| { |
| "best_metric": 0.8856447688564477, |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-183", |
| "epoch": 9.836065573770492, |
| "eval_steps": 500, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 4.936834812164307, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.9945, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 2.4745380878448486, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.5619, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 3.340874433517456, |
| "learning_rate": 5e-05, |
| "loss": 0.4494, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "eval_accuracy": 0.8223844282238443, |
| "eval_loss": 0.495254784822464, |
| "eval_runtime": 47.0869, |
| "eval_samples_per_second": 8.729, |
| "eval_steps_per_second": 0.149, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3114754098360657, |
| "grad_norm": 2.102787733078003, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.3852, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.639344262295082, |
| "grad_norm": 1.9069348573684692, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 0.3536, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9672131147540983, |
| "grad_norm": 2.154897451400757, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.3369, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8832116788321168, |
| "eval_loss": 0.3206270635128021, |
| "eval_runtime": 46.9296, |
| "eval_samples_per_second": 8.758, |
| "eval_steps_per_second": 0.149, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.2950819672131146, |
| "grad_norm": 2.829212188720703, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.3171, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.6229508196721314, |
| "grad_norm": 2.4426212310791016, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.3019, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.9508196721311473, |
| "grad_norm": 2.601443290710449, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.3173, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.9836065573770494, |
| "eval_accuracy": 0.8734793187347932, |
| "eval_loss": 0.3022870123386383, |
| "eval_runtime": 47.009, |
| "eval_samples_per_second": 8.743, |
| "eval_steps_per_second": 0.149, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.278688524590164, |
| "grad_norm": 1.8936508893966675, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.3082, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.6065573770491803, |
| "grad_norm": 2.6445701122283936, |
| "learning_rate": 3.518518518518519e-05, |
| "loss": 0.2837, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.9344262295081966, |
| "grad_norm": 4.797309875488281, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.2865, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8734793187347932, |
| "eval_loss": 0.2900189161300659, |
| "eval_runtime": 46.7107, |
| "eval_samples_per_second": 8.799, |
| "eval_steps_per_second": 0.15, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.262295081967213, |
| "grad_norm": 2.120328664779663, |
| "learning_rate": 3.148148148148148e-05, |
| "loss": 0.2838, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.590163934426229, |
| "grad_norm": 2.334688663482666, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.2709, |
| "step": 140 |
| }, |
| { |
| "epoch": 4.918032786885246, |
| "grad_norm": 2.006906747817993, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.2612, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.983606557377049, |
| "eval_accuracy": 0.8710462287104623, |
| "eval_loss": 0.28622761368751526, |
| "eval_runtime": 47.1214, |
| "eval_samples_per_second": 8.722, |
| "eval_steps_per_second": 0.149, |
| "step": 152 |
| }, |
| { |
| "epoch": 5.245901639344262, |
| "grad_norm": 2.6484014987945557, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.2525, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.573770491803279, |
| "grad_norm": 2.379870891571045, |
| "learning_rate": 2.4074074074074074e-05, |
| "loss": 0.2548, |
| "step": 170 |
| }, |
| { |
| "epoch": 5.901639344262295, |
| "grad_norm": 2.97287917137146, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.2412, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8856447688564477, |
| "eval_loss": 0.26367661356925964, |
| "eval_runtime": 46.9018, |
| "eval_samples_per_second": 8.763, |
| "eval_steps_per_second": 0.149, |
| "step": 183 |
| }, |
| { |
| "epoch": 6.229508196721311, |
| "grad_norm": 2.9260308742523193, |
| "learning_rate": 2.037037037037037e-05, |
| "loss": 0.246, |
| "step": 190 |
| }, |
| { |
| "epoch": 6.557377049180328, |
| "grad_norm": 3.2257614135742188, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.2434, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.885245901639344, |
| "grad_norm": 2.4753129482269287, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.2533, |
| "step": 210 |
| }, |
| { |
| "epoch": 6.983606557377049, |
| "eval_accuracy": 0.878345498783455, |
| "eval_loss": 0.27688971161842346, |
| "eval_runtime": 46.8021, |
| "eval_samples_per_second": 8.782, |
| "eval_steps_per_second": 0.15, |
| "step": 213 |
| }, |
| { |
| "epoch": 7.213114754098361, |
| "grad_norm": 2.772411584854126, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.2399, |
| "step": 220 |
| }, |
| { |
| "epoch": 7.540983606557377, |
| "grad_norm": 2.4606740474700928, |
| "learning_rate": 1.2962962962962962e-05, |
| "loss": 0.2454, |
| "step": 230 |
| }, |
| { |
| "epoch": 7.868852459016393, |
| "grad_norm": 2.5486361980438232, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.2413, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8832116788321168, |
| "eval_loss": 0.26485782861709595, |
| "eval_runtime": 47.0631, |
| "eval_samples_per_second": 8.733, |
| "eval_steps_per_second": 0.149, |
| "step": 244 |
| }, |
| { |
| "epoch": 8.19672131147541, |
| "grad_norm": 4.631506443023682, |
| "learning_rate": 9.259259259259259e-06, |
| "loss": 0.2199, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.524590163934427, |
| "grad_norm": 2.3710556030273438, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.2372, |
| "step": 260 |
| }, |
| { |
| "epoch": 8.852459016393443, |
| "grad_norm": 4.1779608726501465, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.2139, |
| "step": 270 |
| }, |
| { |
| "epoch": 8.98360655737705, |
| "eval_accuracy": 0.878345498783455, |
| "eval_loss": 0.2632748484611511, |
| "eval_runtime": 46.7653, |
| "eval_samples_per_second": 8.789, |
| "eval_steps_per_second": 0.15, |
| "step": 274 |
| }, |
| { |
| "epoch": 9.180327868852459, |
| "grad_norm": 2.4798853397369385, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.2365, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.508196721311476, |
| "grad_norm": 3.2969157695770264, |
| "learning_rate": 1.8518518518518519e-06, |
| "loss": 0.2242, |
| "step": 290 |
| }, |
| { |
| "epoch": 9.836065573770492, |
| "grad_norm": 2.2613918781280518, |
| "learning_rate": 0.0, |
| "loss": 0.2087, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.836065573770492, |
| "eval_accuracy": 0.8807785888077859, |
| "eval_loss": 0.2599342465400696, |
| "eval_runtime": 47.0372, |
| "eval_samples_per_second": 8.738, |
| "eval_steps_per_second": 0.149, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.836065573770492, |
| "step": 300, |
| "total_flos": 1.9063087726729052e+18, |
| "train_loss": 0.3090126927693685, |
| "train_runtime": 8089.4797, |
| "train_samples_per_second": 9.637, |
| "train_steps_per_second": 0.037 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 1.9063087726729052e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
