| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 4, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 24.14248275756836, |
| "learning_rate": 0.0, |
| "loss": 2.4073, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_cosine_accuracy": 0.8333333134651184, |
| "eval_loss": 1.1724432706832886, |
| "eval_runtime": 2.8395, |
| "eval_samples_per_second": 2.113, |
| "eval_steps_per_second": 0.352, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_cosine_accuracy": 0.8333333134651184, |
| "eval_loss": 1.1766316890716553, |
| "eval_runtime": 0.2923, |
| "eval_samples_per_second": 20.526, |
| "eval_steps_per_second": 3.421, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_cosine_accuracy": 0.8333333134651184, |
| "eval_loss": 1.1792185306549072, |
| "eval_runtime": 0.3021, |
| "eval_samples_per_second": 19.864, |
| "eval_steps_per_second": 3.311, |
| "step": 3 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_cosine_accuracy": 0.8333333134651184, |
| "eval_loss": 1.1788537502288818, |
| "eval_runtime": 0.3088, |
| "eval_samples_per_second": 19.428, |
| "eval_steps_per_second": 3.238, |
| "step": 4 |
| } |
| ], |
| "logging_steps": 4000, |
| "max_steps": 4, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
