| { | |
| "best_metric": 0.9491525423728814, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-52", | |
| "epoch": 39.94117647058823, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.11864406779661017, | |
| "eval_loss": 1.888161540031433, | |
| "eval_runtime": 4.1522, | |
| "eval_samples_per_second": 14.209, | |
| "eval_steps_per_second": 0.482, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.3559322033898305, | |
| "eval_loss": 1.67988920211792, | |
| "eval_runtime": 4.5824, | |
| "eval_samples_per_second": 12.875, | |
| "eval_steps_per_second": 0.436, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_accuracy": 0.576271186440678, | |
| "eval_loss": 1.4259672164916992, | |
| "eval_runtime": 3.9572, | |
| "eval_samples_per_second": 14.91, | |
| "eval_steps_per_second": 0.505, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.6779661016949152, | |
| "eval_loss": 1.1092320680618286, | |
| "eval_runtime": 4.365, | |
| "eval_samples_per_second": 13.517, | |
| "eval_steps_per_second": 0.458, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.7242, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_accuracy": 0.7457627118644068, | |
| "eval_loss": 0.8652871251106262, | |
| "eval_runtime": 3.9966, | |
| "eval_samples_per_second": 14.762, | |
| "eval_steps_per_second": 0.5, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "eval_accuracy": 0.7796610169491526, | |
| "eval_loss": 0.6787465810775757, | |
| "eval_runtime": 4.26, | |
| "eval_samples_per_second": 13.85, | |
| "eval_steps_per_second": 0.469, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_accuracy": 0.8305084745762712, | |
| "eval_loss": 0.5506174564361572, | |
| "eval_runtime": 4.3376, | |
| "eval_samples_per_second": 13.602, | |
| "eval_steps_per_second": 0.461, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_accuracy": 0.8813559322033898, | |
| "eval_loss": 0.4173695743083954, | |
| "eval_runtime": 3.9498, | |
| "eval_samples_per_second": 14.937, | |
| "eval_steps_per_second": 0.506, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.8813559322033898, | |
| "eval_loss": 0.3643472194671631, | |
| "eval_runtime": 4.2828, | |
| "eval_samples_per_second": 13.776, | |
| "eval_steps_per_second": 0.467, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.8337, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.2679864466190338, | |
| "eval_runtime": 4.0645, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 0.492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "eval_accuracy": 0.8983050847457628, | |
| "eval_loss": 0.2705465257167816, | |
| "eval_runtime": 3.9127, | |
| "eval_samples_per_second": 15.079, | |
| "eval_steps_per_second": 0.511, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "eval_accuracy": 0.9152542372881356, | |
| "eval_loss": 0.2270025759935379, | |
| "eval_runtime": 4.2904, | |
| "eval_samples_per_second": 13.752, | |
| "eval_steps_per_second": 0.466, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.17896686494350433, | |
| "eval_runtime": 4.2572, | |
| "eval_samples_per_second": 13.859, | |
| "eval_steps_per_second": 0.47, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.16937005519866943, | |
| "eval_runtime": 3.9569, | |
| "eval_samples_per_second": 14.911, | |
| "eval_steps_per_second": 0.505, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.493, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "eval_accuracy": 0.9152542372881356, | |
| "eval_loss": 0.17763535678386688, | |
| "eval_runtime": 4.2916, | |
| "eval_samples_per_second": 13.748, | |
| "eval_steps_per_second": 0.466, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.1831100881099701, | |
| "eval_runtime": 4.3067, | |
| "eval_samples_per_second": 13.7, | |
| "eval_steps_per_second": 0.464, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.17647486925125122, | |
| "eval_runtime": 3.9721, | |
| "eval_samples_per_second": 14.854, | |
| "eval_steps_per_second": 0.504, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.15746894478797913, | |
| "eval_runtime": 4.3018, | |
| "eval_samples_per_second": 13.715, | |
| "eval_steps_per_second": 0.465, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.14716410636901855, | |
| "eval_runtime": 4.2957, | |
| "eval_samples_per_second": 13.735, | |
| "eval_steps_per_second": 0.466, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3966, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.13601559400558472, | |
| "eval_runtime": 3.8795, | |
| "eval_samples_per_second": 15.208, | |
| "eval_steps_per_second": 0.516, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.1448136419057846, | |
| "eval_runtime": 4.2669, | |
| "eval_samples_per_second": 13.827, | |
| "eval_steps_per_second": 0.469, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.16579066216945648, | |
| "eval_runtime": 4.1904, | |
| "eval_samples_per_second": 14.08, | |
| "eval_steps_per_second": 0.477, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 22.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.1652187556028366, | |
| "eval_runtime": 3.894, | |
| "eval_samples_per_second": 15.152, | |
| "eval_steps_per_second": 0.514, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.15646469593048096, | |
| "eval_runtime": 4.3539, | |
| "eval_samples_per_second": 13.551, | |
| "eval_steps_per_second": 0.459, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 24.94, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.3645, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 24.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.1700868457555771, | |
| "eval_runtime": 3.9704, | |
| "eval_samples_per_second": 14.86, | |
| "eval_steps_per_second": 0.504, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.18298125267028809, | |
| "eval_runtime": 3.9238, | |
| "eval_samples_per_second": 15.036, | |
| "eval_steps_per_second": 0.51, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "eval_accuracy": 0.9322033898305084, | |
| "eval_loss": 0.16823288798332214, | |
| "eval_runtime": 5.0017, | |
| "eval_samples_per_second": 11.796, | |
| "eval_steps_per_second": 0.4, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.1410430371761322, | |
| "eval_runtime": 4.472, | |
| "eval_samples_per_second": 13.193, | |
| "eval_steps_per_second": 0.447, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 28.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12907052040100098, | |
| "eval_runtime": 3.8982, | |
| "eval_samples_per_second": 15.135, | |
| "eval_steps_per_second": 0.513, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3358, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12478938698768616, | |
| "eval_runtime": 4.248, | |
| "eval_samples_per_second": 13.889, | |
| "eval_steps_per_second": 0.471, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 30.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12751266360282898, | |
| "eval_runtime": 4.3163, | |
| "eval_samples_per_second": 13.669, | |
| "eval_steps_per_second": 0.463, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.1257278025150299, | |
| "eval_runtime": 3.9781, | |
| "eval_samples_per_second": 14.831, | |
| "eval_steps_per_second": 0.503, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 32.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12883280217647552, | |
| "eval_runtime": 4.3885, | |
| "eval_samples_per_second": 13.444, | |
| "eval_steps_per_second": 0.456, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 33.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12463054060935974, | |
| "eval_runtime": 4.1226, | |
| "eval_samples_per_second": 14.311, | |
| "eval_steps_per_second": 0.485, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 34.94, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3049, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 34.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12190988659858704, | |
| "eval_runtime": 3.969, | |
| "eval_samples_per_second": 14.865, | |
| "eval_steps_per_second": 0.504, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 35.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12239754945039749, | |
| "eval_runtime": 4.3753, | |
| "eval_samples_per_second": 13.485, | |
| "eval_steps_per_second": 0.457, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12457720935344696, | |
| "eval_runtime": 4.1325, | |
| "eval_samples_per_second": 14.277, | |
| "eval_steps_per_second": 0.484, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 37.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12425000220537186, | |
| "eval_runtime": 3.9849, | |
| "eval_samples_per_second": 14.806, | |
| "eval_steps_per_second": 0.502, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 38.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12478892505168915, | |
| "eval_runtime": 4.257, | |
| "eval_samples_per_second": 13.86, | |
| "eval_steps_per_second": 0.47, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 39.94, | |
| "learning_rate": 0.0, | |
| "loss": 0.2962, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 39.94, | |
| "eval_accuracy": 0.9491525423728814, | |
| "eval_loss": 0.12530554831027985, | |
| "eval_runtime": 4.3582, | |
| "eval_samples_per_second": 13.538, | |
| "eval_steps_per_second": 0.459, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 39.94, | |
| "step": 160, | |
| "total_flos": 5.226950410064732e+17, | |
| "train_loss": 0.5936037123203277, | |
| "train_runtime": 2238.3601, | |
| "train_samples_per_second": 9.4, | |
| "train_steps_per_second": 0.071 | |
| } | |
| ], | |
| "max_steps": 160, | |
| "num_train_epochs": 40, | |
| "total_flos": 5.226950410064732e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |