| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18796992481203006, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037593984962406013, | |
| "eval_loss": 4.221013069152832, | |
| "eval_runtime": 11.9374, | |
| "eval_samples_per_second": 9.382, | |
| "eval_steps_per_second": 4.691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018796992481203006, | |
| "grad_norm": 1.9136879444122314, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9849, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03759398496240601, | |
| "grad_norm": 2.47013521194458, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03759398496240601, | |
| "eval_loss": 3.3705058097839355, | |
| "eval_runtime": 12.098, | |
| "eval_samples_per_second": 9.258, | |
| "eval_steps_per_second": 4.629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05639097744360902, | |
| "grad_norm": 3.2527971267700195, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "grad_norm": 3.517575740814209, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "eval_loss": 2.3837223052978516, | |
| "eval_runtime": 12.1674, | |
| "eval_samples_per_second": 9.205, | |
| "eval_steps_per_second": 4.602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09398496240601503, | |
| "grad_norm": 3.1065804958343506, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.373, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11278195488721804, | |
| "grad_norm": 2.54834246635437, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1893, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11278195488721804, | |
| "eval_loss": 2.230018138885498, | |
| "eval_runtime": 12.1899, | |
| "eval_samples_per_second": 9.188, | |
| "eval_steps_per_second": 4.594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 3.29943585395813, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2817, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 2.248333215713501, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "eval_loss": 2.1822826862335205, | |
| "eval_runtime": 12.215, | |
| "eval_samples_per_second": 9.169, | |
| "eval_steps_per_second": 4.585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16917293233082706, | |
| "grad_norm": 4.86949348449707, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9816, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18796992481203006, | |
| "grad_norm": 2.6801929473876953, | |
| "learning_rate": 0.0, | |
| "loss": 1.925, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18796992481203006, | |
| "eval_loss": 2.1708285808563232, | |
| "eval_runtime": 12.147, | |
| "eval_samples_per_second": 9.22, | |
| "eval_steps_per_second": 4.61, | |
| "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": 1.4611557560352768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |