| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12658227848101267, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004219409282700422, | |
| "eval_loss": 2.5663743019104004, | |
| "eval_runtime": 5.2669, | |
| "eval_samples_per_second": 18.987, | |
| "eval_steps_per_second": 9.493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": 3.0995514392852783, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3377, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": 1.6316229104995728, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2401, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03375527426160337, | |
| "eval_loss": 2.2458245754241943, | |
| "eval_runtime": 5.2759, | |
| "eval_samples_per_second": 18.954, | |
| "eval_steps_per_second": 9.477, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0379746835443038, | |
| "grad_norm": 1.8484519720077515, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 1.7582972049713135, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.0823, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06329113924050633, | |
| "grad_norm": 1.1602634191513062, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0754, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06751054852320675, | |
| "eval_loss": 2.117725133895874, | |
| "eval_runtime": 5.2809, | |
| "eval_samples_per_second": 18.936, | |
| "eval_steps_per_second": 9.468, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "grad_norm": 1.7242730855941772, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0674, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08860759493670886, | |
| "grad_norm": 1.357497215270996, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9841, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 1.8452017307281494, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.0563, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "eval_loss": 2.0715420246124268, | |
| "eval_runtime": 5.2919, | |
| "eval_samples_per_second": 18.897, | |
| "eval_steps_per_second": 9.448, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11392405063291139, | |
| "grad_norm": 1.4692493677139282, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.9065, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 1.197749376296997, | |
| "learning_rate": 0.0, | |
| "loss": 1.9786, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015894871572480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |