| { | |
| "best_global_step": 804, | |
| "best_metric": 0.23307399451732635, | |
| "best_model_checkpoint": "siglip2-finetune/checkpoint-804", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 804, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7478077867414942, | |
| "eval_loss": 0.6867316961288452, | |
| "eval_model_preparation_time": 0.0039, | |
| "eval_runtime": 73.0639, | |
| "eval_samples_per_second": 78.041, | |
| "eval_steps_per_second": 9.759, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 11.605195045471191, | |
| "learning_rate": 4.031830238726791e-05, | |
| "loss": 0.6005, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8921431076815153, | |
| "eval_loss": 0.3235144019126892, | |
| "eval_model_preparation_time": 0.0039, | |
| "eval_runtime": 72.6895, | |
| "eval_samples_per_second": 78.443, | |
| "eval_steps_per_second": 9.809, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9200280603297089, | |
| "eval_loss": 0.23307399451732635, | |
| "eval_model_preparation_time": 0.0039, | |
| "eval_runtime": 72.6624, | |
| "eval_samples_per_second": 78.473, | |
| "eval_steps_per_second": 9.813, | |
| "step": 804 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 804, | |
| "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": 2.148740086736517e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |