| { |
| "best_metric": 0.5961538461538461, |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-DAV6/checkpoint-348", |
| "epoch": 30.0, |
| "eval_steps": 500, |
| "global_step": 360, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 4.056356430053711, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": 1.65, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.34615384615384615, |
| "eval_loss": 1.563740849494934, |
| "eval_runtime": 1.053, |
| "eval_samples_per_second": 49.382, |
| "eval_steps_per_second": 0.95, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 4.256997108459473, |
| "learning_rate": 1.1111111111111113e-05, |
| "loss": 1.5819, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.3269230769230769, |
| "eval_loss": 1.4962464570999146, |
| "eval_runtime": 0.9357, |
| "eval_samples_per_second": 55.576, |
| "eval_steps_per_second": 1.069, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 6.2425994873046875, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.4527, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.46153846153846156, |
| "eval_loss": 1.3413437604904175, |
| "eval_runtime": 1.3322, |
| "eval_samples_per_second": 39.032, |
| "eval_steps_per_second": 0.751, |
| "step": 36 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 8.280574798583984, |
| "learning_rate": 1.9753086419753087e-05, |
| "loss": 1.2853, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.4423076923076923, |
| "eval_loss": 1.2034096717834473, |
| "eval_runtime": 0.9656, |
| "eval_samples_per_second": 53.85, |
| "eval_steps_per_second": 1.036, |
| "step": 48 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 10.168972969055176, |
| "learning_rate": 1.9135802469135804e-05, |
| "loss": 1.0518, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 17.288293838500977, |
| "learning_rate": 1.851851851851852e-05, |
| "loss": 1.0185, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.4807692307692308, |
| "eval_loss": 1.1204253435134888, |
| "eval_runtime": 0.9698, |
| "eval_samples_per_second": 53.62, |
| "eval_steps_per_second": 1.031, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 9.274469375610352, |
| "learning_rate": 1.7901234567901236e-05, |
| "loss": 0.8102, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.4807692307692308, |
| "eval_loss": 1.100393533706665, |
| "eval_runtime": 1.2608, |
| "eval_samples_per_second": 41.245, |
| "eval_steps_per_second": 0.793, |
| "step": 72 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 14.213850975036621, |
| "learning_rate": 1.728395061728395e-05, |
| "loss": 0.7477, |
| "step": 80 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.4807692307692308, |
| "eval_loss": 1.1704537868499756, |
| "eval_runtime": 0.9485, |
| "eval_samples_per_second": 54.823, |
| "eval_steps_per_second": 1.054, |
| "step": 84 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 9.665724754333496, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.6684, |
| "step": 90 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.5192307692307693, |
| "eval_loss": 1.0245306491851807, |
| "eval_runtime": 0.9459, |
| "eval_samples_per_second": 54.973, |
| "eval_steps_per_second": 1.057, |
| "step": 96 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 9.731916427612305, |
| "learning_rate": 1.6049382716049385e-05, |
| "loss": 0.6297, |
| "step": 100 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.0009715557098389, |
| "eval_runtime": 0.9584, |
| "eval_samples_per_second": 54.259, |
| "eval_steps_per_second": 1.043, |
| "step": 108 |
| }, |
| { |
| "epoch": 9.166666666666666, |
| "grad_norm": 12.01754093170166, |
| "learning_rate": 1.54320987654321e-05, |
| "loss": 0.5887, |
| "step": 110 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 14.239096641540527, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.5453, |
| "step": 120 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.4807692307692308, |
| "eval_loss": 1.19045889377594, |
| "eval_runtime": 1.3161, |
| "eval_samples_per_second": 39.51, |
| "eval_steps_per_second": 0.76, |
| "step": 120 |
| }, |
| { |
| "epoch": 10.833333333333334, |
| "grad_norm": 18.023754119873047, |
| "learning_rate": 1.4197530864197532e-05, |
| "loss": 0.5496, |
| "step": 130 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.4807692307692308, |
| "eval_loss": 1.122729778289795, |
| "eval_runtime": 0.9582, |
| "eval_samples_per_second": 54.268, |
| "eval_steps_per_second": 1.044, |
| "step": 132 |
| }, |
| { |
| "epoch": 11.666666666666666, |
| "grad_norm": 10.79216194152832, |
| "learning_rate": 1.3580246913580248e-05, |
| "loss": 0.4993, |
| "step": 140 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 0.9618959426879883, |
| "eval_runtime": 0.9743, |
| "eval_samples_per_second": 53.369, |
| "eval_steps_per_second": 1.026, |
| "step": 144 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 15.657975196838379, |
| "learning_rate": 1.2962962962962964e-05, |
| "loss": 0.4297, |
| "step": 150 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.5192307692307693, |
| "eval_loss": 1.0743120908737183, |
| "eval_runtime": 1.3502, |
| "eval_samples_per_second": 38.513, |
| "eval_steps_per_second": 0.741, |
| "step": 156 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 11.634675025939941, |
| "learning_rate": 1.234567901234568e-05, |
| "loss": 0.4459, |
| "step": 160 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.0194507837295532, |
| "eval_runtime": 0.9767, |
| "eval_samples_per_second": 53.239, |
| "eval_steps_per_second": 1.024, |
| "step": 168 |
| }, |
| { |
| "epoch": 14.166666666666666, |
| "grad_norm": 10.06187629699707, |
| "learning_rate": 1.1728395061728398e-05, |
| "loss": 0.4395, |
| "step": 170 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 12.079572677612305, |
| "learning_rate": 1.1111111111111113e-05, |
| "loss": 0.4219, |
| "step": 180 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.5, |
| "eval_loss": 1.0888128280639648, |
| "eval_runtime": 0.9857, |
| "eval_samples_per_second": 52.756, |
| "eval_steps_per_second": 1.015, |
| "step": 180 |
| }, |
| { |
| "epoch": 15.833333333333334, |
| "grad_norm": 10.321825981140137, |
| "learning_rate": 1.0493827160493827e-05, |
| "loss": 0.3742, |
| "step": 190 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.5769230769230769, |
| "eval_loss": 1.0122987031936646, |
| "eval_runtime": 0.9616, |
| "eval_samples_per_second": 54.074, |
| "eval_steps_per_second": 1.04, |
| "step": 192 |
| }, |
| { |
| "epoch": 16.666666666666668, |
| "grad_norm": 11.117116928100586, |
| "learning_rate": 9.876543209876543e-06, |
| "loss": 0.4603, |
| "step": 200 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.5192307692307693, |
| "eval_loss": 1.0502595901489258, |
| "eval_runtime": 1.341, |
| "eval_samples_per_second": 38.778, |
| "eval_steps_per_second": 0.746, |
| "step": 204 |
| }, |
| { |
| "epoch": 17.5, |
| "grad_norm": 11.7776460647583, |
| "learning_rate": 9.25925925925926e-06, |
| "loss": 0.3607, |
| "step": 210 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.1304657459259033, |
| "eval_runtime": 0.9684, |
| "eval_samples_per_second": 53.695, |
| "eval_steps_per_second": 1.033, |
| "step": 216 |
| }, |
| { |
| "epoch": 18.333333333333332, |
| "grad_norm": 9.46719741821289, |
| "learning_rate": 8.641975308641975e-06, |
| "loss": 0.3399, |
| "step": 220 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.5384615384615384, |
| "eval_loss": 1.1327446699142456, |
| "eval_runtime": 1.3627, |
| "eval_samples_per_second": 38.16, |
| "eval_steps_per_second": 0.734, |
| "step": 228 |
| }, |
| { |
| "epoch": 19.166666666666668, |
| "grad_norm": 11.968366622924805, |
| "learning_rate": 8.024691358024692e-06, |
| "loss": 0.3505, |
| "step": 230 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 18.940866470336914, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.3422, |
| "step": 240 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.5192307692307693, |
| "eval_loss": 1.1124639511108398, |
| "eval_runtime": 0.9833, |
| "eval_samples_per_second": 52.884, |
| "eval_steps_per_second": 1.017, |
| "step": 240 |
| }, |
| { |
| "epoch": 20.833333333333332, |
| "grad_norm": 8.889911651611328, |
| "learning_rate": 6.790123456790124e-06, |
| "loss": 0.3254, |
| "step": 250 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_accuracy": 0.5769230769230769, |
| "eval_loss": 1.0242624282836914, |
| "eval_runtime": 0.9799, |
| "eval_samples_per_second": 53.065, |
| "eval_steps_per_second": 1.02, |
| "step": 252 |
| }, |
| { |
| "epoch": 21.666666666666668, |
| "grad_norm": 10.384934425354004, |
| "learning_rate": 6.17283950617284e-06, |
| "loss": 0.3363, |
| "step": 260 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.0753213167190552, |
| "eval_runtime": 1.3339, |
| "eval_samples_per_second": 38.982, |
| "eval_steps_per_second": 0.75, |
| "step": 264 |
| }, |
| { |
| "epoch": 22.5, |
| "grad_norm": 14.690075874328613, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": 0.3203, |
| "step": 270 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.0778136253356934, |
| "eval_runtime": 0.9785, |
| "eval_samples_per_second": 53.142, |
| "eval_steps_per_second": 1.022, |
| "step": 276 |
| }, |
| { |
| "epoch": 23.333333333333332, |
| "grad_norm": 15.333271026611328, |
| "learning_rate": 4.938271604938272e-06, |
| "loss": 0.3248, |
| "step": 280 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_accuracy": 0.5384615384615384, |
| "eval_loss": 1.110023021697998, |
| "eval_runtime": 1.3581, |
| "eval_samples_per_second": 38.289, |
| "eval_steps_per_second": 0.736, |
| "step": 288 |
| }, |
| { |
| "epoch": 24.166666666666668, |
| "grad_norm": 15.043098449707031, |
| "learning_rate": 4.3209876543209875e-06, |
| "loss": 0.2772, |
| "step": 290 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 11.997562408447266, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.2446, |
| "step": 300 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.5576923076923077, |
| "eval_loss": 1.077340006828308, |
| "eval_runtime": 0.9829, |
| "eval_samples_per_second": 52.906, |
| "eval_steps_per_second": 1.017, |
| "step": 300 |
| }, |
| { |
| "epoch": 25.833333333333332, |
| "grad_norm": 12.851033210754395, |
| "learning_rate": 3.08641975308642e-06, |
| "loss": 0.3058, |
| "step": 310 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_accuracy": 0.5769230769230769, |
| "eval_loss": 1.0874526500701904, |
| "eval_runtime": 0.9815, |
| "eval_samples_per_second": 52.981, |
| "eval_steps_per_second": 1.019, |
| "step": 312 |
| }, |
| { |
| "epoch": 26.666666666666668, |
| "grad_norm": 9.959371566772461, |
| "learning_rate": 2.469135802469136e-06, |
| "loss": 0.254, |
| "step": 320 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_accuracy": 0.5769230769230769, |
| "eval_loss": 1.0672507286071777, |
| "eval_runtime": 1.3542, |
| "eval_samples_per_second": 38.398, |
| "eval_steps_per_second": 0.738, |
| "step": 324 |
| }, |
| { |
| "epoch": 27.5, |
| "grad_norm": 11.765765190124512, |
| "learning_rate": 1.8518518518518519e-06, |
| "loss": 0.2644, |
| "step": 330 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_accuracy": 0.5769230769230769, |
| "eval_loss": 1.1026289463043213, |
| "eval_runtime": 0.975, |
| "eval_samples_per_second": 53.334, |
| "eval_steps_per_second": 1.026, |
| "step": 336 |
| }, |
| { |
| "epoch": 28.333333333333332, |
| "grad_norm": 14.380167961120605, |
| "learning_rate": 1.234567901234568e-06, |
| "loss": 0.2962, |
| "step": 340 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_accuracy": 0.5961538461538461, |
| "eval_loss": 1.089858889579773, |
| "eval_runtime": 0.9732, |
| "eval_samples_per_second": 53.434, |
| "eval_steps_per_second": 1.028, |
| "step": 348 |
| }, |
| { |
| "epoch": 29.166666666666668, |
| "grad_norm": 10.202056884765625, |
| "learning_rate": 6.17283950617284e-07, |
| "loss": 0.28, |
| "step": 350 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 9.827922821044922, |
| "learning_rate": 0.0, |
| "loss": 0.2579, |
| "step": 360 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_accuracy": 0.5961538461538461, |
| "eval_loss": 1.0815707445144653, |
| "eval_runtime": 1.281, |
| "eval_samples_per_second": 40.594, |
| "eval_steps_per_second": 0.781, |
| "step": 360 |
| }, |
| { |
| "epoch": 30.0, |
| "step": 360, |
| "total_flos": 7.115852825454182e+17, |
| "train_loss": 0.5703052765793271, |
| "train_runtime": 560.5356, |
| "train_samples_per_second": 39.016, |
| "train_steps_per_second": 0.642 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 360, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "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": 7.115852825454182e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
