| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00015078218257209272, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.026072752403091e-05, | |
| "grad_norm": 2.244288682937622, | |
| "learning_rate": 2e-05, | |
| "loss": 2.649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.026072752403091e-05, | |
| "eval_loss": 2.738063335418701, | |
| "eval_runtime": 602.7397, | |
| "eval_samples_per_second": 13.9, | |
| "eval_steps_per_second": 6.95, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010052145504806182, | |
| "grad_norm": 2.3517963886260986, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8619, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00015078218257209272, | |
| "grad_norm": 2.521275520324707, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015078218257209272, | |
| "eval_loss": 2.727404832839966, | |
| "eval_runtime": 630.5941, | |
| "eval_samples_per_second": 13.286, | |
| "eval_steps_per_second": 6.643, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 216286290247680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |