| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005301524188204109, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005301524188204108, | |
| "grad_norm": 0.539082407951355, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005301524188204108, | |
| "eval_loss": 1.6137040853500366, | |
| "eval_runtime": 70.4487, | |
| "eval_samples_per_second": 11.285, | |
| "eval_steps_per_second": 5.65, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010603048376408217, | |
| "grad_norm": 0.5260076522827148, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4584, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015904572564612327, | |
| "grad_norm": 0.522720217704773, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015904572564612327, | |
| "eval_loss": 1.6069713830947876, | |
| "eval_runtime": 66.2061, | |
| "eval_samples_per_second": 12.008, | |
| "eval_steps_per_second": 6.012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021206096752816434, | |
| "grad_norm": 0.6277130842208862, | |
| "learning_rate": 8e-05, | |
| "loss": 1.666, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026507620941020544, | |
| "grad_norm": 0.7468717694282532, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031809145129224653, | |
| "grad_norm": 1.006897211074829, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7221, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031809145129224653, | |
| "eval_loss": 1.4851133823394775, | |
| "eval_runtime": 66.272, | |
| "eval_samples_per_second": 11.996, | |
| "eval_steps_per_second": 6.006, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037110669317428763, | |
| "grad_norm": 0.9897186160087585, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5271, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004241219350563287, | |
| "grad_norm": 1.0747867822647095, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5138, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004771371769383698, | |
| "grad_norm": 0.6603133678436279, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2162, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004771371769383698, | |
| "eval_loss": 1.1624972820281982, | |
| "eval_runtime": 66.2338, | |
| "eval_samples_per_second": 12.003, | |
| "eval_steps_per_second": 6.009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005301524188204109, | |
| "grad_norm": 0.514535665512085, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1227, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5689176081039360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |