{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7532956685499058,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003766478342749529,
      "eval_loss": 0.7905556559562683,
      "eval_runtime": 6.9494,
      "eval_samples_per_second": 16.116,
      "eval_steps_per_second": 8.058,
      "step": 1
    },
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 0.5194510221481323,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.6767,
      "step": 10
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 0.3418649137020111,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.5109,
      "step": 20
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.29763174057006836,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.4577,
      "step": 30
    },
    {
      "epoch": 0.15065913370998116,
      "grad_norm": 0.31743451952934265,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.4554,
      "step": 40
    },
    {
      "epoch": 0.18832391713747645,
      "grad_norm": 0.32205116748809814,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.4428,
      "step": 50
    },
    {
      "epoch": 0.18832391713747645,
      "eval_loss": 0.43825122714042664,
      "eval_runtime": 5.9413,
      "eval_samples_per_second": 18.851,
      "eval_steps_per_second": 9.426,
      "step": 50
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.30510589480400085,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.4543,
      "step": 60
    },
    {
      "epoch": 0.263653483992467,
      "grad_norm": 0.2747015357017517,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4222,
      "step": 70
    },
    {
      "epoch": 0.3013182674199623,
      "grad_norm": 0.321909099817276,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.4222,
      "step": 80
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.3133584260940552,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.4055,
      "step": 90
    },
    {
      "epoch": 0.3766478342749529,
      "grad_norm": 0.33860835433006287,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.4354,
      "step": 100
    },
    {
      "epoch": 0.3766478342749529,
      "eval_loss": 0.41263094544410706,
      "eval_runtime": 5.9368,
      "eval_samples_per_second": 18.865,
      "eval_steps_per_second": 9.433,
      "step": 100
    },
    {
      "epoch": 0.4143126177024482,
      "grad_norm": 0.34971070289611816,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.3719,
      "step": 110
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.29900649189949036,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.407,
      "step": 120
    },
    {
      "epoch": 0.4896421845574388,
      "grad_norm": 0.33400940895080566,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.4163,
      "step": 130
    },
    {
      "epoch": 0.527306967984934,
      "grad_norm": 0.30247005820274353,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.3844,
      "step": 140
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 0.4009445607662201,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.4035,
      "step": 150
    },
    {
      "epoch": 0.5649717514124294,
      "eval_loss": 0.3986522853374481,
      "eval_runtime": 5.9405,
      "eval_samples_per_second": 18.854,
      "eval_steps_per_second": 9.427,
      "step": 150
    },
    {
      "epoch": 0.6026365348399246,
      "grad_norm": 0.34540390968322754,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.4117,
      "step": 160
    },
    {
      "epoch": 0.64030131826742,
      "grad_norm": 0.2759045362472534,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.3965,
      "step": 170
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.34777021408081055,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.3756,
      "step": 180
    },
    {
      "epoch": 0.7156308851224106,
      "grad_norm": 0.3243567645549774,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.39,
      "step": 190
    },
    {
      "epoch": 0.7532956685499058,
      "grad_norm": 0.2695101201534271,
      "learning_rate": 0.0,
      "loss": 0.4128,
      "step": 200
    },
    {
      "epoch": 0.7532956685499058,
      "eval_loss": 0.3957762122154236,
      "eval_runtime": 5.9442,
      "eval_samples_per_second": 18.842,
      "eval_steps_per_second": 9.421,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.088705701838848e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}