| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.099601593625498, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00199203187250996, |
| "eval_loss": 1.1114661693572998, |
| "eval_runtime": 14.9557, |
| "eval_samples_per_second": 14.175, |
| "eval_steps_per_second": 7.088, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0099601593625498, |
| "grad_norm": 0.4821946322917938, |
| "learning_rate": 5e-05, |
| "loss": 1.1065, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0199203187250996, |
| "grad_norm": 0.5409933924674988, |
| "learning_rate": 0.0001, |
| "loss": 1.1812, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0199203187250996, |
| "eval_loss": 1.0850259065628052, |
| "eval_runtime": 14.8907, |
| "eval_samples_per_second": 14.237, |
| "eval_steps_per_second": 7.119, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.029880478087649404, |
| "grad_norm": 0.6434897780418396, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 1.0113, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0398406374501992, |
| "grad_norm": 0.9250468611717224, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.1422, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0398406374501992, |
| "eval_loss": 1.044611930847168, |
| "eval_runtime": 14.8938, |
| "eval_samples_per_second": 14.234, |
| "eval_steps_per_second": 7.117, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.049800796812749, |
| "grad_norm": 0.5784384608268738, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.9165, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.05976095617529881, |
| "grad_norm": 0.6139729619026184, |
| "learning_rate": 5e-05, |
| "loss": 1.1056, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.05976095617529881, |
| "eval_loss": 1.0264966487884521, |
| "eval_runtime": 14.9046, |
| "eval_samples_per_second": 14.224, |
| "eval_steps_per_second": 7.112, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0697211155378486, |
| "grad_norm": 0.5393847227096558, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.9776, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0796812749003984, |
| "grad_norm": 0.5789812803268433, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.9913, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0796812749003984, |
| "eval_loss": 1.020814299583435, |
| "eval_runtime": 14.9615, |
| "eval_samples_per_second": 14.17, |
| "eval_steps_per_second": 7.085, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.08964143426294821, |
| "grad_norm": 0.5929783582687378, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.9709, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.099601593625498, |
| "grad_norm": 0.6848423480987549, |
| "learning_rate": 0.0, |
| "loss": 1.0246, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.099601593625498, |
| "eval_loss": 1.0198479890823364, |
| "eval_runtime": 14.9231, |
| "eval_samples_per_second": 14.206, |
| "eval_steps_per_second": 7.103, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4163310278148096.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
