| { |
| "best_metric": 0.8301314459049545, |
| "best_model_checkpoint": "./swin_final_model/checkpoint-88", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 198, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 5.4057230949401855, |
| "learning_rate": 4.993630286525634e-05, |
| "loss": 0.1972, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 3.5544466972351074, |
| "learning_rate": 4.9745536047023324e-05, |
| "loss": 0.1455, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6785714285714286, |
| "eval_f1": 0.40425531914893614, |
| "eval_loss": 0.1654156595468521, |
| "eval_precision": 0.3392857142857143, |
| "eval_recall": 0.5, |
| "eval_runtime": 2.0657, |
| "eval_samples_per_second": 27.11, |
| "eval_steps_per_second": 1.936, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 34.79863357543945, |
| "learning_rate": 4.942867164927899e-05, |
| "loss": 0.1528, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 3.0228710174560547, |
| "learning_rate": 4.898732434036244e-05, |
| "loss": 0.1415, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6785714285714286, |
| "eval_f1": 0.6199095022624435, |
| "eval_loss": 0.15097904205322266, |
| "eval_precision": 0.625, |
| "eval_recall": 0.6169590643274854, |
| "eval_runtime": 2.0117, |
| "eval_samples_per_second": 27.838, |
| "eval_steps_per_second": 1.988, |
| "step": 44 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 4.495301246643066, |
| "learning_rate": 4.842374312499405e-05, |
| "loss": 0.1288, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 2.2047574520111084, |
| "learning_rate": 4.774079988386296e-05, |
| "loss": 0.1213, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7142857142857143, |
| "eval_f1": 0.7005347593582887, |
| "eval_loss": 0.1337863653898239, |
| "eval_precision": 0.7025641025641025, |
| "eval_recall": 0.7309941520467836, |
| "eval_runtime": 2.1054, |
| "eval_samples_per_second": 26.599, |
| "eval_steps_per_second": 1.9, |
| "step": 66 |
| }, |
| { |
| "epoch": 3.1818181818181817, |
| "grad_norm": 1.6458451747894287, |
| "learning_rate": 4.6941974739181395e-05, |
| "loss": 0.1208, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "grad_norm": 1.5783404111862183, |
| "learning_rate": 4.6031338320779534e-05, |
| "loss": 0.1211, |
| "step": 80 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8392857142857143, |
| "eval_f1": 0.8301314459049545, |
| "eval_loss": 0.1286560595035553, |
| "eval_precision": 0.8238709677419356, |
| "eval_recall": 0.8669590643274854, |
| "eval_runtime": 1.9937, |
| "eval_samples_per_second": 28.088, |
| "eval_steps_per_second": 2.006, |
| "step": 88 |
| }, |
| { |
| "epoch": 4.090909090909091, |
| "grad_norm": 2.3769476413726807, |
| "learning_rate": 4.5013531023109014e-05, |
| "loss": 0.1136, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 2.6184587478637695, |
| "learning_rate": 4.389373935885646e-05, |
| "loss": 0.1024, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.965785264968872, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 0.1159, |
| "step": 110 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8392857142857143, |
| "eval_f1": 0.790610718737017, |
| "eval_loss": 0.08838049322366714, |
| "eval_precision": 0.8656565656565656, |
| "eval_recall": 0.7646198830409356, |
| "eval_runtime": 2.0259, |
| "eval_samples_per_second": 27.642, |
| "eval_steps_per_second": 1.974, |
| "step": 110 |
| }, |
| { |
| "epoch": 5.454545454545454, |
| "grad_norm": 6.49717378616333, |
| "learning_rate": 4.137151834863213e-05, |
| "loss": 0.1013, |
| "step": 120 |
| }, |
| { |
| "epoch": 5.909090909090909, |
| "grad_norm": 2.3494088649749756, |
| "learning_rate": 3.9981941662783674e-05, |
| "loss": 0.1307, |
| "step": 130 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7857142857142857, |
| "eval_f1": 0.6818181818181819, |
| "eval_loss": 0.13052888214588165, |
| "eval_precision": 0.88, |
| "eval_recall": 0.6666666666666666, |
| "eval_runtime": 2.0536, |
| "eval_samples_per_second": 27.269, |
| "eval_steps_per_second": 1.948, |
| "step": 132 |
| }, |
| { |
| "epoch": 6.363636363636363, |
| "grad_norm": 1.3006728887557983, |
| "learning_rate": 3.851602043638994e-05, |
| "loss": 0.0906, |
| "step": 140 |
| }, |
| { |
| "epoch": 6.818181818181818, |
| "grad_norm": 2.7580723762512207, |
| "learning_rate": 3.6981224668001424e-05, |
| "loss": 0.1085, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8214285714285714, |
| "eval_f1": 0.78125, |
| "eval_loss": 0.1015724316239357, |
| "eval_precision": 0.8095238095238095, |
| "eval_recall": 0.7660818713450293, |
| "eval_runtime": 2.0225, |
| "eval_samples_per_second": 27.688, |
| "eval_steps_per_second": 1.978, |
| "step": 154 |
| }, |
| { |
| "epoch": 7.2727272727272725, |
| "grad_norm": 2.479637384414673, |
| "learning_rate": 3.5385375325047166e-05, |
| "loss": 0.0981, |
| "step": 160 |
| }, |
| { |
| "epoch": 7.7272727272727275, |
| "grad_norm": 2.572568655014038, |
| "learning_rate": 3.3736604489977466e-05, |
| "loss": 0.0782, |
| "step": 170 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8571428571428571, |
| "eval_f1": 0.8095238095238095, |
| "eval_loss": 0.06962920725345612, |
| "eval_precision": 0.9130434782608696, |
| "eval_recall": 0.7777777777777778, |
| "eval_runtime": 2.0794, |
| "eval_samples_per_second": 26.931, |
| "eval_steps_per_second": 1.924, |
| "step": 176 |
| }, |
| { |
| "epoch": 8.181818181818182, |
| "grad_norm": 22.004362106323242, |
| "learning_rate": 3.2043313921035743e-05, |
| "loss": 0.0619, |
| "step": 180 |
| }, |
| { |
| "epoch": 8.636363636363637, |
| "grad_norm": 6.473495006561279, |
| "learning_rate": 3.0314132238824415e-05, |
| "loss": 0.0449, |
| "step": 190 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8571428571428571, |
| "eval_f1": 0.8095238095238095, |
| "eval_loss": 0.1630028635263443, |
| "eval_precision": 0.9130434782608696, |
| "eval_recall": 0.7777777777777778, |
| "eval_runtime": 2.0328, |
| "eval_samples_per_second": 27.548, |
| "eval_steps_per_second": 1.968, |
| "step": 198 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 440, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4326295022503936e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
