| { |
| "best_metric": 0.6966970562934875, |
| "best_model_checkpoint": "./LongT5-XLarge-NSPCC/checkpoint-377", |
| "epoch": 1.9973509933774833, |
| "eval_steps": 500, |
| "global_step": 377, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9960264900662251, |
| "grad_norm": 0.6866635680198669, |
| "learning_rate": 0.00026365056951661766, |
| "loss": 3.6911, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.9960264900662251, |
| "eval_gen_len": 360.7021, |
| "eval_loss": 0.7291953563690186, |
| "eval_rouge1": 0.4665, |
| "eval_rouge2": 0.1826, |
| "eval_rougeL": 0.2611, |
| "eval_rougeLsum": 0.2611, |
| "eval_runtime": 6342.3266, |
| "eval_samples_per_second": 0.015, |
| "eval_steps_per_second": 0.015, |
| "step": 188 |
| }, |
| { |
| "epoch": 1.9973509933774833, |
| "grad_norm": 0.37886831164360046, |
| "learning_rate": 0.00015678507557860595, |
| "loss": 0.8701, |
| "step": 377 |
| }, |
| { |
| "epoch": 1.9973509933774833, |
| "eval_gen_len": 365.3298, |
| "eval_loss": 0.6966970562934875, |
| "eval_rouge1": 0.4886, |
| "eval_rouge2": 0.2073, |
| "eval_rougeL": 0.2805, |
| "eval_rougeLsum": 0.2799, |
| "eval_runtime": 6456.3838, |
| "eval_samples_per_second": 0.015, |
| "eval_steps_per_second": 0.015, |
| "step": 377 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 752, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 4.146560459027251e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
