| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9787360300662644, |
| "eval_steps": 500, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.39560874295321924, |
| "grad_norm": 0.0, |
| "learning_rate": 0.00017831390620764436, |
| "loss": 2.9168, |
| "mean_token_accuracy": 0.4181546172648668, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7912174859064385, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0001512062889671998, |
| "loss": 2.9095, |
| "mean_token_accuracy": 0.4197094915360212, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.187518544159826, |
| "grad_norm": 0.0, |
| "learning_rate": 0.00012409867172675522, |
| "loss": 2.939, |
| "mean_token_accuracy": 0.4158593440304572, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.583127287113045, |
| "grad_norm": 0.0, |
| "learning_rate": 9.699105448631067e-05, |
| "loss": 2.8947, |
| "mean_token_accuracy": 0.42097397207841275, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.9787360300662644, |
| "grad_norm": 0.0, |
| "learning_rate": 6.98834372458661e-05, |
| "loss": 2.9123, |
| "mean_token_accuracy": 0.4193452677279711, |
| "step": 2500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3789, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8422274795002266e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
