| { |
| "best_global_step": 495, |
| "best_metric": 0.9091259145167501, |
| "best_model_checkpoint": "run/nsfw_finetune_1e-4_224/checkpoint-495", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 495, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9006546014632268, |
| "eval_loss": 0.267375111579895, |
| "eval_runtime": 29.975, |
| "eval_samples_per_second": 86.639, |
| "eval_steps_per_second": 0.367, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9010396611474779, |
| "eval_loss": 0.2740514576435089, |
| "eval_runtime": 30.0301, |
| "eval_samples_per_second": 86.48, |
| "eval_steps_per_second": 0.366, |
| "step": 198 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.902194840200231, |
| "eval_loss": 0.2687060832977295, |
| "eval_runtime": 29.8935, |
| "eval_samples_per_second": 86.875, |
| "eval_steps_per_second": 0.368, |
| "step": 297 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8991143627262226, |
| "eval_loss": 0.2927175760269165, |
| "eval_runtime": 29.8756, |
| "eval_samples_per_second": 86.927, |
| "eval_steps_per_second": 0.368, |
| "step": 396 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9091259145167501, |
| "eval_loss": 0.31239020824432373, |
| "eval_runtime": 30.1905, |
| "eval_samples_per_second": 86.02, |
| "eval_steps_per_second": 0.364, |
| "step": 495 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4950, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.959286279726347e+19, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
