Reshcode/java-coder-llama8B

1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 0.5600672080649678,5  "eval_steps": 500,6  "global_step": 500,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.11201344161299356,13      "grad_norm": 24.437002182006836,14      "learning_rate": 0.000425,15      "loss": 11.2945,16      "step": 10017    },18    {19      "epoch": 0.22402688322598713,20      "grad_norm": 2.8428707122802734,21      "learning_rate": 0.0004859240052689831,22      "loss": 9.0685,23      "step": 20024    },25    {26      "epoch": 0.33604032483898066,27      "grad_norm": 2.8141651153564453,28      "learning_rate": 0.0004356534373254316,29      "loss": 8.5419,30      "step": 30031    },32    {33      "epoch": 0.44805376645197426,34      "grad_norm": 447.9421691894531,35      "learning_rate": 0.00035655248499579206,36      "loss": 8.8585,37      "step": 40038    },39    {40      "epoch": 0.5600672080649678,41      "grad_norm": 3.154489278793335,42      "learning_rate": 0.00026090484684133404,43      "loss": 8.9436,44      "step": 50045    },46    {47      "epoch": 0.5600672080649678,48      "eval_loss": 23.479717254638672,49      "eval_runtime": 52.8168,50      "eval_samples_per_second": 1.893,51      "eval_steps_per_second": 0.947,52      "step": 50053    }54  ],55  "logging_steps": 100,56  "max_steps": 892,57  "num_input_tokens_seen": 0,58  "num_train_epochs": 1,59  "save_steps": 500,60  "stateful_callbacks": {61    "TrainerControl": {62      "args": {63        "should_epoch_stop": false,64        "should_evaluate": false,65        "should_log": false,66        "should_save": true,67        "should_training_stop": false68      },69      "attributes": {}70    }71  },72  "total_flos": 9.2249505398784e+16,73  "train_batch_size": 2,74  "trial_name": null,75  "trial_params": null76}77