| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12531328320802004, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02506265664160401, | |
| "grad_norm": 1.0692139863967896, | |
| "learning_rate": 2.5e-06, | |
| "loss": 4.188, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05012531328320802, | |
| "grad_norm": 1.1046545505523682, | |
| "learning_rate": 5e-06, | |
| "loss": 4.1657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "grad_norm": 1.2392791509628296, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 4.1205, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10025062656641603, | |
| "grad_norm": 1.4656062126159668, | |
| "learning_rate": 1e-05, | |
| "loss": 4.0411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12531328320802004, | |
| "grad_norm": 1.5381596088409424, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 3.8527, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.391402699718656e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |