| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028037383177570093, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 2.4644651412963867, | |
| "learning_rate": 2e-05, | |
| "loss": 1.455, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "eval_loss": 1.510602355003357, | |
| "eval_runtime": 16.4984, | |
| "eval_samples_per_second": 2.728, | |
| "eval_steps_per_second": 1.394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 2.558793306350708, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5614, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 2.8438074588775635, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "eval_loss": 1.4593942165374756, | |
| "eval_runtime": 16.7044, | |
| "eval_samples_per_second": 2.694, | |
| "eval_steps_per_second": 1.377, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3920749211418624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |