| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.4210526315789473, |
| "eval_steps": 500, |
| "global_step": 12, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21052631578947367, |
| "grad_norm": 6.0625, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.538, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "grad_norm": 6.15625, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.5346, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "grad_norm": 6.03125, |
| "learning_rate": 6e-06, |
| "loss": 0.5295, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.8421052631578947, |
| "grad_norm": 5.9375, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.5205, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.1875, |
| "learning_rate": 1e-05, |
| "loss": 0.465, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.2105263157894737, |
| "grad_norm": 4.625, |
| "learning_rate": 1.2e-05, |
| "loss": 0.3812, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.4210526315789473, |
| "grad_norm": 3.453125, |
| "learning_rate": 1.4e-05, |
| "loss": 0.2928, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.631578947368421, |
| "grad_norm": 2.65625, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.2065, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.8421052631578947, |
| "grad_norm": 2.125, |
| "learning_rate": 1.8e-05, |
| "loss": 0.1665, |
| "step": 9 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.5234375, |
| "learning_rate": 2e-05, |
| "loss": 0.1252, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.2105263157894735, |
| "grad_norm": 0.984375, |
| "learning_rate": 1e-05, |
| "loss": 0.0615, |
| "step": 11 |
| }, |
| { |
| "epoch": 2.4210526315789473, |
| "grad_norm": 0.6875, |
| "learning_rate": 0.0, |
| "loss": 0.0366, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.4210526315789473, |
| "step": 12, |
| "total_flos": 3104270972583936.0, |
| "train_loss": 0.3214962125445406, |
| "train_runtime": 430.3556, |
| "train_samples_per_second": 2.091, |
| "train_steps_per_second": 0.028 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 12, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3104270972583936.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
