| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9980657640232108, |
| "eval_steps": 500, |
| "global_step": 129, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07736943907156674, |
| "grad_norm": 0.7897351384162903, |
| "learning_rate": 2e-05, |
| "loss": 1.7966, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15473887814313347, |
| "grad_norm": 0.546701192855835, |
| "learning_rate": 4e-05, |
| "loss": 1.6821, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23210831721470018, |
| "grad_norm": 0.24719476699829102, |
| "learning_rate": 6e-05, |
| "loss": 1.4684, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30947775628626695, |
| "grad_norm": 0.19408376514911652, |
| "learning_rate": 8e-05, |
| "loss": 1.3593, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38684719535783363, |
| "grad_norm": 0.18511685729026794, |
| "learning_rate": 0.0001, |
| "loss": 1.2809, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.46421663442940037, |
| "grad_norm": 0.18041056394577026, |
| "learning_rate": 0.00012, |
| "loss": 1.1822, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5415860735009671, |
| "grad_norm": 0.18419483304023743, |
| "learning_rate": 0.00014, |
| "loss": 1.0731, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6189555125725339, |
| "grad_norm": 0.22910986840724945, |
| "learning_rate": 0.00016, |
| "loss": 1.0346, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6963249516441006, |
| "grad_norm": 0.20705537497997284, |
| "learning_rate": 0.00018, |
| "loss": 0.983, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7736943907156673, |
| "grad_norm": 0.22625038027763367, |
| "learning_rate": 0.0002, |
| "loss": 0.9447, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.23730379343032837, |
| "learning_rate": 0.00019802973668046363, |
| "loss": 0.9222, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9284332688588007, |
| "grad_norm": 0.20882545411586761, |
| "learning_rate": 0.00019219658547282067, |
| "loss": 0.9112, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 258, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.7984509185097728e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
