| { |
| "best_metric": 0.49723756906077354, |
| "best_model_checkpoint": "RuleBert-v0.3-k0/checkpoint-250", |
| "epoch": 0.06172839506172839, |
| "eval_steps": 250, |
| "global_step": 250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 4.9687500000000005e-06, |
| "loss": 0.6506, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.937500000000001e-06, |
| "loss": 0.5459, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.90625e-06, |
| "loss": 0.4495, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 4.875e-06, |
| "loss": 0.4012, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.84375e-06, |
| "loss": 0.3623, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.06, |
| "eval_accuracy": 0.0, |
| "eval_f1": 0.49723756906077354, |
| "eval_loss": 0.3701123297214508, |
| "eval_roc_auc": 0.6720357564513407, |
| "eval_runtime": 2.6386, |
| "eval_samples_per_second": 56.848, |
| "eval_steps_per_second": 1.137, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 8000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 250, |
| "total_flos": 134660395008000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
