| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07672634271099744, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025575447570332483, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5373, | |
| "eval_samples_per_second": 21.891, | |
| "eval_steps_per_second": 11.012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0076726342710997444, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015345268542199489, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020460358056265986, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.1114, | |
| "eval_samples_per_second": 23.202, | |
| "eval_steps_per_second": 11.671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023017902813299233, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030690537084398978, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03836317135549872, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04092071611253197, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.1216, | |
| "eval_samples_per_second": 23.169, | |
| "eval_steps_per_second": 11.655, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04603580562659847, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05370843989769821, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.061381074168797956, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061381074168797956, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.1458, | |
| "eval_samples_per_second": 23.09, | |
| "eval_steps_per_second": 11.615, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06905370843989769, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07672634271099744, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2302869944401920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |