| { |
| "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": 0.8280937391233623, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": 0.0088, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.42892880209219414, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": 0.0101, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 1.2587642005258775, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -0.0003, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 1.6569925805278782, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -0.0143, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 2.25335102228849, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -0.0408, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 6.412934437634897, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -0.0923, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 10.127190796777503, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -0.2371, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 10.880609389032724, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -0.4302, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 9.262050609952361, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -0.6702, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 8.431759353354728, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -0.8539, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 8.344437225733662, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -1.0231, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 13.06416274535358, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -1.183, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 16.308042548119754, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -1.3728, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 14.833801792656182, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -1.5867, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 14.639882042570903, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -1.8048, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 12.766409117077956, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -1.9707, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 11.676823789591399, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -2.0969, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 10.437736093426334, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -2.1937, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 10.937875299607056, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -2.2787, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 11.115345766031535, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -2.3384, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 11.280806639200389, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -2.3696, |
| "step": 147 |
| } |
| ], |
| "logging_steps": 7, |
| "max_steps": 150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 150, |
| "save_steps": 0, |
| "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 |
| } |
|
|
