trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04740670508585058,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002962919067865661,
      "grad_norm": 0.0781773254275322,
      "learning_rate": 0.0004985778620526191,
      "loss": 1.4945,
      "step": 50
    },
    {
      "epoch": 0.005925838135731322,
      "grad_norm": 0.08408337086439133,
      "learning_rate": 0.0004970964683574307,
      "loss": 1.1653,
      "step": 100
    },
    {
      "epoch": 0.008888757203596984,
      "grad_norm": 0.10583573579788208,
      "learning_rate": 0.0004956150746622422,
      "loss": 1.1169,
      "step": 150
    },
    {
      "epoch": 0.011851676271462644,
      "grad_norm": 0.08750592172145844,
      "learning_rate": 0.0004941336809670538,
      "loss": 1.0972,
      "step": 200
    },
    {
      "epoch": 0.014814595339328307,
      "grad_norm": 0.07067917287349701,
      "learning_rate": 0.0004926522872718654,
      "loss": 1.1012,
      "step": 250
    },
    {
      "epoch": 0.017777514407193967,
      "grad_norm": 0.12936587631702423,
      "learning_rate": 0.0004911708935766769,
      "loss": 1.0908,
      "step": 300
    },
    {
      "epoch": 0.02074043347505963,
      "grad_norm": 0.09118826687335968,
      "learning_rate": 0.0004896894998814885,
      "loss": 1.0773,
      "step": 350
    },
    {
      "epoch": 0.02370335254292529,
      "grad_norm": 0.08850109577178955,
      "learning_rate": 0.00048820810618630005,
      "loss": 1.1012,
      "step": 400
    },
    {
      "epoch": 0.02666627161079095,
      "grad_norm": 0.07888604700565338,
      "learning_rate": 0.00048672671249111167,
      "loss": 1.1343,
      "step": 450
    },
    {
      "epoch": 0.029629190678656613,
      "grad_norm": 0.0906878113746643,
      "learning_rate": 0.00048524531879592323,
      "loss": 1.1184,
      "step": 500
    },
    {
      "epoch": 0.032592109746522276,
      "grad_norm": 0.07720430195331573,
      "learning_rate": 0.0004837639251007348,
      "loss": 1.0968,
      "step": 550
    },
    {
      "epoch": 0.035555028814387934,
      "grad_norm": 0.0831717997789383,
      "learning_rate": 0.00048228253140554636,
      "loss": 1.0983,
      "step": 600
    },
    {
      "epoch": 0.03851794788225359,
      "grad_norm": 0.09815791249275208,
      "learning_rate": 0.0004808011377103579,
      "loss": 1.1235,
      "step": 650
    },
    {
      "epoch": 0.04148086695011926,
      "grad_norm": 0.07672577351331711,
      "learning_rate": 0.0004793197440151695,
      "loss": 1.0744,
      "step": 700
    },
    {
      "epoch": 0.04444378601798492,
      "grad_norm": 0.08625241369009018,
      "learning_rate": 0.0004778679781938848,
      "loss": 1.0897,
      "step": 750
    },
    {
      "epoch": 0.04740670508585058,
      "grad_norm": 0.10188218951225281,
      "learning_rate": 0.0004763865844986964,
      "loss": 1.0737,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 16876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.4844182233088e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}