| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 3750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.2385, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_f1": 0.9824900538642076, | |
| "eval_loss": 0.06151168420910835, | |
| "eval_runtime": 19.4562, | |
| "eval_samples_per_second": 308.386, | |
| "eval_steps_per_second": 38.548, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.071, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_f1": 0.9883248221286651, | |
| "eval_loss": 0.047542937099933624, | |
| "eval_runtime": 7.5074, | |
| "eval_samples_per_second": 799.21, | |
| "eval_steps_per_second": 99.901, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0659, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_f1": 0.9906601900273291, | |
| "eval_loss": 0.04389449208974838, | |
| "eval_runtime": 6.6018, | |
| "eval_samples_per_second": 908.837, | |
| "eval_steps_per_second": 113.605, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0679, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_f1": 0.9919927935141627, | |
| "eval_loss": 0.03968248888850212, | |
| "eval_runtime": 8.8193, | |
| "eval_samples_per_second": 680.326, | |
| "eval_steps_per_second": 85.041, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0414, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_f1": 0.9909945206661297, | |
| "eval_loss": 0.044602639973163605, | |
| "eval_runtime": 6.4726, | |
| "eval_samples_per_second": 926.979, | |
| "eval_steps_per_second": 115.872, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0447, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_f1": 0.9926591496358939, | |
| "eval_loss": 0.037685297429561615, | |
| "eval_runtime": 7.0088, | |
| "eval_samples_per_second": 856.061, | |
| "eval_steps_per_second": 107.008, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0427, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_f1": 0.9923271737589343, | |
| "eval_loss": 0.03635118156671524, | |
| "eval_runtime": 8.2324, | |
| "eval_samples_per_second": 728.825, | |
| "eval_steps_per_second": 91.103, | |
| "step": 3584 | |
| } | |
| ], | |
| "max_steps": 3750, | |
| "num_train_epochs": 1, | |
| "total_flos": 38061091933440.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |