| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.36450739429285567, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.947927515101021e-05, | |
| "loss": 2.2374, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_exact_match": 49.46965745087811, | |
| "eval_f1": 54.705922468625346, | |
| "eval_loss": 1.399248480796814, | |
| "eval_runtime": 152.8082, | |
| "eval_samples_per_second": 92.96, | |
| "eval_steps_per_second": 11.622, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.8958550302020413e-05, | |
| "loss": 1.1963, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_exact_match": 54.33837593462007, | |
| "eval_f1": 59.335692166319255, | |
| "eval_loss": 1.046236276626587, | |
| "eval_runtime": 153.237, | |
| "eval_samples_per_second": 92.7, | |
| "eval_steps_per_second": 11.59, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8437825453030617e-05, | |
| "loss": 1.1031, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_exact_match": 56.17283950617284, | |
| "eval_f1": 61.40430603082631, | |
| "eval_loss": 0.8644341230392456, | |
| "eval_runtime": 153.7515, | |
| "eval_samples_per_second": 92.389, | |
| "eval_steps_per_second": 11.551, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.7917100604040825e-05, | |
| "loss": 0.9479, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_exact_match": 57.21613632411754, | |
| "eval_f1": 61.625922292628005, | |
| "eval_loss": 0.7944296002388, | |
| "eval_runtime": 153.833, | |
| "eval_samples_per_second": 92.34, | |
| "eval_steps_per_second": 11.545, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.7396375755051033e-05, | |
| "loss": 0.899, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_exact_match": 59.867849069727, | |
| "eval_f1": 64.17727571949499, | |
| "eval_loss": 0.7857800722122192, | |
| "eval_runtime": 154.1204, | |
| "eval_samples_per_second": 92.168, | |
| "eval_steps_per_second": 11.523, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.6875650906061238e-05, | |
| "loss": 0.8672, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_exact_match": 65.00608589810467, | |
| "eval_f1": 69.60946105310353, | |
| "eval_loss": 0.8072792887687683, | |
| "eval_runtime": 154.2464, | |
| "eval_samples_per_second": 92.093, | |
| "eval_steps_per_second": 11.514, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.6354926057071445e-05, | |
| "loss": 0.8375, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_exact_match": 63.82368283776734, | |
| "eval_f1": 68.19581427410363, | |
| "eval_loss": 0.7115561366081238, | |
| "eval_runtime": 154.7006, | |
| "eval_samples_per_second": 91.822, | |
| "eval_steps_per_second": 11.48, | |
| "step": 3500 | |
| } | |
| ], | |
| "max_steps": 28806, | |
| "num_train_epochs": 3, | |
| "total_flos": 7316309188608000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |