| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9773260359655981, | |
| "global_step": 30000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8373729476153247e-05, | |
| "loss": 1.6126, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_exact_match": 68.15336463223787, | |
| "eval_f1": 73.98256617857639, | |
| "eval_loss": 1.189887523651123, | |
| "eval_runtime": 1542.7266, | |
| "eval_samples_per_second": 7.463, | |
| "eval_steps_per_second": 3.732, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.674550430023456e-05, | |
| "loss": 1.1965, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_exact_match": 75.13475917231786, | |
| "eval_f1": 79.95184555682803, | |
| "eval_loss": 0.9056070446968079, | |
| "eval_runtime": 1533.9546, | |
| "eval_samples_per_second": 7.505, | |
| "eval_steps_per_second": 3.753, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.511695334897055e-05, | |
| "loss": 1.0769, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_exact_match": 77.56042427403929, | |
| "eval_f1": 82.22503770504048, | |
| "eval_loss": 0.9495312571525574, | |
| "eval_runtime": 1533.818, | |
| "eval_samples_per_second": 7.506, | |
| "eval_steps_per_second": 3.753, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.3488728173051864e-05, | |
| "loss": 0.9992, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_exact_match": 81.09024517475221, | |
| "eval_f1": 85.49992934663945, | |
| "eval_loss": 0.8323877453804016, | |
| "eval_runtime": 1541.3611, | |
| "eval_samples_per_second": 7.469, | |
| "eval_steps_per_second": 3.735, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.1860502997133176e-05, | |
| "loss": 0.9329, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_exact_match": 81.264127977743, | |
| "eval_f1": 85.43481659242194, | |
| "eval_loss": 0.7231199741363525, | |
| "eval_runtime": 1535.496, | |
| "eval_samples_per_second": 7.498, | |
| "eval_steps_per_second": 3.749, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.0232277821214492e-05, | |
| "loss": 0.8913, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_exact_match": 81.92488262910798, | |
| "eval_f1": 85.96065424027016, | |
| "eval_loss": 0.7569286227226257, | |
| "eval_runtime": 1529.0019, | |
| "eval_samples_per_second": 7.53, | |
| "eval_steps_per_second": 3.765, | |
| "step": 30000 | |
| } | |
| ], | |
| "max_steps": 92088, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.619410874368e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |