| { |
| "best_metric": 0.21197938919067383, |
| "best_model_checkpoint": "./text2sql/13b-codellama_instruct_pt_text2sql_ckpt8k_ft_spider/checkpoint-300", |
| "epoch": 1.8475750577367207, |
| "eval_steps": 100, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 6.17283950617284e-07, |
| "loss": 0.5755, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 3.08641975308642e-05, |
| "loss": 0.4793, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 4.9251379038613084e-05, |
| "loss": 0.2673, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.37, |
| "eval_loss": 0.25259310007095337, |
| "eval_runtime": 78.7093, |
| "eval_samples_per_second": 13.137, |
| "eval_steps_per_second": 3.291, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 4.728132387706856e-05, |
| "loss": 0.2062, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 4.5311268715524035e-05, |
| "loss": 0.1763, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_loss": 0.21567295491695404, |
| "eval_runtime": 78.7696, |
| "eval_samples_per_second": 13.127, |
| "eval_steps_per_second": 3.288, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 4.334121355397952e-05, |
| "loss": 0.1569, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 4.1371158392434986e-05, |
| "loss": 0.1387, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.11, |
| "eval_loss": 0.21197938919067383, |
| "eval_runtime": 78.7959, |
| "eval_samples_per_second": 13.123, |
| "eval_steps_per_second": 3.287, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 3.940110323089047e-05, |
| "loss": 0.131, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 3.743104806934594e-05, |
| "loss": 0.125, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.48, |
| "eval_loss": 0.21536056697368622, |
| "eval_runtime": 78.6623, |
| "eval_samples_per_second": 13.145, |
| "eval_steps_per_second": 3.293, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 3.546099290780142e-05, |
| "loss": 0.1221, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 3.349093774625689e-05, |
| "loss": 0.1126, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.85, |
| "eval_loss": 0.21894869208335876, |
| "eval_runtime": 78.8279, |
| "eval_samples_per_second": 13.117, |
| "eval_steps_per_second": 3.286, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1350, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "total_flos": 2.4465242205093888e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
