| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013183481098183977, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002636696219636795, | |
| "grad_norm": 0.38135769963264465, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002636696219636795, | |
| "eval_loss": 1.0587295293807983, | |
| "eval_runtime": 261.6537, | |
| "eval_samples_per_second": 24.414, | |
| "eval_steps_per_second": 12.207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000527339243927359, | |
| "grad_norm": 0.20315295457839966, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000527339243927359, | |
| "eval_loss": 1.0513490438461304, | |
| "eval_runtime": 185.372, | |
| "eval_samples_per_second": 34.46, | |
| "eval_steps_per_second": 17.23, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007910088658910385, | |
| "grad_norm": 0.32279691100120544, | |
| "learning_rate": 3e-05, | |
| "loss": 0.835, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001054678487854718, | |
| "grad_norm": 0.2902750074863434, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9151, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001054678487854718, | |
| "eval_loss": 1.0427939891815186, | |
| "eval_runtime": 185.0569, | |
| "eval_samples_per_second": 34.519, | |
| "eval_steps_per_second": 17.26, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013183481098183977, | |
| "grad_norm": 0.20842979848384857, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2104, | |
| "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": 778315820433408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |