| { |
| "best_metric": 0.9696969696969697, |
| "best_model_checkpoint": "/kaggle/working/swin-brain-plane-classification/checkpoint-6", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.3462605476379395, |
| "learning_rate": 5e-05, |
| "loss": 0.7819, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_accuracy": 0.8484848484848485, |
| "eval_loss": 0.5965157151222229, |
| "eval_runtime": 0.2012, |
| "eval_samples_per_second": 164.047, |
| "eval_steps_per_second": 9.942, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 4.70327091217041, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.689, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_accuracy": 0.8484848484848485, |
| "eval_loss": 0.5047040581703186, |
| "eval_runtime": 0.1988, |
| "eval_samples_per_second": 165.985, |
| "eval_steps_per_second": 10.06, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 5.389795780181885, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.58, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_accuracy": 0.9090909090909091, |
| "eval_loss": 0.3954509198665619, |
| "eval_runtime": 0.196, |
| "eval_samples_per_second": 168.338, |
| "eval_steps_per_second": 10.202, |
| "step": 3 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 4.907708644866943, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.2252, |
| "step": 5 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9393939393939394, |
| "eval_loss": 0.2680495083332062, |
| "eval_runtime": 0.2061, |
| "eval_samples_per_second": 160.109, |
| "eval_steps_per_second": 9.704, |
| "step": 5 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 6.3704328536987305, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.3826, |
| "step": 6 |
| }, |
| { |
| "epoch": 4.8, |
| "eval_accuracy": 0.9696969696969697, |
| "eval_loss": 0.2426709532737732, |
| "eval_runtime": 0.2047, |
| "eval_samples_per_second": 161.236, |
| "eval_steps_per_second": 9.772, |
| "step": 6 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 5.068804740905762, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.3551, |
| "step": 7 |
| }, |
| { |
| "epoch": 5.6, |
| "eval_accuracy": 0.9090909090909091, |
| "eval_loss": 0.22610554099082947, |
| "eval_runtime": 0.2073, |
| "eval_samples_per_second": 159.187, |
| "eval_steps_per_second": 9.648, |
| "step": 7 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 3.142571449279785, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.3171, |
| "step": 8 |
| }, |
| { |
| "epoch": 6.4, |
| "eval_accuracy": 0.9393939393939394, |
| "eval_loss": 0.21792414784431458, |
| "eval_runtime": 0.1962, |
| "eval_samples_per_second": 168.154, |
| "eval_steps_per_second": 10.191, |
| "step": 8 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 4.538871765136719, |
| "learning_rate": 0.0, |
| "loss": 0.1802, |
| "step": 10 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9393939393939394, |
| "eval_loss": 0.21566466987133026, |
| "eval_runtime": 0.219, |
| "eval_samples_per_second": 150.655, |
| "eval_steps_per_second": 9.131, |
| "step": 10 |
| }, |
| { |
| "epoch": 8.0, |
| "step": 10, |
| "total_flos": 3.121999450369229e+16, |
| "train_loss": 0.3916594386100769, |
| "train_runtime": 22.6465, |
| "train_samples_per_second": 69.326, |
| "train_steps_per_second": 0.442 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "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": 3.121999450369229e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
