| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 4254, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.394895903290799e-07, | |
| "loss": 0.2474, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.6789791806581599e-06, | |
| "loss": 0.1139, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.09119495749473572, | |
| "eval_mse": 0.09119495749473572, | |
| "eval_pearson": 0.46595820319292786, | |
| "eval_runtime": 33.7746, | |
| "eval_samples_per_second": 83.909, | |
| "eval_spearman": 0.4688124167009965, | |
| "eval_steps_per_second": 20.992, | |
| "step": 1418 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.5184687709872403e-06, | |
| "loss": 0.1088, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.3579583613163197e-06, | |
| "loss": 0.1009, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.1974479516454e-06, | |
| "loss": 0.0969, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.11053851991891861, | |
| "eval_mse": 0.1105385348200798, | |
| "eval_pearson": 0.4833832570029285, | |
| "eval_runtime": 33.4956, | |
| "eval_samples_per_second": 84.608, | |
| "eval_spearman": 0.48034044382389435, | |
| "eval_steps_per_second": 21.167, | |
| "step": 2836 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.9137931034482765e-06, | |
| "loss": 0.0984, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.954545454545455e-06, | |
| "loss": 0.0902, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.952978056426333e-07, | |
| "loss": 0.0877, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.09364812821149826, | |
| "eval_mse": 0.09364812821149826, | |
| "eval_pearson": 0.49938424295343353, | |
| "eval_runtime": 33.6749, | |
| "eval_samples_per_second": 84.158, | |
| "eval_spearman": 0.4991673030641522, | |
| "eval_steps_per_second": 21.054, | |
| "step": 4254 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4254, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 7370098469868708.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |