{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3095,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03231017770597738,
      "grad_norm": 2.219433546066284,
      "learning_rate": 3.166397415185784e-06,
      "loss": 0.13468141555786134,
      "step": 100
    },
    {
      "epoch": 0.06462035541195477,
      "grad_norm": 1.7088854312896729,
      "learning_rate": 6.397415185783522e-06,
      "loss": 0.08345352172851563,
      "step": 200
    },
    {
      "epoch": 0.09693053311793215,
      "grad_norm": 1.8784979581832886,
      "learning_rate": 9.62843295638126e-06,
      "loss": 0.07643356323242187,
      "step": 300
    },
    {
      "epoch": 0.12924071082390953,
      "grad_norm": 3.160496234893799,
      "learning_rate": 1.2859450726979e-05,
      "loss": 0.07728703022003174,
      "step": 400
    },
    {
      "epoch": 0.16155088852988692,
      "grad_norm": 1.793244481086731,
      "learning_rate": 1.609046849757674e-05,
      "loss": 0.0715451717376709,
      "step": 500
    },
    {
      "epoch": 0.1938610662358643,
      "grad_norm": 0.49027326703071594,
      "learning_rate": 1.9321486268174476e-05,
      "loss": 0.07877041339874268,
      "step": 600
    },
    {
      "epoch": 0.22617124394184168,
      "grad_norm": 0.728702962398529,
      "learning_rate": 1.999007830695722e-05,
      "loss": 0.07102310180664062,
      "step": 700
    },
    {
      "epoch": 0.25848142164781907,
      "grad_norm": 2.55074405670166,
      "learning_rate": 1.9949097313414066e-05,
      "loss": 0.074349045753479,
      "step": 800
    },
    {
      "epoch": 0.29079159935379645,
      "grad_norm": 3.9224605560302734,
      "learning_rate": 1.9876486114300215e-05,
      "loss": 0.07766849994659424,
      "step": 900
    },
    {
      "epoch": 0.32310177705977383,
      "grad_norm": 0.9257252216339111,
      "learning_rate": 1.9772475555398188e-05,
      "loss": 0.0694255781173706,
      "step": 1000
    },
    {
      "epoch": 0.3554119547657512,
      "grad_norm": 0.8081497550010681,
      "learning_rate": 1.9637396307446846e-05,
      "loss": 0.07494896411895752,
      "step": 1100
    },
    {
      "epoch": 0.3877221324717286,
      "grad_norm": 2.14691424369812,
      "learning_rate": 1.9471677814871786e-05,
      "loss": 0.0675746250152588,
      "step": 1200
    },
    {
      "epoch": 0.420032310177706,
      "grad_norm": 0.38400450348854065,
      "learning_rate": 1.927584693049412e-05,
      "loss": 0.07241044998168945,
      "step": 1300
    },
    {
      "epoch": 0.45234248788368336,
      "grad_norm": 0.580016553401947,
      "learning_rate": 1.9050526240558083e-05,
      "loss": 0.07040606498718262,
      "step": 1400
    },
    {
      "epoch": 0.48465266558966075,
      "grad_norm": 1.0501762628555298,
      "learning_rate": 1.8796432085402662e-05,
      "loss": 0.07063678741455078,
      "step": 1500
    },
    {
      "epoch": 0.5169628432956381,
      "grad_norm": 0.9808917045593262,
      "learning_rate": 1.8514372282069805e-05,
      "loss": 0.067080078125,
      "step": 1600
    },
    {
      "epoch": 0.5492730210016155,
      "grad_norm": 0.8777210116386414,
      "learning_rate": 1.8205243556089643e-05,
      "loss": 0.06770069122314454,
      "step": 1700
    },
    {
      "epoch": 0.5815831987075929,
      "grad_norm": 1.6874562501907349,
      "learning_rate": 1.7870028690607476e-05,
      "loss": 0.07079707622528077,
      "step": 1800
    },
    {
      "epoch": 0.6138933764135702,
      "grad_norm": 1.3245418071746826,
      "learning_rate": 1.7509793401916104e-05,
      "loss": 0.06404186248779296,
      "step": 1900
    },
    {
      "epoch": 0.6462035541195477,
      "grad_norm": 0.3585558831691742,
      "learning_rate": 1.7125682951326795e-05,
      "loss": 0.06824737071990966,
      "step": 2000
    },
    {
      "epoch": 0.678513731825525,
      "grad_norm": 0.8804681897163391,
      "learning_rate": 1.671891850415046e-05,
      "loss": 0.07004157543182372,
      "step": 2100
    },
    {
      "epoch": 0.7108239095315024,
      "grad_norm": 0.6549601554870605,
      "learning_rate": 1.629079324736454e-05,
      "loss": 0.06939639568328858,
      "step": 2200
    },
    {
      "epoch": 0.7431340872374798,
      "grad_norm": 1.4602007865905762,
      "learning_rate": 1.584266827830838e-05,
      "loss": 0.06469368457794189,
      "step": 2300
    },
    {
      "epoch": 0.7754442649434572,
      "grad_norm": 1.0985392332077026,
      "learning_rate": 1.537596827747772e-05,
      "loss": 0.07550141334533692,
      "step": 2400
    },
    {
      "epoch": 0.8077544426494345,
      "grad_norm": 0.9523833394050598,
      "learning_rate": 1.4892176979175388e-05,
      "loss": 0.06276164531707763,
      "step": 2500
    },
    {
      "epoch": 0.840064620355412,
      "grad_norm": 0.4565122723579407,
      "learning_rate": 1.4392832454417938e-05,
      "loss": 0.0644590950012207,
      "step": 2600
    },
    {
      "epoch": 0.8723747980613893,
      "grad_norm": 2.104994058609009,
      "learning_rate": 1.387952222109479e-05,
      "loss": 0.06694219589233398,
      "step": 2700
    },
    {
      "epoch": 0.9046849757673667,
      "grad_norm": 1.4507120847702026,
      "learning_rate": 1.3353878196925727e-05,
      "loss": 0.059137086868286136,
      "step": 2800
    },
    {
      "epoch": 0.9369951534733441,
      "grad_norm": 1.1051520109176636,
      "learning_rate": 1.2817571511262256e-05,
      "loss": 0.06713937282562256,
      "step": 2900
    },
    {
      "epoch": 0.9693053311793215,
      "grad_norm": 1.7327321767807007,
      "learning_rate": 1.2272307192227245e-05,
      "loss": 0.0657884407043457,
      "step": 3000
    }
  ],
  "logging_steps": 100,
  "max_steps": 6190,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}