| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.269230769230769, | |
| "eval_steps": 25, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.022049378603696823, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "eval_loss": 10.376497268676758, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 703.335, | |
| "eval_steps_per_second": 106.566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.022089313715696335, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3785, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.020821381360292435, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.019955597817897797, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3779, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0897435897435896, | |
| "grad_norm": 0.03681916743516922, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 19.5494, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.294871794871795, | |
| "grad_norm": 0.020215725526213646, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3206, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.024511199444532394, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 10.4732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.7051282051282053, | |
| "grad_norm": 0.039325207471847534, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 10.3158, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.9102564102564101, | |
| "grad_norm": 0.027439570054411888, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.0088, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.1794871794871793, | |
| "grad_norm": 0.02728217840194702, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.8883, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.3846153846153846, | |
| "grad_norm": 0.02833603322505951, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 10.4045, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.58974358974359, | |
| "grad_norm": 0.02498561702668667, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3581, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.7948717948717947, | |
| "grad_norm": 0.03389596566557884, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 10.3767, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.064102564102564, | |
| "grad_norm": 0.04106740280985832, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 18.0558, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.269230769230769, | |
| "grad_norm": 0.04655333608388901, | |
| "learning_rate": 0.0, | |
| "loss": 11.0026, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 12830417879040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |