trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1228803145736053,
  "eval_steps": 500,
  "global_step": 7500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008192020971573687,
      "grad_norm": 0.2447698563337326,
      "learning_rate": 0.0001494,
      "loss": 2.4052,
      "step": 500
    },
    {
      "epoch": 0.016384041943147375,
      "grad_norm": 0.29972031712532043,
      "learning_rate": 0.00029939999999999996,
      "loss": 1.8314,
      "step": 1000
    },
    {
      "epoch": 0.024576062914721062,
      "grad_norm": 0.22787177562713623,
      "learning_rate": 0.0004494,
      "loss": 1.6945,
      "step": 1500
    },
    {
      "epoch": 0.03276808388629475,
      "grad_norm": 0.21664758026599884,
      "learning_rate": 0.0005993999999999999,
      "loss": 1.5686,
      "step": 2000
    },
    {
      "epoch": 0.04096010485786843,
      "grad_norm": 0.177582785487175,
      "learning_rate": 0.0005998946571323422,
      "loss": 1.4698,
      "step": 2500
    },
    {
      "epoch": 0.049152125829442124,
      "grad_norm": 0.21073713898658752,
      "learning_rate": 0.0005995770092517366,
      "loss": 1.41,
      "step": 3000
    },
    {
      "epoch": 0.05734414680101581,
      "grad_norm": 0.17612150311470032,
      "learning_rate": 0.0005990472795339199,
      "loss": 1.3714,
      "step": 3500
    },
    {
      "epoch": 0.0655361677725895,
      "grad_norm": 0.17588965594768524,
      "learning_rate": 0.0005983058429944914,
      "loss": 1.3247,
      "step": 4000
    },
    {
      "epoch": 0.07372818874416319,
      "grad_norm": 0.17322216928005219,
      "learning_rate": 0.0005973532245242761,
      "loss": 1.2806,
      "step": 4500
    },
    {
      "epoch": 0.08192020971573687,
      "grad_norm": 0.1861853152513504,
      "learning_rate": 0.0005961900985177338,
      "loss": 1.279,
      "step": 5000
    },
    {
      "epoch": 0.09011223068731056,
      "grad_norm": 0.14911051094532013,
      "learning_rate": 0.0005948172883955301,
      "loss": 1.2516,
      "step": 5500
    },
    {
      "epoch": 0.09830425165888425,
      "grad_norm": 0.18009094893932343,
      "learning_rate": 0.000593235766021606,
      "loss": 1.2326,
      "step": 6000
    },
    {
      "epoch": 0.10649627263045794,
      "grad_norm": 0.15231232345104218,
      "learning_rate": 0.000591446651015159,
      "loss": 1.2247,
      "step": 6500
    },
    {
      "epoch": 0.11468829360203162,
      "grad_norm": 0.14419229328632355,
      "learning_rate": 0.0005894512099580222,
      "loss": 1.2203,
      "step": 7000
    },
    {
      "epoch": 0.1228803145736053,
      "grad_norm": 0.1426558941602707,
      "learning_rate": 0.0005872508554980035,
      "loss": 1.2077,
      "step": 7500
    }
  ],
  "logging_steps": 500,
  "max_steps": 61035,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2542017536e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}