| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03397027600849257, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006794055201698514, | |
| "grad_norm": 0.817079484462738, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006794055201698514, | |
| "eval_loss": 1.4749836921691895, | |
| "eval_runtime": 65.0826, | |
| "eval_samples_per_second": 3.811, | |
| "eval_steps_per_second": 1.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013588110403397028, | |
| "grad_norm": 0.7562941312789917, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5222, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013588110403397028, | |
| "eval_loss": 1.4645147323608398, | |
| "eval_runtime": 2.2, | |
| "eval_samples_per_second": 112.726, | |
| "eval_steps_per_second": 56.363, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02038216560509554, | |
| "grad_norm": 0.8504584431648254, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027176220806794056, | |
| "grad_norm": 0.7962632179260254, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4063, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027176220806794056, | |
| "eval_loss": 1.4501497745513916, | |
| "eval_runtime": 2.235, | |
| "eval_samples_per_second": 110.961, | |
| "eval_steps_per_second": 55.48, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03397027600849257, | |
| "grad_norm": 0.6398099660873413, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5279, | |
| "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": 203318076899328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |