{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 3.875,
      "learning_rate": 4.934444103134438e-06,
      "loss": 0.3094,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 4.25,
      "learning_rate": 1.1102499232052485e-05,
      "loss": 0.2175,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.6796875,
      "learning_rate": 1.7270554360970535e-05,
      "loss": 0.1203,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.31640625,
      "learning_rate": 2.343860948988858e-05,
      "loss": 0.0886,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.271484375,
      "learning_rate": 2.960666461880663e-05,
      "loss": 0.0777,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.359375,
      "learning_rate": 3.577471974772468e-05,
      "loss": 0.0736,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.275390625,
      "learning_rate": 4.194277487664273e-05,
      "loss": 0.0706,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.291015625,
      "learning_rate": 4.8110830005560774e-05,
      "loss": 0.0679,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.322265625,
      "learning_rate": 5.427888513447882e-05,
      "loss": 0.0684,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.234375,
      "learning_rate": 6.0446940263396864e-05,
      "loss": 0.0648,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.32421875,
      "learning_rate": 6.166454446045803e-05,
      "loss": 0.0629,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.46484375,
      "learning_rate": 6.159954835897547e-05,
      "loss": 0.0639,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.37890625,
      "learning_rate": 6.14846795951453e-05,
      "loss": 0.0655,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.322265625,
      "learning_rate": 6.132014517024399e-05,
      "loss": 0.063,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.26171875,
      "learning_rate": 6.110624158642619e-05,
      "loss": 0.0623,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.39453125,
      "learning_rate": 6.084335431240784e-05,
      "loss": 0.0637,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.423828125,
      "learning_rate": 6.0531957088825416e-05,
      "loss": 0.0629,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.23828125,
      "learning_rate": 6.017261107452336e-05,
      "loss": 0.0614,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.2353515625,
      "learning_rate": 5.9765963835307865e-05,
      "loss": 0.0607,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.2578125,
      "learning_rate": 5.931274817698955e-05,
      "loss": 0.0605,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.291015625,
      "learning_rate": 5.881378082481784e-05,
      "loss": 0.0606,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.2490234375,
      "learning_rate": 5.826996095168686e-05,
      "loss": 0.0616,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.263671875,
      "learning_rate": 5.768226855776513e-05,
      "loss": 0.0621,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2197265625,
      "learning_rate": 5.705176270446901e-05,
      "loss": 0.0613,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.2265625,
      "learning_rate": 5.637957960596242e-05,
      "loss": 0.0591,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.197265625,
      "learning_rate": 5.566693058162216e-05,
      "loss": 0.0588,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.205078125,
      "learning_rate": 5.4915099873158475e-05,
      "loss": 0.0581,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.255859375,
      "learning_rate": 5.4125442330324754e-05,
      "loss": 0.0594,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.060138072818517685,
      "eval_runtime": 1.2495,
      "eval_samples_per_second": 19.207,
      "eval_steps_per_second": 19.207,
      "step": 140
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.255859375,
      "learning_rate": 5.329938096938664e-05,
      "loss": 0.0503,
      "step": 145
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.2431640625,
      "learning_rate": 5.243840440875054e-05,
      "loss": 0.0501,
      "step": 150
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.2412109375,
      "learning_rate": 5.154406418637269e-05,
      "loss": 0.0501,
      "step": 155
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.21484375,
      "learning_rate": 5.0617971963782815e-05,
      "loss": 0.0506,
      "step": 160
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.298828125,
      "learning_rate": 4.966179662176122e-05,
      "loss": 0.0504,
      "step": 165
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.27734375,
      "learning_rate": 4.867726125290271e-05,
      "loss": 0.0514,
      "step": 170
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.2392578125,
      "learning_rate": 4.766614005648736e-05,
      "loss": 0.0496,
      "step": 175
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.205078125,
      "learning_rate": 4.663025514125339e-05,
      "loss": 0.0492,
      "step": 180
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.29296875,
      "learning_rate": 4.557147324183422e-05,
      "loss": 0.0499,
      "step": 185
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.2451171875,
      "learning_rate": 4.4491702354776326e-05,
      "loss": 0.0506,
      "step": 190
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.2138671875,
      "learning_rate": 4.3392888300200596e-05,
      "loss": 0.0499,
      "step": 195
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.234375,
      "learning_rate": 4.227701121530291e-05,
      "loss": 0.0496,
      "step": 200
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.2138671875,
      "learning_rate": 4.1146081986013094e-05,
      "loss": 0.0503,
      "step": 205
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.2431640625,
      "learning_rate": 4.000213862324256e-05,
      "loss": 0.0507,
      "step": 210
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.1875,
      "learning_rate": 3.884724259025089e-05,
      "loss": 0.0504,
      "step": 215
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.2255859375,
      "learning_rate": 3.7683475087749684e-05,
      "loss": 0.0493,
      "step": 220
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.193359375,
      "learning_rate": 3.651293330343824e-05,
      "loss": 0.0476,
      "step": 225
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.228515625,
      "learning_rate": 3.533772663272954e-05,
      "loss": 0.0503,
      "step": 230
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.234375,
      "learning_rate": 3.415997287747719e-05,
      "loss": 0.0495,
      "step": 235
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.2080078125,
      "learning_rate": 3.298179442955327e-05,
      "loss": 0.0497,
      "step": 240
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.21484375,
      "learning_rate": 3.180531444615476e-05,
      "loss": 0.0498,
      "step": 245
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.21484375,
      "learning_rate": 3.06326530237308e-05,
      "loss": 0.0484,
      "step": 250
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.1904296875,
      "learning_rate": 2.94659233774255e-05,
      "loss": 0.0493,
      "step": 255
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.2119140625,
      "learning_rate": 2.8307228032921534e-05,
      "loss": 0.0504,
      "step": 260
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.1728515625,
      "learning_rate": 2.7158655037546628e-05,
      "loss": 0.0485,
      "step": 265
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.1728515625,
      "learning_rate": 2.602227419747125e-05,
      "loss": 0.049,
      "step": 270
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.2421875,
      "learning_rate": 2.4900133347777897e-05,
      "loss": 0.0495,
      "step": 275
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.255859375,
      "learning_rate": 2.379425466212396e-05,
      "loss": 0.0491,
      "step": 280
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.05861632898449898,
      "eval_runtime": 1.1424,
      "eval_samples_per_second": 21.008,
      "eval_steps_per_second": 21.008,
      "step": 280
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4.50841030950912e+17,
  "train_batch_size": 100,
  "trial_name": null,
  "trial_params": null
}