| { | |
| "best_metric": 0.1422310322523117, | |
| "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/cola/checkpoint-75", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 7.2579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 6.0871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0100170373916626, | |
| "eval_runtime": 5.8549, | |
| "eval_samples_per_second": 34.159, | |
| "eval_steps_per_second": 4.27, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 1.808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.000234, | |
| "loss": 0.2533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000294, | |
| "loss": 0.2083, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.19681957364082336, | |
| "eval_runtime": 5.8474, | |
| "eval_samples_per_second": 34.203, | |
| "eval_steps_per_second": 4.275, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00028649999999999997, | |
| "loss": 0.1663, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002715, | |
| "loss": 0.1771, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.1422310322523117, | |
| "eval_runtime": 5.848, | |
| "eval_samples_per_second": 34.2, | |
| "eval_steps_per_second": 4.275, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4495226494648320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |