| { | |
| "best_metric": 0.8729433272394881, | |
| "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-11\\checkpoint-600", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 600, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.546076859205841e-05, | |
| "loss": 0.5075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8555758683729433, | |
| "eval_loss": 0.4903055727481842, | |
| "eval_runtime": 10.8207, | |
| "eval_samples_per_second": 202.205, | |
| "eval_steps_per_second": 1.663, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.15955764440438e-05, | |
| "loss": 0.4756, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.856489945155393, | |
| "eval_loss": 0.4780411124229431, | |
| "eval_runtime": 10.8942, | |
| "eval_samples_per_second": 200.84, | |
| "eval_steps_per_second": 1.652, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.7730384296029203e-05, | |
| "loss": 0.4648, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8656307129798904, | |
| "eval_loss": 0.47325029969215393, | |
| "eval_runtime": 10.798, | |
| "eval_samples_per_second": 202.631, | |
| "eval_steps_per_second": 1.667, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.3865192148014602e-05, | |
| "loss": 0.4567, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8720292504570384, | |
| "eval_loss": 0.47100675106048584, | |
| "eval_runtime": 10.8776, | |
| "eval_samples_per_second": 201.147, | |
| "eval_steps_per_second": 1.655, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4533, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8729433272394881, | |
| "eval_loss": 0.4702821373939514, | |
| "eval_runtime": 10.8456, | |
| "eval_samples_per_second": 201.741, | |
| "eval_steps_per_second": 1.66, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 9988136054880.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 6.9325960740073e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 64, | |
| "seed": 9 | |
| } | |
| } | |