| { |
| "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": 0.8471220819687227, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.0078, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.34016548845162425, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": 0.0053, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 1.1168056621468856, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0005, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.060412519842383, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0082, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 3.77419735563003, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.0312, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 3.4528292508395344, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.086, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 3.7230768721459584, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.1654, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 4.581784861891046, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.2394, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 4.339056584745866, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.3258, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 5.992049974643026, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.4109, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 6.971427065201847, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -0.5093, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 7.662762854251727, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -0.6128, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 9.984439380595688, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -0.7371, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 10.352750492450491, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -0.879, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 12.47397500910868, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -1.0461, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 12.98063160722281, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -1.1937, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 13.393692554215617, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -1.3365, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 13.056810374190105, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -1.4556, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 15.048035064118682, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -1.5582, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 16.0053868709308, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -1.6484, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 16.225398426773744, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -1.704, |
| "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 |
| } |
|
|
