| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 529, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1890359168241966, | |
| "grad_norm": 0.5558584332466125, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1103, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3780718336483932, | |
| "grad_norm": 0.4733140468597412, | |
| "learning_rate": 3e-05, | |
| "loss": 1.931, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5671077504725898, | |
| "grad_norm": 0.48580050468444824, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8948, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7561436672967864, | |
| "grad_norm": 0.40655234456062317, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8988, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.945179584120983, | |
| "grad_norm": 0.6303955316543579, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8745, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5701538461538461, | |
| "eval_loss": 1.6455246210098267, | |
| "eval_runtime": 5.0805, | |
| "eval_samples_per_second": 98.415, | |
| "eval_steps_per_second": 12.4, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 15.0, | |
| "eval_f1": 23.927619047619068, | |
| "step": 529 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 26450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.311002824835072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |