| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00823045267489712, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00205761316872428, | |
| "grad_norm": 0.019490934908390045, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00205761316872428, | |
| "eval_loss": 10.375575065612793, | |
| "eval_runtime": 27.8549, | |
| "eval_samples_per_second": 29.402, | |
| "eval_steps_per_second": 14.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00411522633744856, | |
| "grad_norm": 0.019118010997772217, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00411522633744856, | |
| "eval_loss": 10.375570297241211, | |
| "eval_runtime": 1.1146, | |
| "eval_samples_per_second": 734.793, | |
| "eval_steps_per_second": 367.845, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": 0.020525598898530006, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3758, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 0.01772131957113743, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3725, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "eval_loss": 10.375541687011719, | |
| "eval_runtime": 1.1438, | |
| "eval_samples_per_second": 716.006, | |
| "eval_steps_per_second": 358.44, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 206894530560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |