| { |
| "best_metric": 1.3130167722702026, |
| "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-18", |
| "epoch": 2.88, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.96, |
| "eval_accuracy": { |
| "accuracy": 0.42 |
| }, |
| "eval_logLoss": 1.4662960767745972, |
| "eval_loss": 1.4662964344024658, |
| "eval_runtime": 71.93, |
| "eval_samples_per_second": 2.78, |
| "eval_steps_per_second": 0.097, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 2.0363504886627197, |
| "learning_rate": 2.5e-05, |
| "loss": 1.4937, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_accuracy": { |
| "accuracy": 0.445 |
| }, |
| "eval_logLoss": 1.3507485389709473, |
| "eval_loss": 1.3507485389709473, |
| "eval_runtime": 4.9957, |
| "eval_samples_per_second": 40.034, |
| "eval_steps_per_second": 1.401, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.88, |
| "eval_accuracy": { |
| "accuracy": 0.43 |
| }, |
| "eval_logLoss": 1.3130167722702026, |
| "eval_loss": 1.3130167722702026, |
| "eval_runtime": 6.5823, |
| "eval_samples_per_second": 30.385, |
| "eval_steps_per_second": 1.063, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.88, |
| "step": 18, |
| "total_flos": 5.789887959505306e+16, |
| "train_loss": 1.4178554217020671, |
| "train_runtime": 455.1681, |
| "train_samples_per_second": 5.273, |
| "train_steps_per_second": 0.04 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 18, |
| "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": 5.789887959505306e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
