| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.6296296296296298, |
| "eval_steps": 25, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 18.570375442504883, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 7.6743, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "eval_loss": 4.120080471038818, |
| "eval_runtime": 1.0842, |
| "eval_samples_per_second": 11.068, |
| "eval_steps_per_second": 1.845, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.4074074074074074, |
| "grad_norm": 33.19840621948242, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 7.2832, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 13.319454193115234, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 1.537, |
| "step": 3 |
| }, |
| { |
| "epoch": 3.037037037037037, |
| "grad_norm": 4.994159698486328, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 0.6703, |
| "step": 4 |
| }, |
| { |
| "epoch": 3.6296296296296298, |
| "grad_norm": 1.9377405643463135, |
| "learning_rate": 0.0, |
| "loss": 0.3186, |
| "step": 5 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 1, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.968083617316864e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
