| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009051821679112922, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018103643358225842, | |
| "grad_norm": 0.17819726467132568, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018103643358225842, | |
| "eval_loss": 0.719778299331665, | |
| "eval_runtime": 404.5555, | |
| "eval_samples_per_second": 2.301, | |
| "eval_steps_per_second": 1.152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036207286716451684, | |
| "grad_norm": 0.18435272574424744, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7975, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036207286716451684, | |
| "eval_loss": 0.7125133275985718, | |
| "eval_runtime": 148.2555, | |
| "eval_samples_per_second": 6.28, | |
| "eval_steps_per_second": 3.143, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005431093007467753, | |
| "grad_norm": 0.1686888337135315, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007241457343290337, | |
| "grad_norm": 0.17673583328723907, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7164, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007241457343290337, | |
| "eval_loss": 0.7069319486618042, | |
| "eval_runtime": 150.9996, | |
| "eval_samples_per_second": 6.166, | |
| "eval_steps_per_second": 3.086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009051821679112922, | |
| "grad_norm": 0.1695946305990219, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7241, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6508900547297280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |