{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00823799569564725,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.118997847823624e-05,
      "eval_loss": 1.339060664176941,
      "eval_runtime": 274.2472,
      "eval_samples_per_second": 37.277,
      "eval_steps_per_second": 18.64,
      "step": 1
    },
    {
      "epoch": 0.00041189978478236243,
      "grad_norm": 0.813252329826355,
      "learning_rate": 0.00019967573081342103,
      "loss": 1.2829,
      "step": 10
    },
    {
      "epoch": 0.0008237995695647249,
      "grad_norm": 0.7132832407951355,
      "learning_rate": 0.0001970941817426052,
      "loss": 1.0706,
      "step": 20
    },
    {
      "epoch": 0.0012356993543470873,
      "grad_norm": 0.773230254650116,
      "learning_rate": 0.00019199794436588243,
      "loss": 1.0452,
      "step": 30
    },
    {
      "epoch": 0.0016475991391294497,
      "grad_norm": 0.8867335319519043,
      "learning_rate": 0.0001845190085543795,
      "loss": 1.0197,
      "step": 40
    },
    {
      "epoch": 0.0020594989239118124,
      "grad_norm": 0.880136251449585,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.98,
      "step": 50
    },
    {
      "epoch": 0.0020594989239118124,
      "eval_loss": 0.9921454787254333,
      "eval_runtime": 274.2011,
      "eval_samples_per_second": 37.283,
      "eval_steps_per_second": 18.643,
      "step": 50
    },
    {
      "epoch": 0.0024713987086941746,
      "grad_norm": 0.918820321559906,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.9951,
      "step": 60
    },
    {
      "epoch": 0.0028832984934765373,
      "grad_norm": 0.7711983919143677,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9866,
      "step": 70
    },
    {
      "epoch": 0.0032951982782588995,
      "grad_norm": 0.7847739458084106,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.9617,
      "step": 80
    },
    {
      "epoch": 0.003707098063041262,
      "grad_norm": 0.6941512227058411,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.8879,
      "step": 90
    },
    {
      "epoch": 0.004118997847823625,
      "grad_norm": 0.8060756921768188,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.9394,
      "step": 100
    },
    {
      "epoch": 0.004118997847823625,
      "eval_loss": 0.9454370737075806,
      "eval_runtime": 274.0665,
      "eval_samples_per_second": 37.301,
      "eval_steps_per_second": 18.652,
      "step": 100
    },
    {
      "epoch": 0.004530897632605987,
      "grad_norm": 0.8922375440597534,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.9168,
      "step": 110
    },
    {
      "epoch": 0.004942797417388349,
      "grad_norm": 0.8508503437042236,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.9419,
      "step": 120
    },
    {
      "epoch": 0.005354697202170712,
      "grad_norm": 0.7896482348442078,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.9312,
      "step": 130
    },
    {
      "epoch": 0.0057665969869530745,
      "grad_norm": 0.8143855929374695,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.9023,
      "step": 140
    },
    {
      "epoch": 0.006178496771735437,
      "grad_norm": 0.7980097532272339,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.8894,
      "step": 150
    },
    {
      "epoch": 0.006178496771735437,
      "eval_loss": 0.9244847893714905,
      "eval_runtime": 273.882,
      "eval_samples_per_second": 37.326,
      "eval_steps_per_second": 18.665,
      "step": 150
    },
    {
      "epoch": 0.006590396556517799,
      "grad_norm": 0.770283579826355,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.862,
      "step": 160
    },
    {
      "epoch": 0.007002296341300162,
      "grad_norm": 0.8209188580513,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.9222,
      "step": 170
    },
    {
      "epoch": 0.007414196126082524,
      "grad_norm": 1.0810291767120361,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.8923,
      "step": 180
    },
    {
      "epoch": 0.007826095910864887,
      "grad_norm": 0.8928555250167847,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.9189,
      "step": 190
    },
    {
      "epoch": 0.00823799569564725,
      "grad_norm": 0.901564359664917,
      "learning_rate": 0.0,
      "loss": 0.9354,
      "step": 200
    },
    {
      "epoch": 0.00823799569564725,
      "eval_loss": 0.9190196394920349,
      "eval_runtime": 273.858,
      "eval_samples_per_second": 37.33,
      "eval_steps_per_second": 18.667,
      "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": 1.6400973299712e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}