| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 129, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47058823529411764, |
| "grad_norm": 0.44545748829841614, |
| "learning_rate": 7.6e-05, |
| "loss": 0.687, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9411764705882353, |
| "grad_norm": 0.3853379189968109, |
| "learning_rate": 0.00015600000000000002, |
| "loss": 0.6039, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.4913628101348877, |
| "learning_rate": 0.00017721518987341773, |
| "loss": 0.4516, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.8705882352941177, |
| "grad_norm": 0.7104933261871338, |
| "learning_rate": 0.00012658227848101267, |
| "loss": 0.4665, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.3294117647058825, |
| "grad_norm": 0.3440960645675659, |
| "learning_rate": 7.59493670886076e-05, |
| "loss": 0.3683, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.470425546169281, |
| "learning_rate": 2.5316455696202533e-05, |
| "loss": 0.3161, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 129, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1761705519193088e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
