| { |
| "best_global_step": 504, |
| "best_metric": 0.9870483980913429, |
| "best_model_checkpoint": "./deberta_v3_fold_3/checkpoint-504", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 504, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.132867455482483, |
| "eval_map@3": 0.7177914110429446, |
| "eval_runtime": 66.7481, |
| "eval_samples_per_second": 7.326, |
| "eval_steps_per_second": 7.326, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.11986057460308075, |
| "eval_map@3": 0.9795501022494887, |
| "eval_runtime": 67.9102, |
| "eval_samples_per_second": 7.201, |
| "eval_steps_per_second": 7.201, |
| "step": 252 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.06871046870946884, |
| "eval_map@3": 0.985344239945467, |
| "eval_runtime": 68.3125, |
| "eval_samples_per_second": 7.158, |
| "eval_steps_per_second": 7.158, |
| "step": 378 |
| }, |
| { |
| "epoch": 3.970661362506216, |
| "grad_norm": 153.56666564941406, |
| "learning_rate": 2.1962072489860595e-09, |
| "loss": 9.9226845703125, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.0618998222053051, |
| "eval_map@3": 0.9870483980913429, |
| "eval_runtime": 66.6534, |
| "eval_samples_per_second": 7.336, |
| "eval_steps_per_second": 7.336, |
| "step": 504 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 504, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4520100776172240.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
