| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004024934469035676, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.049868938071353e-05, | |
| "grad_norm": 3.37302303314209, | |
| "learning_rate": 1e-05, | |
| "loss": 177.75, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.049868938071353e-05, | |
| "eval_loss": 11.112937927246094, | |
| "eval_runtime": 117.3181, | |
| "eval_samples_per_second": 178.344, | |
| "eval_steps_per_second": 89.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016099737876142705, | |
| "grad_norm": 3.5934317111968994, | |
| "learning_rate": 2e-05, | |
| "loss": 177.8125, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016099737876142705, | |
| "eval_loss": 11.112866401672363, | |
| "eval_runtime": 93.7607, | |
| "eval_samples_per_second": 223.153, | |
| "eval_steps_per_second": 111.582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024149606814214056, | |
| "grad_norm": 3.309920072555542, | |
| "learning_rate": 3e-05, | |
| "loss": 177.75, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003219947575228541, | |
| "grad_norm": 3.6221368312835693, | |
| "learning_rate": 4e-05, | |
| "loss": 177.75, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003219947575228541, | |
| "eval_loss": 11.112495422363281, | |
| "eval_runtime": 94.4901, | |
| "eval_samples_per_second": 221.43, | |
| "eval_steps_per_second": 110.721, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004024934469035676, | |
| "grad_norm": 3.487070083618164, | |
| "learning_rate": 5e-05, | |
| "loss": 177.8125, | |
| "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": 238708850688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |