| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002650371788264743, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029448575425163807, | |
| "eval_loss": 2.0751140117645264, | |
| "eval_runtime": 392.124, | |
| "eval_samples_per_second": 14.587, | |
| "eval_steps_per_second": 1.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008834572627549142, | |
| "grad_norm": 45.209259033203125, | |
| "learning_rate": 3e-05, | |
| "loss": 8.1417, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017669145255098284, | |
| "grad_norm": 18.42889404296875, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002650371788264743, | |
| "grad_norm": 13.495532035827637, | |
| "learning_rate": 9e-05, | |
| "loss": 4.8841, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002650371788264743, | |
| "eval_loss": 1.0568773746490479, | |
| "eval_runtime": 394.6909, | |
| "eval_samples_per_second": 14.492, | |
| "eval_steps_per_second": 1.812, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2661897253879808e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |