| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 150.0, |
| "eval_steps": 0, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.6834083574931933, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.0077, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.27994771756475606, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": 0.0055, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 0.9970344621134015, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 1.167522528199649, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0071, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 2.96448431380143, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.0241, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 3.1200182251586424, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.076, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 3.244187248897048, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.1611, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 4.048629013533452, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.2365, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 3.4576160857873113, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.3255, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 4.646397810632367, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.4084, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 5.3273333610843805, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -0.5018, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 5.755614854110475, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -0.5957, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 7.204085937960347, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -0.7083, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 8.295607189381665, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -0.8364, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 10.34850908448477, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -0.9974, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 10.830194831407763, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -1.1473, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 11.118775309462283, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -1.2966, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 10.752585975666898, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -1.4174, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 11.719391797642974, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -1.5186, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 12.42346614515245, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -1.6052, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 12.654166394331199, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -1.6596, |
| "step": 147 |
| } |
| ], |
| "logging_steps": 7, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 150, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
