| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 8.578907482349805, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 0.8412, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 6.369087267807891, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.731, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.7364492282439006, |
| "learning_rate": 5e-06, |
| "loss": 0.5582, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 3.29244856700798, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.5174, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 1.992012474552257, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 0.4274, |
| "step": 5 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.8170643811808114, |
| "learning_rate": 0.0, |
| "loss": 0.4212, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 6, |
| "total_flos": 1638043484160.0, |
| "train_loss": 0.5827497492233912, |
| "train_runtime": 64.3617, |
| "train_samples_per_second": 7.302, |
| "train_steps_per_second": 0.093 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 6, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 5000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1638043484160.0, |
| "train_batch_size": 5, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
