| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 109, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09174311926605505, |
| "grad_norm": 3.399044990539551, |
| "learning_rate": 9.96283394041954e-05, |
| "loss": 0.8928, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1834862385321101, |
| "grad_norm": 2.4229464530944824, |
| "learning_rate": 9.551035271070664e-05, |
| "loss": 0.259, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.27522935779816515, |
| "grad_norm": 0.9839027523994446, |
| "learning_rate": 8.71912372061598e-05, |
| "loss": 0.1739, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3669724770642202, |
| "grad_norm": 0.5743712186813354, |
| "learning_rate": 7.543894290076103e-05, |
| "loss": 0.1485, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.45871559633027525, |
| "grad_norm": 0.4701073467731476, |
| "learning_rate": 6.133834168105206e-05, |
| "loss": 0.1151, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5504587155963303, |
| "grad_norm": 0.742197573184967, |
| "learning_rate": 4.619108116145411e-05, |
| "loss": 0.1047, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.6422018348623854, |
| "grad_norm": 0.45065852999687195, |
| "learning_rate": 3.1395427643746796e-05, |
| "loss": 0.1007, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.7339449541284404, |
| "grad_norm": 0.47702592611312866, |
| "learning_rate": 1.831719006082924e-05, |
| "loss": 0.1008, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8256880733944955, |
| "grad_norm": 0.32038915157318115, |
| "learning_rate": 8.163640108807896e-06, |
| "loss": 0.0822, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.9174311926605505, |
| "grad_norm": 0.3243330419063568, |
| "learning_rate": 1.8720671888242059e-06, |
| "loss": 0.0813, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 109, |
| "total_flos": 3.068167030348032e+16, |
| "train_loss": 0.19585996702176714, |
| "train_runtime": 128.7508, |
| "train_samples_per_second": 107.494, |
| "train_steps_per_second": 0.847 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 109, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 20000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.068167030348032e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
