| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.025550942190993294, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005110188438198659, | |
| "grad_norm": 1.0135972499847412, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005110188438198659, | |
| "eval_loss": 1.1604063510894775, | |
| "eval_runtime": 48.9942, | |
| "eval_samples_per_second": 6.735, | |
| "eval_steps_per_second": 3.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010220376876397317, | |
| "grad_norm": 0.9915676116943359, | |
| "learning_rate": 2e-05, | |
| "loss": 1.109, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010220376876397317, | |
| "eval_loss": 1.1345270872116089, | |
| "eval_runtime": 8.1476, | |
| "eval_samples_per_second": 40.503, | |
| "eval_steps_per_second": 20.251, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015330565314595975, | |
| "grad_norm": 1.0163768529891968, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0749, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020440753752794635, | |
| "grad_norm": 0.8627431988716125, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020440753752794635, | |
| "eval_loss": 1.1072744131088257, | |
| "eval_runtime": 8.0488, | |
| "eval_samples_per_second": 41.0, | |
| "eval_steps_per_second": 20.5, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025550942190993294, | |
| "grad_norm": 0.8725192546844482, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9856, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 648596517027840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |