| { |
| "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": 0.7576484911831471, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.0041, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 1.3404509421096586, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -0.0052, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 1.9583405277968773, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0348, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.01152110460163, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0854, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 1.84855280500219, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.15, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 1.5462092066736608, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.2106, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 1.716881099357167, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.2723, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 1.9332709383703668, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.3203, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 2.39820620704032, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.3831, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 3.6163205680692396, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.4539, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 5.114662300332845, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -0.5525, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 6.914185006846521, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -0.7022, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 7.51579096852159, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -0.8843, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 7.30376399528173, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -1.0668, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 8.682473400334242, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -1.2584, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 9.438173214381765, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -1.4349, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 10.00089683617346, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -1.5962, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 9.831779515720486, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -1.7416, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 10.987364996999428, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -1.8826, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 11.23246387856771, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -1.9851, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 11.34982152768313, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -2.0228, |
| "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 |
| } |
|
|
