{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3710729104919976,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07903576368306658,
      "grad_norm": 2.3245134353637695,
      "learning_rate": 1.948325863432639e-05,
      "loss": 2.9096,
      "step": 100
    },
    {
      "epoch": 0.15807152736613317,
      "grad_norm": 2.990708112716675,
      "learning_rate": 1.8955971526496178e-05,
      "loss": 0.7375,
      "step": 200
    },
    {
      "epoch": 0.23710729104919975,
      "grad_norm": 2.713043451309204,
      "learning_rate": 1.8428684418665965e-05,
      "loss": 0.4412,
      "step": 300
    },
    {
      "epoch": 0.31614305473226634,
      "grad_norm": 2.839672088623047,
      "learning_rate": 1.790139731083575e-05,
      "loss": 0.3861,
      "step": 400
    },
    {
      "epoch": 0.3951788184153329,
      "grad_norm": 2.5622401237487793,
      "learning_rate": 1.7374110203005538e-05,
      "loss": 0.3694,
      "step": 500
    },
    {
      "epoch": 0.4742145820983995,
      "grad_norm": 2.527787923812866,
      "learning_rate": 1.6846823095175325e-05,
      "loss": 0.3538,
      "step": 600
    },
    {
      "epoch": 0.5532503457814661,
      "grad_norm": 2.7099175453186035,
      "learning_rate": 1.631953598734511e-05,
      "loss": 0.3478,
      "step": 700
    },
    {
      "epoch": 0.6322861094645327,
      "grad_norm": 2.159538745880127,
      "learning_rate": 1.5792248879514898e-05,
      "loss": 0.338,
      "step": 800
    },
    {
      "epoch": 0.7113218731475993,
      "grad_norm": 2.3641576766967773,
      "learning_rate": 1.5264961771684685e-05,
      "loss": 0.3423,
      "step": 900
    },
    {
      "epoch": 0.7903576368306658,
      "grad_norm": 2.5248115062713623,
      "learning_rate": 1.4737674663854471e-05,
      "loss": 0.3244,
      "step": 1000
    },
    {
      "epoch": 0.8693934005137325,
      "grad_norm": 2.2045676708221436,
      "learning_rate": 1.4210387556024256e-05,
      "loss": 0.3215,
      "step": 1100
    },
    {
      "epoch": 0.948429164196799,
      "grad_norm": 2.5387887954711914,
      "learning_rate": 1.3683100448194043e-05,
      "loss": 0.3239,
      "step": 1200
    },
    {
      "epoch": 1.0274649278798655,
      "grad_norm": 2.1010782718658447,
      "learning_rate": 1.315581334036383e-05,
      "loss": 0.316,
      "step": 1300
    },
    {
      "epoch": 1.1065006915629323,
      "grad_norm": 2.8399364948272705,
      "learning_rate": 1.2628526232533616e-05,
      "loss": 0.3143,
      "step": 1400
    },
    {
      "epoch": 1.1855364552459988,
      "grad_norm": 2.4526548385620117,
      "learning_rate": 1.2101239124703401e-05,
      "loss": 0.3076,
      "step": 1500
    },
    {
      "epoch": 1.2645722189290654,
      "grad_norm": 2.1812686920166016,
      "learning_rate": 1.157395201687319e-05,
      "loss": 0.3074,
      "step": 1600
    },
    {
      "epoch": 1.343607982612132,
      "grad_norm": 2.12322735786438,
      "learning_rate": 1.1046664909042974e-05,
      "loss": 0.3019,
      "step": 1700
    },
    {
      "epoch": 1.4226437462951986,
      "grad_norm": 2.5394980907440186,
      "learning_rate": 1.0519377801212763e-05,
      "loss": 0.3114,
      "step": 1800
    },
    {
      "epoch": 1.5016795099782652,
      "grad_norm": 2.698906660079956,
      "learning_rate": 9.992090693382548e-06,
      "loss": 0.302,
      "step": 1900
    },
    {
      "epoch": 1.580715273661332,
      "grad_norm": 2.7786617279052734,
      "learning_rate": 9.464803585552334e-06,
      "loss": 0.2995,
      "step": 2000
    },
    {
      "epoch": 1.6597510373443982,
      "grad_norm": 2.2823212146759033,
      "learning_rate": 8.937516477722121e-06,
      "loss": 0.3117,
      "step": 2100
    },
    {
      "epoch": 1.738786801027465,
      "grad_norm": 2.129678726196289,
      "learning_rate": 8.410229369891908e-06,
      "loss": 0.3045,
      "step": 2200
    },
    {
      "epoch": 1.8178225647105315,
      "grad_norm": 1.627656102180481,
      "learning_rate": 7.882942262061694e-06,
      "loss": 0.297,
      "step": 2300
    },
    {
      "epoch": 1.896858328393598,
      "grad_norm": 1.6226264238357544,
      "learning_rate": 7.355655154231479e-06,
      "loss": 0.2987,
      "step": 2400
    },
    {
      "epoch": 1.9758940920766648,
      "grad_norm": 1.6640758514404297,
      "learning_rate": 6.828368046401266e-06,
      "loss": 0.3022,
      "step": 2500
    },
    {
      "epoch": 2.054929855759731,
      "grad_norm": 2.3779549598693848,
      "learning_rate": 6.3010809385710525e-06,
      "loss": 0.2985,
      "step": 2600
    },
    {
      "epoch": 2.133965619442798,
      "grad_norm": 2.0160937309265137,
      "learning_rate": 5.773793830740839e-06,
      "loss": 0.2986,
      "step": 2700
    },
    {
      "epoch": 2.2130013831258646,
      "grad_norm": 2.8362996578216553,
      "learning_rate": 5.246506722910625e-06,
      "loss": 0.2997,
      "step": 2800
    },
    {
      "epoch": 2.292037146808931,
      "grad_norm": 1.8160929679870605,
      "learning_rate": 4.7192196150804116e-06,
      "loss": 0.2847,
      "step": 2900
    },
    {
      "epoch": 2.3710729104919976,
      "grad_norm": 1.660947322845459,
      "learning_rate": 4.191932507250198e-06,
      "loss": 0.2913,
      "step": 3000
    }
  ],
  "logging_steps": 100,
  "max_steps": 3795,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9485385996265165e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}