| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00034618247278140306, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1539415759380102e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1324.7781, | |
| "eval_samples_per_second": 27.543, | |
| "eval_steps_per_second": 13.772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.4618247278140306e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.923649455628061e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.231532607504082e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1327.3751, | |
| "eval_samples_per_second": 27.49, | |
| "eval_steps_per_second": 13.745, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00010385474183442092, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00013847298911256122, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00017309123639070153, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00018463065215008163, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1328.9321, | |
| "eval_samples_per_second": 27.457, | |
| "eval_steps_per_second": 13.729, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00020770948366884183, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00024232773094698217, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00027694597822512245, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00027694597822512245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1320.2211, | |
| "eval_samples_per_second": 27.639, | |
| "eval_steps_per_second": 13.82, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003115642255032628, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00034618247278140306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 476752851763200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |