| { | |
| "best_metric": 0.4382284382284382, | |
| "best_model_checkpoint": "convnextv2-base-1k-224-for-pre_evaluation/checkpoint-268", | |
| "epoch": 27.906976744186046, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.5952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.29603729603729606, | |
| "eval_loss": 1.5510554313659668, | |
| "eval_runtime": 8.4324, | |
| "eval_samples_per_second": 50.875, | |
| "eval_steps_per_second": 1.66, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.5238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_accuracy": 0.34265734265734266, | |
| "eval_loss": 1.5091006755828857, | |
| "eval_runtime": 8.9811, | |
| "eval_samples_per_second": 47.767, | |
| "eval_steps_per_second": 1.559, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4881, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.34498834498834496, | |
| "eval_loss": 1.4853538274765015, | |
| "eval_runtime": 8.6991, | |
| "eval_samples_per_second": 49.315, | |
| "eval_steps_per_second": 1.609, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.4708, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3473193473193473, | |
| "eval_loss": 1.4616328477859497, | |
| "eval_runtime": 8.3701, | |
| "eval_samples_per_second": 51.254, | |
| "eval_steps_per_second": 1.673, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.4361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_accuracy": 0.34498834498834496, | |
| "eval_loss": 1.4416619539260864, | |
| "eval_runtime": 8.7032, | |
| "eval_samples_per_second": 49.292, | |
| "eval_steps_per_second": 1.609, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3764, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_accuracy": 0.3752913752913753, | |
| "eval_loss": 1.4134629964828491, | |
| "eval_runtime": 8.9398, | |
| "eval_samples_per_second": 47.988, | |
| "eval_steps_per_second": 1.566, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.3333, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.3986013986013986, | |
| "eval_loss": 1.3822472095489502, | |
| "eval_runtime": 8.7499, | |
| "eval_samples_per_second": 49.029, | |
| "eval_steps_per_second": 1.6, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.3296, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.36363636363636365, | |
| "eval_loss": 1.4111592769622803, | |
| "eval_runtime": 8.8496, | |
| "eval_samples_per_second": 48.477, | |
| "eval_steps_per_second": 1.582, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.2798, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_accuracy": 0.38927738927738925, | |
| "eval_loss": 1.4038037061691284, | |
| "eval_runtime": 8.5853, | |
| "eval_samples_per_second": 49.969, | |
| "eval_steps_per_second": 1.631, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.3129, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_accuracy": 0.3776223776223776, | |
| "eval_loss": 1.424072265625, | |
| "eval_runtime": 8.6578, | |
| "eval_samples_per_second": 49.551, | |
| "eval_steps_per_second": 1.617, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.3014, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.38927738927738925, | |
| "eval_loss": 1.356952428817749, | |
| "eval_runtime": 8.5422, | |
| "eval_samples_per_second": 50.221, | |
| "eval_steps_per_second": 1.639, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2332, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.38927738927738925, | |
| "eval_loss": 1.4072706699371338, | |
| "eval_runtime": 8.3607, | |
| "eval_samples_per_second": 51.312, | |
| "eval_steps_per_second": 1.675, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 1.212, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_accuracy": 0.40326340326340326, | |
| "eval_loss": 1.376956820487976, | |
| "eval_runtime": 8.3675, | |
| "eval_samples_per_second": 51.27, | |
| "eval_steps_per_second": 1.673, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 1.1844, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1763, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "eval_accuracy": 0.3962703962703963, | |
| "eval_loss": 1.3891488313674927, | |
| "eval_runtime": 8.5717, | |
| "eval_samples_per_second": 50.049, | |
| "eval_steps_per_second": 1.633, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.124, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.4125874125874126, | |
| "eval_loss": 1.3915237188339233, | |
| "eval_runtime": 8.5638, | |
| "eval_samples_per_second": 50.095, | |
| "eval_steps_per_second": 1.635, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 1.0963, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4149184149184149, | |
| "eval_loss": 1.4098657369613647, | |
| "eval_runtime": 8.8116, | |
| "eval_samples_per_second": 48.686, | |
| "eval_steps_per_second": 1.589, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.0547, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "eval_accuracy": 0.40326340326340326, | |
| "eval_loss": 1.4206278324127197, | |
| "eval_runtime": 8.7717, | |
| "eval_samples_per_second": 48.907, | |
| "eval_steps_per_second": 1.596, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 1.0631, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "eval_accuracy": 0.4195804195804196, | |
| "eval_loss": 1.4040827751159668, | |
| "eval_runtime": 8.3983, | |
| "eval_samples_per_second": 51.082, | |
| "eval_steps_per_second": 1.667, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.9911, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.4149184149184149, | |
| "eval_loss": 1.4271957874298096, | |
| "eval_runtime": 8.2919, | |
| "eval_samples_per_second": 51.737, | |
| "eval_steps_per_second": 1.688, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 19.53, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.005, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4219114219114219, | |
| "eval_loss": 1.42105233669281, | |
| "eval_runtime": 8.2769, | |
| "eval_samples_per_second": 51.831, | |
| "eval_steps_per_second": 1.691, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 20.47, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.9663, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 20.93, | |
| "eval_accuracy": 0.40093240093240096, | |
| "eval_loss": 1.466171145439148, | |
| "eval_runtime": 9.4718, | |
| "eval_samples_per_second": 45.292, | |
| "eval_steps_per_second": 1.478, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.9533, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "eval_accuracy": 0.43356643356643354, | |
| "eval_loss": 1.428614616394043, | |
| "eval_runtime": 8.343, | |
| "eval_samples_per_second": 51.42, | |
| "eval_steps_per_second": 1.678, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.9506, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.43123543123543123, | |
| "eval_loss": 1.413465976715088, | |
| "eval_runtime": 8.7694, | |
| "eval_samples_per_second": 48.92, | |
| "eval_steps_per_second": 1.596, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 23.26, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.8973, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.42657342657342656, | |
| "eval_loss": 1.442847728729248, | |
| "eval_runtime": 8.7464, | |
| "eval_samples_per_second": 49.049, | |
| "eval_steps_per_second": 1.601, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.8807, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 24.93, | |
| "eval_accuracy": 0.4382284382284382, | |
| "eval_loss": 1.447946548461914, | |
| "eval_runtime": 8.3339, | |
| "eval_samples_per_second": 51.476, | |
| "eval_steps_per_second": 1.68, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.8731, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "eval_accuracy": 0.4289044289044289, | |
| "eval_loss": 1.4429428577423096, | |
| "eval_runtime": 8.7998, | |
| "eval_samples_per_second": 48.751, | |
| "eval_steps_per_second": 1.591, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 26.05, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.8366, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.8472, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.43123543123543123, | |
| "eval_loss": 1.4461231231689453, | |
| "eval_runtime": 8.7766, | |
| "eval_samples_per_second": 48.88, | |
| "eval_steps_per_second": 1.595, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.8348, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "eval_accuracy": 0.43356643356643354, | |
| "eval_loss": 1.453087568283081, | |
| "eval_runtime": 8.3523, | |
| "eval_samples_per_second": 51.363, | |
| "eval_steps_per_second": 1.676, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "step": 300, | |
| "total_flos": 3.007291871298355e+18, | |
| "train_loss": 1.1542485936482747, | |
| "train_runtime": 2419.37, | |
| "train_samples_per_second": 16.864, | |
| "train_steps_per_second": 0.124 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 300, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 3.007291871298355e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |