{
  "best_metric": 0.9128336310386658,
  "best_model_checkpoint": "./outputs/public-irc-mistral-24b/checkpoint-24",
  "epoch": 0.9746192893401016,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 3.373054027557373,
      "learning_rate": 2e-05,
      "loss": 1.2957,
      "step": 1
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 3.194347381591797,
      "learning_rate": 4e-05,
      "loss": 1.3221,
      "step": 2
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 1.2986558675765991,
      "learning_rate": 6.000000000000001e-05,
      "loss": 1.2683,
      "step": 3
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 1.1605945825576782,
      "learning_rate": 8e-05,
      "loss": 1.1636,
      "step": 4
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.811213493347168,
      "learning_rate": 7.997668089464696e-05,
      "loss": 1.0964,
      "step": 5
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 0.7070867419242859,
      "learning_rate": 7.990675076762158e-05,
      "loss": 1.0897,
      "step": 6
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 0.674956738948822,
      "learning_rate": 7.97902911543238e-05,
      "loss": 1.0602,
      "step": 7
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 0.6653350591659546,
      "learning_rate": 7.962743784145323e-05,
      "loss": 1.0097,
      "step": 8
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 0.6503349542617798,
      "learning_rate": 7.941838070868787e-05,
      "loss": 1.0102,
      "step": 9
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 0.49681031703948975,
      "learning_rate": 7.916336350729293e-05,
      "loss": 1.0227,
      "step": 10
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 0.5602617263793945,
      "learning_rate": 7.886268357591766e-05,
      "loss": 0.9935,
      "step": 11
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 0.48682689666748047,
      "learning_rate": 7.851669149391198e-05,
      "loss": 0.9811,
      "step": 12
    },
    {
      "epoch": 0.5279187817258884,
      "grad_norm": 0.5210645198822021,
      "learning_rate": 7.812579067256644e-05,
      "loss": 0.9828,
      "step": 13
    },
    {
      "epoch": 0.5685279187817259,
      "grad_norm": 0.46042340993881226,
      "learning_rate": 7.769043688475283e-05,
      "loss": 0.9629,
      "step": 14
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 0.4750231206417084,
      "learning_rate": 7.721113773351333e-05,
      "loss": 0.9599,
      "step": 15
    },
    {
      "epoch": 0.649746192893401,
      "grad_norm": 0.44704967737197876,
      "learning_rate": 7.668845206021812e-05,
      "loss": 0.9417,
      "step": 16
    },
    {
      "epoch": 0.6903553299492385,
      "grad_norm": 0.45399850606918335,
      "learning_rate": 7.612298929298132e-05,
      "loss": 0.9442,
      "step": 17
    },
    {
      "epoch": 0.7309644670050761,
      "grad_norm": 0.48387065529823303,
      "learning_rate": 7.551540873609502e-05,
      "loss": 0.9388,
      "step": 18
    },
    {
      "epoch": 0.7715736040609137,
      "grad_norm": 0.4469858705997467,
      "learning_rate": 7.486641880131006e-05,
      "loss": 0.9357,
      "step": 19
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 0.4322652816772461,
      "learning_rate": 7.417677618185955e-05,
      "loss": 0.9191,
      "step": 20
    },
    {
      "epoch": 0.8527918781725888,
      "grad_norm": 0.4220181703567505,
      "learning_rate": 7.344728497018844e-05,
      "loss": 0.9269,
      "step": 21
    },
    {
      "epoch": 0.8934010152284264,
      "grad_norm": 0.4223184287548065,
      "learning_rate": 7.267879572041768e-05,
      "loss": 0.9092,
      "step": 22
    },
    {
      "epoch": 0.934010152284264,
      "grad_norm": 0.5329856276512146,
      "learning_rate": 7.187220445663618e-05,
      "loss": 0.8954,
      "step": 23
    },
    {
      "epoch": 0.9746192893401016,
      "grad_norm": 0.504860520362854,
      "learning_rate": 7.10284516281768e-05,
      "loss": 0.9145,
      "step": 24
    },
    {
      "epoch": 0.9746192893401016,
      "eval_loss": 0.9128336310386658,
      "eval_runtime": 89.3062,
      "eval_samples_per_second": 0.84,
      "eval_steps_per_second": 0.426,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 4.4736262854148096e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}