| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.343283582089552, | |
| "eval_steps": 25, | |
| "global_step": 7, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 1.9903051853179932, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 2.1582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "eval_loss": 1.844475507736206, | |
| "eval_runtime": 3.1969, | |
| "eval_samples_per_second": 15.64, | |
| "eval_steps_per_second": 4.066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 1.2216306924819946, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 1.841, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 2.3758370876312256, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 3.0861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.905314564704895, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 1.5611, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 1.9539397954940796, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 2.8408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 0.8861082792282104, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 1.4753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.343283582089552, | |
| "grad_norm": 1.6677148342132568, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4598, | |
| "step": 7 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 7, | |
| "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": 8.644271082255155e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |