| { |
| "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": 37.5044046375821, |
| "learning_rate": 9.59731543624161e-06, |
| "loss": -1.9117, |
| "step": 7 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 45.00127802344571, |
| "learning_rate": 9.12751677852349e-06, |
| "loss": -1.4476, |
| "step": 14 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 40.05225460455974, |
| "learning_rate": 8.65771812080537e-06, |
| "loss": -3.2214, |
| "step": 21 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 40.16944169799428, |
| "learning_rate": 8.18791946308725e-06, |
| "loss": -3.0378, |
| "step": 28 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 41.13756360863679, |
| "learning_rate": 7.718120805369127e-06, |
| "loss": -3.8818, |
| "step": 35 |
| }, |
| { |
| "epoch": 42.0, |
| "grad_norm": 55.1024136090307, |
| "learning_rate": 7.248322147651007e-06, |
| "loss": -5.3167, |
| "step": 42 |
| }, |
| { |
| "epoch": 49.0, |
| "grad_norm": 140.68733117692003, |
| "learning_rate": 6.778523489932887e-06, |
| "loss": -6.6341, |
| "step": 49 |
| }, |
| { |
| "epoch": 56.0, |
| "grad_norm": 85.21425439592477, |
| "learning_rate": 6.308724832214766e-06, |
| "loss": -8.3786, |
| "step": 56 |
| }, |
| { |
| "epoch": 63.0, |
| "grad_norm": 109.94497985536023, |
| "learning_rate": 5.8389261744966455e-06, |
| "loss": -10.4618, |
| "step": 63 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 81.23958484658506, |
| "learning_rate": 5.369127516778524e-06, |
| "loss": -10.9961, |
| "step": 70 |
| }, |
| { |
| "epoch": 77.0, |
| "grad_norm": 72.06612033628436, |
| "learning_rate": 4.899328859060403e-06, |
| "loss": -13.0287, |
| "step": 77 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 75.20052396097407, |
| "learning_rate": 4.429530201342283e-06, |
| "loss": -13.3461, |
| "step": 84 |
| }, |
| { |
| "epoch": 91.0, |
| "grad_norm": 81.19736224228653, |
| "learning_rate": 3.959731543624161e-06, |
| "loss": -14.2969, |
| "step": 91 |
| }, |
| { |
| "epoch": 98.0, |
| "grad_norm": 78.1687708906577, |
| "learning_rate": 3.4899328859060407e-06, |
| "loss": -15.6283, |
| "step": 98 |
| }, |
| { |
| "epoch": 105.0, |
| "grad_norm": 80.8166786798015, |
| "learning_rate": 3.02013422818792e-06, |
| "loss": -17.2069, |
| "step": 105 |
| }, |
| { |
| "epoch": 112.0, |
| "grad_norm": 82.45670556197513, |
| "learning_rate": 2.5503355704697992e-06, |
| "loss": -17.8644, |
| "step": 112 |
| }, |
| { |
| "epoch": 119.0, |
| "grad_norm": 84.53298328916162, |
| "learning_rate": 2.080536912751678e-06, |
| "loss": -18.5074, |
| "step": 119 |
| }, |
| { |
| "epoch": 126.0, |
| "grad_norm": 88.23278473005284, |
| "learning_rate": 1.6107382550335572e-06, |
| "loss": -19.0334, |
| "step": 126 |
| }, |
| { |
| "epoch": 133.0, |
| "grad_norm": 95.45835500057268, |
| "learning_rate": 1.1409395973154363e-06, |
| "loss": -19.6337, |
| "step": 133 |
| }, |
| { |
| "epoch": 140.0, |
| "grad_norm": 90.86469808647496, |
| "learning_rate": 6.711409395973155e-07, |
| "loss": -20.0151, |
| "step": 140 |
| }, |
| { |
| "epoch": 147.0, |
| "grad_norm": 90.82034838230379, |
| "learning_rate": 2.0134228187919465e-07, |
| "loss": -20.7169, |
| "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 |
| } |
|
|
