| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.158730158730159, |
| "eval_steps": 0, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.4761904761904763, |
| "grad_norm": 0.34064996242523193, |
| "learning_rate": 0.0001, |
| "loss": 4.3632, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.9523809523809526, |
| "grad_norm": 0.1575096845626831, |
| "learning_rate": 0.0001, |
| "loss": 0.0554, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.317460317460317, |
| "grad_norm": 0.16478388011455536, |
| "learning_rate": 0.0001, |
| "loss": 0.0546, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.7936507936507935, |
| "grad_norm": 0.140571728348732, |
| "learning_rate": 0.0001, |
| "loss": 0.0479, |
| "step": 40 |
| }, |
| { |
| "epoch": 7.158730158730159, |
| "grad_norm": 0.1423598974943161, |
| "learning_rate": 0.0001, |
| "loss": 0.0405, |
| "step": 50 |
| }, |
| { |
| "epoch": 7.158730158730159, |
| "step": 50, |
| "total_flos": 6.287430713700516e+17, |
| "train_loss": 0.912325621843338, |
| "train_runtime": 619.2374, |
| "train_samples_per_second": 12.919, |
| "train_steps_per_second": 0.081 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.287430713700516e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
