| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003981525720656155, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.963051441312311e-05, | |
| "eval_loss": 0.8125210404396057, | |
| "eval_runtime": 440.94, | |
| "eval_samples_per_second": 11.993, | |
| "eval_steps_per_second": 5.996, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039815257206561556, | |
| "grad_norm": 1.3683063983917236, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007963051441312311, | |
| "grad_norm": 2.482180595397949, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007963051441312311, | |
| "eval_loss": 0.5994144678115845, | |
| "eval_runtime": 450.0496, | |
| "eval_samples_per_second": 11.75, | |
| "eval_steps_per_second": 5.875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011944577161968467, | |
| "grad_norm": 4.2152509689331055, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0058, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015926102882624622, | |
| "grad_norm": 6.052931785583496, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7025, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015926102882624622, | |
| "eval_loss": 0.40628117322921753, | |
| "eval_runtime": 448.4239, | |
| "eval_samples_per_second": 11.792, | |
| "eval_steps_per_second": 5.896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019907628603280775, | |
| "grad_norm": 9.131941795349121, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4656, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0023889154323936935, | |
| "grad_norm": 6.8505659103393555, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8193, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023889154323936935, | |
| "eval_loss": 0.36222878098487854, | |
| "eval_runtime": 449.6465, | |
| "eval_samples_per_second": 11.76, | |
| "eval_steps_per_second": 5.88, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002787068004459309, | |
| "grad_norm": 5.405407905578613, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3195, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0031852205765249245, | |
| "grad_norm": 6.3843092918396, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3911, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0031852205765249245, | |
| "eval_loss": 0.34334591031074524, | |
| "eval_runtime": 449.44, | |
| "eval_samples_per_second": 11.766, | |
| "eval_steps_per_second": 5.883, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00358337314859054, | |
| "grad_norm": 5.103909015655518, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4029, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003981525720656155, | |
| "grad_norm": 4.658137798309326, | |
| "learning_rate": 0.0, | |
| "loss": 1.548, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003981525720656155, | |
| "eval_loss": 0.34125182032585144, | |
| "eval_runtime": 448.7319, | |
| "eval_samples_per_second": 11.784, | |
| "eval_steps_per_second": 5.892, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8162390153625600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |