aliREA/Decoder_test2

1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.8,5  "eval_steps": 500,6  "global_step": 6,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.3,13      "grad_norm": 0.4690956175327301,14      "learning_rate": 0.00018888888888888888,15      "loss": 0.3743,16      "step": 117    },18    {19      "epoch": 0.6,20      "grad_norm": 0.42531049251556396,21      "learning_rate": 0.00017777777777777779,22      "loss": 0.3242,23      "step": 224    },25    {26      "epoch": 0.9,27      "grad_norm": 0.2975144386291504,28      "learning_rate": 0.0001666666666666667,29      "loss": 0.271,30      "step": 331    },32    {33      "epoch": 1.2,34      "grad_norm": 0.3152124881744385,35      "learning_rate": 0.00015555555555555556,36      "loss": 0.1879,37      "step": 438    },39    {40      "epoch": 1.5,41      "grad_norm": 0.29342710971832275,42      "learning_rate": 0.00014444444444444444,43      "loss": 0.2171,44      "step": 545    },46    {47      "epoch": 1.8,48      "grad_norm": 0.228942409157753,49      "learning_rate": 0.00013333333333333334,50      "loss": 0.1785,51      "step": 652    }53  ],54  "logging_steps": 1,55  "max_steps": 18,56  "num_input_tokens_seen": 0,57  "num_train_epochs": 6,58  "save_steps": 500,59  "stateful_callbacks": {60    "TrainerControl": {61      "args": {62        "should_epoch_stop": false,63        "should_evaluate": false,64        "should_log": false,65        "should_save": true,66        "should_training_stop": false67      },68      "attributes": {}69    }70  },71  "total_flos": 1.15357183377408e+16,72  "train_batch_size": 6,73  "trial_name": null,74  "trial_params": null75}76