| { | |
| "best_metric": 1.0084277391433716, | |
| "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 10164, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19677292404565133, | |
| "grad_norm": 13.16645622253418, | |
| "learning_rate": 7.644057741744116e-07, | |
| "loss": 0.9682, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39354584809130266, | |
| "grad_norm": 13.873289108276367, | |
| "learning_rate": 7.248566343682025e-07, | |
| "loss": 0.9558, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5903187721369539, | |
| "grad_norm": 9.378376960754395, | |
| "learning_rate": 6.853074945619932e-07, | |
| "loss": 0.9563, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7870916961826053, | |
| "grad_norm": 13.954855918884277, | |
| "learning_rate": 6.45758354755784e-07, | |
| "loss": 0.9576, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9838646202282566, | |
| "grad_norm": 8.968609809875488, | |
| "learning_rate": 6.062092149495747e-07, | |
| "loss": 0.9435, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7204107617360496, | |
| "eval_loss": 1.0221161842346191, | |
| "eval_model_preparation_time": 0.0058, | |
| "eval_runtime": 1192.8471, | |
| "eval_samples_per_second": 90.862, | |
| "eval_steps_per_second": 2.839, | |
| "step": 2541 | |
| }, | |
| { | |
| "epoch": 1.1806375442739079, | |
| "grad_norm": 9.562682151794434, | |
| "learning_rate": 5.666600751433656e-07, | |
| "loss": 0.9435, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.3774104683195592, | |
| "grad_norm": 7.73732328414917, | |
| "learning_rate": 5.271109353371563e-07, | |
| "loss": 0.945, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.5741833923652107, | |
| "grad_norm": 9.456089973449707, | |
| "learning_rate": 4.875617955309472e-07, | |
| "loss": 0.9379, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.770956316410862, | |
| "grad_norm": 8.087896347045898, | |
| "learning_rate": 4.48012655724738e-07, | |
| "loss": 0.93, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9677292404565132, | |
| "grad_norm": 11.194710731506348, | |
| "learning_rate": 4.0846351591852876e-07, | |
| "loss": 0.9457, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7221822409211692, | |
| "eval_loss": 1.0146400928497314, | |
| "eval_model_preparation_time": 0.0058, | |
| "eval_runtime": 1188.9777, | |
| "eval_samples_per_second": 91.157, | |
| "eval_steps_per_second": 2.849, | |
| "step": 5082 | |
| }, | |
| { | |
| "epoch": 2.1645021645021645, | |
| "grad_norm": 9.790952682495117, | |
| "learning_rate": 3.6891437611231956e-07, | |
| "loss": 0.9299, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.3612750885478158, | |
| "grad_norm": 7.579208850860596, | |
| "learning_rate": 3.293652363061103e-07, | |
| "loss": 0.9283, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.558048012593467, | |
| "grad_norm": 8.789483070373535, | |
| "learning_rate": 2.898160964999011e-07, | |
| "loss": 0.9476, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.7548209366391183, | |
| "grad_norm": 10.544241905212402, | |
| "learning_rate": 2.502669566936919e-07, | |
| "loss": 0.9228, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.9515938606847696, | |
| "grad_norm": 8.694629669189453, | |
| "learning_rate": 2.1071781688748268e-07, | |
| "loss": 0.9256, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7234462651313847, | |
| "eval_loss": 1.0090746879577637, | |
| "eval_model_preparation_time": 0.0058, | |
| "eval_runtime": 1192.9376, | |
| "eval_samples_per_second": 90.855, | |
| "eval_steps_per_second": 2.839, | |
| "step": 7623 | |
| }, | |
| { | |
| "epoch": 3.1483667847304213, | |
| "grad_norm": 9.106084823608398, | |
| "learning_rate": 1.7116867708127348e-07, | |
| "loss": 0.9313, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.3451397087760726, | |
| "grad_norm": 14.434243202209473, | |
| "learning_rate": 1.3161953727506426e-07, | |
| "loss": 0.9245, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.541912632821724, | |
| "grad_norm": 6.294890880584717, | |
| "learning_rate": 9.207039746885504e-08, | |
| "loss": 0.9135, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.738685556867375, | |
| "grad_norm": 9.335221290588379, | |
| "learning_rate": 5.2521257662645836e-08, | |
| "loss": 0.9349, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.9354584809130264, | |
| "grad_norm": 8.591920852661133, | |
| "learning_rate": 1.297211785643662e-08, | |
| "loss": 0.913, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.723907587835843, | |
| "eval_loss": 1.0084277391433716, | |
| "eval_model_preparation_time": 0.0058, | |
| "eval_runtime": 1186.2416, | |
| "eval_samples_per_second": 91.368, | |
| "eval_steps_per_second": 2.855, | |
| "step": 10164 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10164, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.0414127158862545e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |