| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004854486759387364, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.708973518774727e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 153.5383, | |
| "eval_samples_per_second": 28.247, | |
| "eval_steps_per_second": 14.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009708973518774728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.9613, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012621665574407146, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.9124, | |
| "eval_samples_per_second": 28.549, | |
| "eval_steps_per_second": 14.278, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019417947037549455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.7588, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002524333114881429, | |
| "eval_loss": NaN, | |
| "eval_runtime": 152.0217, | |
| "eval_samples_per_second": 28.529, | |
| "eval_steps_per_second": 14.268, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002912692055632418, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.3445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037864996723221437, | |
| "eval_loss": NaN, | |
| "eval_runtime": 152.0274, | |
| "eval_samples_per_second": 28.528, | |
| "eval_steps_per_second": 14.267, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003883589407509891, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004854486759387364, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 184.8818, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 1.0340757676228608e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |