| { |
| "best_metric": 0.37884894013404846, |
| "best_model_checkpoint": "./opt_trained2/checkpoint-3212", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 3212, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.6226650062266501, |
| "grad_norm": 0.7334734201431274, |
| "learning_rate": 0.0003875716064757161, |
| "loss": 3.2343, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.4036673307418823, |
| "eval_runtime": 273.6748, |
| "eval_samples_per_second": 10.436, |
| "eval_steps_per_second": 2.609, |
| "step": 803 |
| }, |
| { |
| "epoch": 1.2453300124533002, |
| "grad_norm": 1.277639627456665, |
| "learning_rate": 0.0003751183063511831, |
| "loss": 3.2109, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.86799501867995, |
| "grad_norm": 1.1930288076400757, |
| "learning_rate": 0.00036273972602739727, |
| "loss": 3.4898, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.3986678719520569, |
| "eval_runtime": 273.4619, |
| "eval_samples_per_second": 10.444, |
| "eval_steps_per_second": 2.611, |
| "step": 1606 |
| }, |
| { |
| "epoch": 2.4906600249066004, |
| "grad_norm": 0.363370418548584, |
| "learning_rate": 0.0003502864259028643, |
| "loss": 3.1553, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.3892712891101837, |
| "eval_runtime": 273.5885, |
| "eval_samples_per_second": 10.439, |
| "eval_steps_per_second": 2.61, |
| "step": 2409 |
| }, |
| { |
| "epoch": 3.1133250311332503, |
| "grad_norm": 0.4317278563976288, |
| "learning_rate": 0.0003378331257783313, |
| "loss": 3.0505, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.7359900373599, |
| "grad_norm": 0.3730609118938446, |
| "learning_rate": 0.00032537982565379825, |
| "loss": 2.9785, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.37884894013404846, |
| "eval_runtime": 273.844, |
| "eval_samples_per_second": 10.429, |
| "eval_steps_per_second": 2.607, |
| "step": 3212 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 16060, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 1.2514885666272e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
