| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006459627329192546, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6563146997929607e-05, | |
| "eval_loss": 1.7334619760513306, | |
| "eval_runtime": 1478.9308, | |
| "eval_samples_per_second": 17.189, | |
| "eval_steps_per_second": 8.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.281573498964803e-05, | |
| "grad_norm": 0.30731433629989624, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7783, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016563146997929605, | |
| "grad_norm": 0.3904305696487427, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00016563146997929605, | |
| "eval_loss": 1.6821030378341675, | |
| "eval_runtime": 1481.8112, | |
| "eval_samples_per_second": 17.155, | |
| "eval_steps_per_second": 8.578, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002484472049689441, | |
| "grad_norm": 0.34476760029792786, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7415, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003312629399585921, | |
| "grad_norm": 0.42384272813796997, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003312629399585921, | |
| "eval_loss": 1.6122349500656128, | |
| "eval_runtime": 1482.3023, | |
| "eval_samples_per_second": 17.15, | |
| "eval_steps_per_second": 8.575, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00041407867494824016, | |
| "grad_norm": 0.2773866057395935, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0004968944099378882, | |
| "grad_norm": 0.2703266143798828, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0004968944099378882, | |
| "eval_loss": 1.5814194679260254, | |
| "eval_runtime": 1476.9738, | |
| "eval_samples_per_second": 17.212, | |
| "eval_steps_per_second": 8.606, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005797101449275362, | |
| "grad_norm": 0.30390283465385437, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6012, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5576330921902080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |