| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03836317135549872, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012787723785166241, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1109, | |
| "eval_samples_per_second": 18.221, | |
| "eval_steps_per_second": 9.111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038363171355498722, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00639386189258312, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1315, | |
| "eval_samples_per_second": 18.2, | |
| "eval_steps_per_second": 9.1, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0076726342710997444, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011508951406649617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01278772378516624, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1165, | |
| "eval_samples_per_second": 18.215, | |
| "eval_steps_per_second": 9.108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015345268542199489, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01918158567774936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01918158567774936, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1468, | |
| "eval_samples_per_second": 18.185, | |
| "eval_steps_per_second": 9.093, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023017902813299233, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02557544757033248, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1339, | |
| "eval_samples_per_second": 18.198, | |
| "eval_steps_per_second": 9.099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026854219948849106, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030690537084398978, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0319693094629156, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1357, | |
| "eval_samples_per_second": 18.196, | |
| "eval_steps_per_second": 9.098, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034526854219948847, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03836317135549872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03836317135549872, | |
| "eval_loss": NaN, | |
| "eval_runtime": 18.1036, | |
| "eval_samples_per_second": 18.228, | |
| "eval_steps_per_second": 9.114, | |
| "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": 9888459569233920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |