| { |
| "best_metric": 0.9989996083884333, |
| "best_model_checkpoint": "./swinv2-ai-vs-human/checkpoint-500", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.027848800644278526, |
| "learning_rate": 4.804e-05, |
| "loss": 0.0547, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.19660699367523193, |
| "learning_rate": 4.604e-05, |
| "loss": 0.0147, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.003552996786311269, |
| "learning_rate": 4.4040000000000005e-05, |
| "loss": 0.0043, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.13383957743644714, |
| "learning_rate": 4.2040000000000004e-05, |
| "loss": 0.0061, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.001965691801160574, |
| "learning_rate": 4.004e-05, |
| "loss": 0.0015, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.998, |
| "eval_f1": 0.998, |
| "eval_loss": 0.006758809555321932, |
| "eval_runtime": 42.7981, |
| "eval_samples_per_second": 23.366, |
| "eval_steps_per_second": 2.921, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.0014331854181364179, |
| "learning_rate": 3.804e-05, |
| "loss": 0.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.0010366585338488221, |
| "learning_rate": 3.604e-05, |
| "loss": 0.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.0017909109592437744, |
| "learning_rate": 3.404e-05, |
| "loss": 0.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.0012696795165538788, |
| "learning_rate": 3.2040000000000005e-05, |
| "loss": 0.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.12196046859025955, |
| "learning_rate": 3.004e-05, |
| "loss": 0.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.999, |
| "eval_f1": 0.9989996083884333, |
| "eval_loss": 0.006264013703912497, |
| "eval_runtime": 42.8166, |
| "eval_samples_per_second": 23.355, |
| "eval_steps_per_second": 2.919, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.0006243517273105681, |
| "learning_rate": 2.804e-05, |
| "loss": 0.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.0006688985740765929, |
| "learning_rate": 2.6040000000000005e-05, |
| "loss": 0.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.00047493071178905666, |
| "learning_rate": 2.404e-05, |
| "loss": 0.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.0006771540502086282, |
| "learning_rate": 2.2040000000000002e-05, |
| "loss": 0.0024, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.000500071793794632, |
| "learning_rate": 2.004e-05, |
| "loss": 0.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.998, |
| "eval_f1": 0.998, |
| "eval_loss": 0.005241448991000652, |
| "eval_runtime": 43.2836, |
| "eval_samples_per_second": 23.103, |
| "eval_steps_per_second": 2.888, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.000668955675791949, |
| "learning_rate": 1.804e-05, |
| "loss": 0.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 0.0005380553775466979, |
| "learning_rate": 1.604e-05, |
| "loss": 0.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 0.00043314267531968653, |
| "learning_rate": 1.4040000000000001e-05, |
| "loss": 0.0, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 0.000652027374599129, |
| "learning_rate": 1.204e-05, |
| "loss": 0.0, |
| "step": 950 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.0004371394752524793, |
| "learning_rate": 1.004e-05, |
| "loss": 0.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.999, |
| "eval_f1": 0.9989996083884333, |
| "eval_loss": 0.004136711824685335, |
| "eval_runtime": 43.0268, |
| "eval_samples_per_second": 23.241, |
| "eval_steps_per_second": 2.905, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 0.000431750260759145, |
| "learning_rate": 8.040000000000001e-06, |
| "loss": 0.0, |
| "step": 1050 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 0.0012624277733266354, |
| "learning_rate": 6.040000000000001e-06, |
| "loss": 0.0, |
| "step": 1100 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 0.00036189553793519735, |
| "learning_rate": 4.04e-06, |
| "loss": 0.0, |
| "step": 1150 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.00043084935168735683, |
| "learning_rate": 2.0400000000000004e-06, |
| "loss": 0.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.0005352545995265245, |
| "learning_rate": 4e-08, |
| "loss": 0.0, |
| "step": 1250 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.999, |
| "eval_f1": 0.9989996083884333, |
| "eval_loss": 0.00451634032651782, |
| "eval_runtime": 43.0272, |
| "eval_samples_per_second": 23.241, |
| "eval_steps_per_second": 2.905, |
| "step": 1250 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 9.209823610762691e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
