| { | |
| "best_metric": 0.8615173674588665, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-5\\checkpoint-2874", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2874, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3151780085887827e-05, | |
| "loss": 0.4979, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.48700252175331116, | |
| "eval_runtime": 10.7411, | |
| "eval_samples_per_second": 203.703, | |
| "eval_steps_per_second": 1.676, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.767853390591884e-06, | |
| "loss": 0.4717, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8578610603290676, | |
| "eval_loss": 0.4791734516620636, | |
| "eval_runtime": 10.7469, | |
| "eval_samples_per_second": 203.593, | |
| "eval_steps_per_second": 1.675, | |
| "step": 1916 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.383926695295942e-06, | |
| "loss": 0.4658, | |
| "step": 2874 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8615173674588665, | |
| "eval_loss": 0.47797009348869324, | |
| "eval_runtime": 10.7674, | |
| "eval_samples_per_second": 203.207, | |
| "eval_steps_per_second": 1.672, | |
| "step": 2874 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3832, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 2954016825216.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.7535706781183768e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 8, | |
| "seed": 17 | |
| } | |
| } | |