| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.3076923076923077, |
| "eval_steps": 2, |
| "global_step": 5, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.47904515266418457, |
| "learning_rate": 0.0, |
| "loss": 2.965193033218384, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.456310510635376, |
| "learning_rate": 0.0001, |
| "loss": 2.7841198444366455, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "eval_accuracy": 0.5348454543007923, |
| "eval_loss": 2.749584436416626, |
| "eval_runtime": 2.0604, |
| "eval_samples_per_second": 24.267, |
| "eval_steps_per_second": 3.397, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.48338398337364197, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.890326499938965, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5952783823013306, |
| "learning_rate": 5e-05, |
| "loss": 2.643332004547119, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5556479950956826, |
| "eval_loss": 2.586768388748169, |
| "eval_runtime": 2.0408, |
| "eval_samples_per_second": 24.5, |
| "eval_steps_per_second": 3.43, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.3076923076923077, |
| "grad_norm": 0.4229271411895752, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 2.5542030334472656, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.3076923076923077, |
| "step": 5, |
| "total_flos": 197425390977024.0, |
| "train_loss": 2.7674348831176756, |
| "train_runtime": 14.3041, |
| "train_samples_per_second": 5.593, |
| "train_steps_per_second": 0.35 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 197425390977024.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
