| { |
| "best_global_step": 32, |
| "best_metric": 1.1013036966323853, |
| "best_model_checkpoint": "./finetuning/checkpoint-32", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.625, |
| "grad_norm": 2.963273286819458, |
| "learning_rate": 4.71875e-05, |
| "loss": 1.1393531799316405, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7275, |
| "eval_loss": 1.117279052734375, |
| "eval_runtime": 99.7594, |
| "eval_samples_per_second": 20.048, |
| "eval_steps_per_second": 1.253, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 1.9508087635040283, |
| "learning_rate": 4.40625e-05, |
| "loss": 0.8301602363586426, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 1.7418757677078247, |
| "learning_rate": 4.09375e-05, |
| "loss": 0.5593328952789307, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.733, |
| "eval_loss": 1.1013036966323853, |
| "eval_runtime": 99.7792, |
| "eval_samples_per_second": 20.044, |
| "eval_steps_per_second": 1.253, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 1.2206847667694092, |
| "learning_rate": 3.78125e-05, |
| "loss": 0.4049041271209717, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.729, |
| "eval_loss": 1.130679965019226, |
| "eval_runtime": 98.8399, |
| "eval_samples_per_second": 20.235, |
| "eval_steps_per_second": 1.265, |
| "step": 48 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 160, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 4, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.876443281620992e+18, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
