| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0718232044198894, | |
| "eval_steps": 3, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08839779005524862, | |
| "grad_norm": 0.15974676609039307, | |
| "learning_rate": 1e-05, | |
| "loss": 11.758, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08839779005524862, | |
| "eval_loss": 11.772886276245117, | |
| "eval_runtime": 12.7217, | |
| "eval_samples_per_second": 5.974, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17679558011049723, | |
| "grad_norm": 0.17410075664520264, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7621, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 0.17219673097133636, | |
| "learning_rate": 3e-05, | |
| "loss": 11.7523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.1102, | |
| "eval_samples_per_second": 689.891, | |
| "eval_steps_per_second": 90.775, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.35359116022099446, | |
| "grad_norm": 0.21081098914146423, | |
| "learning_rate": 4e-05, | |
| "loss": 11.76, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4419889502762431, | |
| "grad_norm": 0.21257060766220093, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7497, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5303867403314917, | |
| "grad_norm": 0.213060200214386, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7588, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5303867403314917, | |
| "eval_loss": 11.777400970458984, | |
| "eval_runtime": 0.1098, | |
| "eval_samples_per_second": 691.988, | |
| "eval_steps_per_second": 91.051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6187845303867403, | |
| "grad_norm": 0.18384572863578796, | |
| "learning_rate": 7e-05, | |
| "loss": 11.7538, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7071823204419889, | |
| "grad_norm": 0.2052992433309555, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7604, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7955801104972375, | |
| "grad_norm": 0.1799938976764679, | |
| "learning_rate": 9e-05, | |
| "loss": 11.7505, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7955801104972375, | |
| "eval_loss": 11.764886856079102, | |
| "eval_runtime": 0.11, | |
| "eval_samples_per_second": 690.859, | |
| "eval_steps_per_second": 90.902, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8839779005524862, | |
| "grad_norm": 0.2259252965450287, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9723756906077348, | |
| "grad_norm": 0.21288780868053436, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7536, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0718232044198894, | |
| "grad_norm": 0.43436795473098755, | |
| "learning_rate": 0.0, | |
| "loss": 21.2546, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0718232044198894, | |
| "eval_loss": 11.7653169631958, | |
| "eval_runtime": 0.1338, | |
| "eval_samples_per_second": 568.056, | |
| "eval_steps_per_second": 74.744, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 78220816809984.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |