| { | |
| "best_metric": 0.8528685149601977, | |
| "best_model_checkpoint": "ds3-img-classification/checkpoint-284", | |
| "epoch": 4.403100775193798, | |
| "eval_steps": 142, | |
| "global_step": 284, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015503875968992248, | |
| "grad_norm": 14.292332649230957, | |
| "learning_rate": 1.736111111111111e-06, | |
| "loss": 5.8979, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.201550387596899, | |
| "grad_norm": 3.2709274291992188, | |
| "learning_rate": 0.0002465277777777778, | |
| "loss": 2.2063, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.201550387596899, | |
| "eval_accuracy": 0.8300850947021685, | |
| "eval_loss": 0.6956288814544678, | |
| "eval_macro_f1": 0.8020115300522307, | |
| "eval_macro_precision": 0.8326277180719005, | |
| "eval_macro_recall": 0.8130180643302005, | |
| "eval_micro_f1": 0.8300850947021685, | |
| "eval_micro_precision": 0.8300850947021685, | |
| "eval_micro_recall": 0.8300850947021685, | |
| "eval_runtime": 8.1254, | |
| "eval_samples_per_second": 448.347, | |
| "eval_steps_per_second": 3.569, | |
| "eval_weighted_f1": 0.8217784359221563, | |
| "eval_weighted_precision": 0.8439879212180366, | |
| "eval_weighted_recall": 0.8300850947021685, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.403100775193798, | |
| "grad_norm": 3.7781729698181152, | |
| "learning_rate": 0.0004930555555555556, | |
| "loss": 0.4906, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 4.403100775193798, | |
| "eval_accuracy": 0.8528685149601977, | |
| "eval_loss": 0.5704612731933594, | |
| "eval_macro_f1": 0.8447646928874578, | |
| "eval_macro_precision": 0.8434580548053667, | |
| "eval_macro_recall": 0.8590562294756982, | |
| "eval_micro_f1": 0.8528685149601977, | |
| "eval_micro_precision": 0.8528685149601977, | |
| "eval_micro_recall": 0.8528685149601977, | |
| "eval_runtime": 8.3026, | |
| "eval_samples_per_second": 438.779, | |
| "eval_steps_per_second": 3.493, | |
| "eval_weighted_f1": 0.8542422373852568, | |
| "eval_weighted_precision": 0.8661150819486806, | |
| "eval_weighted_recall": 0.8528685149601977, | |
| "step": 284 | |
| } | |
| ], | |
| "logging_steps": 142, | |
| "max_steps": 5760, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 90, | |
| "save_steps": 142, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.957999132801776e+19, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |