checkpoint-7623/trainer_state.json

{
 "best_metric": 1.488718032836914,
 "best_model_checkpoint": "cat_breed_image_detection/checkpoint-7623",
 "epoch": 3.0,
 "eval_steps": 500,
 "global_step": 7623,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.19677292404565133,
 "grad_norm": 8.220705032348633,
 "learning_rate": 8.465205334741845e-07,
 "loss": 1.4752,
 "step": 500
 },
 {
 "epoch": 0.39354584809130266,
 "grad_norm": 7.696910858154297,
 "learning_rate": 7.870989040010564e-07,
 "loss": 1.4833,
 "step": 1000
 },
 {
 "epoch": 0.5903187721369539,
 "grad_norm": 7.823228359222412,
 "learning_rate": 7.276772745279281e-07,
 "loss": 1.4728,
 "step": 1500
 },
 {
 "epoch": 0.7870916961826053,
 "grad_norm": 6.080297946929932,
 "learning_rate": 6.682556450547999e-07,
 "loss": 1.4901,
 "step": 2000
 },
 {
 "epoch": 0.9838646202282566,
 "grad_norm": 7.583363056182861,
 "learning_rate": 6.088340155816718e-07,
 "loss": 1.4755,
 "step": 2500
 },
 {
 "epoch": 1.0,
 "eval_accuracy": 0.6088537053439622,
 "eval_loss": 1.5104930400848389,
 "eval_model_preparation_time": 0.0053,
 "eval_runtime": 1216.8858,
 "eval_samples_per_second": 89.067,
 "eval_steps_per_second": 2.783,
 "step": 2541
 },
 {
 "epoch": 1.1806375442739079,
 "grad_norm": 9.293631553649902,
 "learning_rate": 5.494123861085435e-07,
 "loss": 1.4665,
 "step": 3000
 },
 {
 "epoch": 1.3774104683195592,
 "grad_norm": 8.063645362854004,
 "learning_rate": 4.899907566354153e-07,
 "loss": 1.4613,
 "step": 3500
 },
 {
 "epoch": 1.5741833923652107,
 "grad_norm": 6.942551612854004,
 "learning_rate": 4.3056912716228705e-07,
 "loss": 1.4569,
 "step": 4000
 },
 {
 "epoch": 1.770956316410862,
 "grad_norm": 11.436430931091309,
 "learning_rate": 3.7114749768915883e-07,
 "loss": 1.4412,
 "step": 4500
 },
 {
 "epoch": 1.9677292404565132,
 "grad_norm": 6.971865177154541,
 "learning_rate": 3.117258682160306e-07,
 "loss": 1.4428,
 "step": 5000
 },
 {
 "epoch": 2.0,
 "eval_accuracy": 0.6121660023619723,
 "eval_loss": 1.4942480325698853,
 "eval_model_preparation_time": 0.0053,
 "eval_runtime": 1210.5473,
 "eval_samples_per_second": 89.533,
 "eval_steps_per_second": 2.798,
 "step": 5082
 },
 {
 "epoch": 2.1645021645021645,
 "grad_norm": 7.25930643081665,
 "learning_rate": 2.523042387429024e-07,
 "loss": 1.4412,
 "step": 5500
 },
 {
 "epoch": 2.3612750885478158,
 "grad_norm": 8.07095718383789,
 "learning_rate": 1.928826092697742e-07,
 "loss": 1.4362,
 "step": 6000
 },
 {
 "epoch": 2.558048012593467,
 "grad_norm": 8.908621788024902,
 "learning_rate": 1.3346097979664598e-07,
 "loss": 1.4375,
 "step": 6500
 },
 {
 "epoch": 2.7548209366391183,
 "grad_norm": 8.16598129272461,
 "learning_rate": 7.403935032351777e-08,
 "loss": 1.4397,
 "step": 7000
 },
 {
 "epoch": 2.9515938606847696,
 "grad_norm": 9.264542579650879,
 "learning_rate": 1.4617720850389543e-08,
 "loss": 1.437,
 "step": 7500
 },
 {
 "epoch": 3.0,
 "eval_accuracy": 0.6130332890463537,
 "eval_loss": 1.488718032836914,
 "eval_model_preparation_time": 0.0053,
 "eval_runtime": 1205.355,
 "eval_samples_per_second": 89.919,
 "eval_steps_per_second": 2.81,
 "step": 7623
 }
 ],
 "logging_steps": 500,
 "max_steps": 7623,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 3,
 "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": 3.781059536914691e+19,
 "train_batch_size": 64,
 "trial_name": null,
 "trial_params": null
}