| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 2750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4406, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 51.07846566398508, | |
| "eval_f1": 61.011399927131706, | |
| "eval_runtime": 8.3465, | |
| "eval_samples_per_second": 1027.616, | |
| "eval_steps_per_second": 3.235, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7644, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 54.133146787921184, | |
| "eval_f1": 62.50711993302596, | |
| "eval_runtime": 7.5444, | |
| "eval_samples_per_second": 1136.864, | |
| "eval_steps_per_second": 3.579, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5654, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 52.8040107263612, | |
| "eval_f1": 62.14306548820758, | |
| "eval_runtime": 7.521, | |
| "eval_samples_per_second": 1140.414, | |
| "eval_steps_per_second": 3.59, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.418, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 53.64346508103066, | |
| "eval_f1": 61.988040522739425, | |
| "eval_runtime": 7.5215, | |
| "eval_samples_per_second": 1140.331, | |
| "eval_steps_per_second": 3.59, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3116, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 53.53853328669698, | |
| "eval_f1": 61.34739758769079, | |
| "eval_runtime": 7.543, | |
| "eval_samples_per_second": 1137.084, | |
| "eval_steps_per_second": 3.579, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2279, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 55.182464731258015, | |
| "eval_f1": 61.675370738118836, | |
| "eval_runtime": 7.5189, | |
| "eval_samples_per_second": 1140.721, | |
| "eval_steps_per_second": 3.591, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1697, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_exact_match": 54.821032995219774, | |
| "eval_f1": 61.93346586592826, | |
| "eval_runtime": 7.554, | |
| "eval_samples_per_second": 1135.424, | |
| "eval_steps_per_second": 3.574, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1274, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_exact_match": 55.765419144222925, | |
| "eval_f1": 62.45150631016991, | |
| "eval_runtime": 7.5444, | |
| "eval_samples_per_second": 1136.865, | |
| "eval_steps_per_second": 3.579, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1011, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_exact_match": 55.065873848665035, | |
| "eval_f1": 61.965971673180476, | |
| "eval_runtime": 7.5299, | |
| "eval_samples_per_second": 1139.057, | |
| "eval_steps_per_second": 3.586, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0848, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_exact_match": 55.194123819517316, | |
| "eval_f1": 62.60240237025559, | |
| "eval_runtime": 7.5603, | |
| "eval_samples_per_second": 1134.474, | |
| "eval_steps_per_second": 3.571, | |
| "step": 2750 | |
| } | |
| ], | |
| "max_steps": 2750, | |
| "num_train_epochs": 10, | |
| "total_flos": 872065594818560.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |