second": 0.134 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 160, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 32, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5536429521628037e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
