| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.103030303030303, | |
| "eval_steps": 25, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 7.01023006439209, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.8111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "eval_loss": 4.974612712860107, | |
| "eval_runtime": 1.4564, | |
| "eval_samples_per_second": 34.331, | |
| "eval_steps_per_second": 8.926, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3878787878787879, | |
| "grad_norm": 5.500810623168945, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.2861, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 4.146025657653809, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.0022, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.7757575757575758, | |
| "grad_norm": 3.80722713470459, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.1037, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 4.564659118652344, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.987, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.1636363636363636, | |
| "grad_norm": 8.205465316772461, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9152, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.3575757575757577, | |
| "grad_norm": 3.277364730834961, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.5444, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.5515151515151515, | |
| "grad_norm": 2.7603092193603516, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.4397, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.7454545454545456, | |
| "grad_norm": 2.520108699798584, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.3199, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 2.309976816177368, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.6516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 5.165183067321777, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 5.748, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.327272727272727, | |
| "grad_norm": 1.971497893333435, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.948, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.5212121212121215, | |
| "grad_norm": 2.5606868267059326, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.3824, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.7151515151515153, | |
| "grad_norm": 2.4024603366851807, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.3981, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 2.4407458305358887, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.3679, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.103030303030303, | |
| "grad_norm": 5.35032844543457, | |
| "learning_rate": 1e-05, | |
| "loss": 5.9397, | |
| "step": 16 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 16, | |
| "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": 8142252970868736.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |