checkpoint-340/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14781966001478197,
      "grad_norm": 0.20523984730243683,
      "learning_rate": 0.00019137254901960786,
      "loss": 1.0818,
      "step": 25
    },
    {
      "epoch": 0.29563932002956395,
      "grad_norm": 0.1347881406545639,
      "learning_rate": 0.0001815686274509804,
      "loss": 0.2846,
      "step": 50
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 0.11665232479572296,
      "learning_rate": 0.00017176470588235293,
      "loss": 0.2523,
      "step": 75
    },
    {
      "epoch": 0.5912786400591279,
      "grad_norm": 0.1508069485425949,
      "learning_rate": 0.0001619607843137255,
      "loss": 0.239,
      "step": 100
    },
    {
      "epoch": 0.7390983000739099,
      "grad_norm": 0.17151322960853577,
      "learning_rate": 0.00015215686274509804,
      "loss": 0.2397,
      "step": 125
    },
    {
      "epoch": 0.8869179600886918,
      "grad_norm": 0.21252259612083435,
      "learning_rate": 0.0001423529411764706,
      "loss": 0.2447,
      "step": 150
    },
    {
      "epoch": 1.0295639320029564,
      "grad_norm": 0.1654823124408722,
      "learning_rate": 0.00013254901960784313,
      "loss": 0.2216,
      "step": 175
    },
    {
      "epoch": 1.1773835920177385,
      "grad_norm": 0.16431653499603271,
      "learning_rate": 0.0001227450980392157,
      "loss": 0.2117,
      "step": 200
    },
    {
      "epoch": 1.3252032520325203,
      "grad_norm": 0.21554099023342133,
      "learning_rate": 0.00011294117647058824,
      "loss": 0.2034,
      "step": 225
    },
    {
      "epoch": 1.4730229120473024,
      "grad_norm": 0.2417294681072235,
      "learning_rate": 0.0001031372549019608,
      "loss": 0.2137,
      "step": 250
    },
    {
      "epoch": 1.6208425720620843,
      "grad_norm": 0.20341823995113373,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.2122,
      "step": 275
    },
    {
      "epoch": 1.7686622320768661,
      "grad_norm": 0.18581856787204742,
      "learning_rate": 8.352941176470589e-05,
      "loss": 0.2259,
      "step": 300
    },
    {
      "epoch": 1.9164818920916482,
      "grad_norm": 0.23839442431926727,
      "learning_rate": 7.372549019607843e-05,
      "loss": 0.2113,
      "step": 325
    }
  ],
  "logging_steps": 25,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7406961549115392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}