| { |
| "best_metric": 0.036812592297792435, |
| "best_model_checkpoint": "./text2sql/13b-codellama_instruct_pt_text2sql/checkpoint-6000", |
| "epoch": 0.668388695876181, |
| "eval_steps": 2000, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.1139992573338283e-07, |
| "loss": 1.0897, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00011139992573338284, |
| "loss": 0.2546, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00022279985146676567, |
| "loss": 0.0774, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.22, |
| "eval_loss": 0.0608125701546669, |
| "eval_runtime": 285.1249, |
| "eval_samples_per_second": 7.014, |
| "eval_steps_per_second": 1.754, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00029781686301467276, |
| "loss": 0.0652, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002907056676227274, |
| "loss": 0.0581, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.45, |
| "eval_loss": 0.04370184242725372, |
| "eval_runtime": 284.9797, |
| "eval_samples_per_second": 7.018, |
| "eval_steps_per_second": 1.755, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00028359447223078195, |
| "loss": 0.0499, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002764832768388366, |
| "loss": 0.0445, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.67, |
| "eval_loss": 0.036812592297792435, |
| "eval_runtime": 284.5683, |
| "eval_samples_per_second": 7.028, |
| "eval_steps_per_second": 1.757, |
| "step": 6000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 44880, |
| "num_train_epochs": 5, |
| "save_steps": 2000, |
| "total_flos": 4.1256600595070976e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
