checkpoint-7623/trainer_state.json

{
 "best_metric": 1.0335272550582886,
 "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": 8.757041931152344,
 "learning_rate": 7.524626964214973e-07,
 "loss": 0.9786,
 "step": 500
 },
 {
 "epoch": 0.39354584809130266,
 "grad_norm": 8.383247375488281,
 "learning_rate": 6.996434702231612e-07,
 "loss": 0.9913,
 "step": 1000
 },
 {
 "epoch": 0.5903187721369539,
 "grad_norm": 11.913640022277832,
 "learning_rate": 6.46824244024825e-07,
 "loss": 0.986,
 "step": 1500
 },
 {
 "epoch": 0.7870916961826053,
 "grad_norm": 8.429478645324707,
 "learning_rate": 5.940050178264888e-07,
 "loss": 0.9742,
 "step": 2000
 },
 {
 "epoch": 0.9838646202282566,
 "grad_norm": 8.826607704162598,
 "learning_rate": 5.411857916281527e-07,
 "loss": 0.9771,
 "step": 2500
 },
 {
 "epoch": 1.0,
 "eval_accuracy": 0.7168678033658105,
 "eval_loss": 1.0437126159667969,
 "eval_model_preparation_time": 0.0056,
 "eval_runtime": 1253.4528,
 "eval_samples_per_second": 86.468,
 "eval_steps_per_second": 2.702,
 "step": 2541
 },
 {
 "epoch": 1.1806375442739079,
 "grad_norm": 11.744253158569336,
 "learning_rate": 4.883665654298165e-07,
 "loss": 0.977,
 "step": 3000
 },
 {
 "epoch": 1.3774104683195592,
 "grad_norm": 9.053071022033691,
 "learning_rate": 4.355473392314803e-07,
 "loss": 0.9658,
 "step": 3500
 },
 {
 "epoch": 1.5741833923652107,
 "grad_norm": 10.54920482635498,
 "learning_rate": 3.8272811303314405e-07,
 "loss": 0.9709,
 "step": 4000
 },
 {
 "epoch": 1.770956316410862,
 "grad_norm": 8.325064659118652,
 "learning_rate": 3.2990888683480783e-07,
 "loss": 0.9738,
 "step": 4500
 },
 {
 "epoch": 1.9677292404565132,
 "grad_norm": 10.403226852416992,
 "learning_rate": 2.7708966063647166e-07,
 "loss": 0.953,
 "step": 5000
 },
 {
 "epoch": 2.0,
 "eval_accuracy": 0.7185377915559492,
 "eval_loss": 1.0369055271148682,
 "eval_model_preparation_time": 0.0056,
 "eval_runtime": 1273.434,
 "eval_samples_per_second": 85.112,
 "eval_steps_per_second": 2.66,
 "step": 5082
 },
 {
 "epoch": 2.1645021645021645,
 "grad_norm": 10.920880317687988,
 "learning_rate": 2.2427043443813546e-07,
 "loss": 0.9497,
 "step": 5500
 },
 {
 "epoch": 2.3612750885478158,
 "grad_norm": 16.526975631713867,
 "learning_rate": 1.714512082397993e-07,
 "loss": 0.9597,
 "step": 6000
 },
 {
 "epoch": 2.558048012593467,
 "grad_norm": 9.863446235656738,
 "learning_rate": 1.186319820414631e-07,
 "loss": 0.9506,
 "step": 6500
 },
 {
 "epoch": 2.7548209366391183,
 "grad_norm": 11.81240463256836,
 "learning_rate": 6.58127558431269e-08,
 "loss": 0.9705,
 "step": 7000
 },
 {
 "epoch": 2.9515938606847696,
 "grad_norm": 10.019937515258789,
 "learning_rate": 1.2993529644790705e-08,
 "loss": 0.9597,
 "step": 7500
 },
 {
 "epoch": 3.0,
 "eval_accuracy": 0.7189898878063182,
 "eval_loss": 1.0335272550582886,
 "eval_model_preparation_time": 0.0056,
 "eval_runtime": 1268.3378,
 "eval_samples_per_second": 85.454,
 "eval_steps_per_second": 2.67,
 "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
}