{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5488867376573088,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030977734753146177,
      "grad_norm": 70.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 7.5845,
      "step": 10
    },
    {
      "epoch": 0.061955469506292354,
      "grad_norm": 52.5,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 7.5258,
      "step": 20
    },
    {
      "epoch": 0.09293320425943853,
      "grad_norm": 44.0,
      "learning_rate": 3e-06,
      "loss": 7.5572,
      "step": 30
    },
    {
      "epoch": 0.12391093901258471,
      "grad_norm": 46.25,
      "learning_rate": 4.000000000000001e-06,
      "loss": 7.5497,
      "step": 40
    },
    {
      "epoch": 0.15488867376573087,
      "grad_norm": 28.625,
      "learning_rate": 5e-06,
      "loss": 7.4982,
      "step": 50
    },
    {
      "epoch": 0.18586640851887706,
      "grad_norm": 38.5,
      "learning_rate": 6e-06,
      "loss": 7.4251,
      "step": 60
    },
    {
      "epoch": 0.21684414327202323,
      "grad_norm": 1968.0,
      "learning_rate": 7.000000000000001e-06,
      "loss": 7.3471,
      "step": 70
    },
    {
      "epoch": 0.24782187802516942,
      "grad_norm": 323584.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 7.2784,
      "step": 80
    },
    {
      "epoch": 0.2787996127783156,
      "grad_norm": 38.25,
      "learning_rate": 9e-06,
      "loss": 7.1812,
      "step": 90
    },
    {
      "epoch": 0.30977734753146174,
      "grad_norm": 46.25,
      "learning_rate": 1e-05,
      "loss": 7.083,
      "step": 100
    },
    {
      "epoch": 0.30977734753146174,
      "eval_loss": 6.660160064697266,
      "eval_runtime": 145.1043,
      "eval_samples_per_second": 10.337,
      "eval_steps_per_second": 2.584,
      "step": 100
    },
    {
      "epoch": 0.34075508228460794,
      "grad_norm": 75.0,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 6.8485,
      "step": 110
    },
    {
      "epoch": 0.3717328170377541,
      "grad_norm": 48.75,
      "learning_rate": 1.2e-05,
      "loss": 6.4221,
      "step": 120
    },
    {
      "epoch": 0.4027105517909003,
      "grad_norm": 88.0,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 5.869,
      "step": 130
    },
    {
      "epoch": 0.43368828654404645,
      "grad_norm": 108.5,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 5.026,
      "step": 140
    },
    {
      "epoch": 0.46466602129719264,
      "grad_norm": 253.0,
      "learning_rate": 1.5e-05,
      "loss": 3.9355,
      "step": 150
    },
    {
      "epoch": 0.49564375605033884,
      "grad_norm": 2528.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.0847,
      "step": 160
    },
    {
      "epoch": 0.526621490803485,
      "grad_norm": 165.0,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 2.6829,
      "step": 170
    },
    {
      "epoch": 0.5575992255566312,
      "grad_norm": 4768.0,
      "learning_rate": 1.8e-05,
      "loss": 2.4876,
      "step": 180
    },
    {
      "epoch": 0.5885769603097774,
      "grad_norm": 177.0,
      "learning_rate": 1.9e-05,
      "loss": 2.2394,
      "step": 190
    },
    {
      "epoch": 0.6195546950629235,
      "grad_norm": 1384.0,
      "learning_rate": 2e-05,
      "loss": 2.0657,
      "step": 200
    },
    {
      "epoch": 0.6195546950629235,
      "eval_loss": 0.878921389579773,
      "eval_runtime": 144.9013,
      "eval_samples_per_second": 10.352,
      "eval_steps_per_second": 2.588,
      "step": 200
    },
    {
      "epoch": 0.6505324298160697,
      "grad_norm": 81.5,
      "learning_rate": 2.1e-05,
      "loss": 2.0229,
      "step": 210
    },
    {
      "epoch": 0.6815101645692159,
      "grad_norm": 90.5,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.9117,
      "step": 220
    },
    {
      "epoch": 0.712487899322362,
      "grad_norm": 255.0,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.9205,
      "step": 230
    },
    {
      "epoch": 0.7434656340755083,
      "grad_norm": 226.0,
      "learning_rate": 2.4e-05,
      "loss": 1.8112,
      "step": 240
    },
    {
      "epoch": 0.7744433688286544,
      "grad_norm": 109.5,
      "learning_rate": 2.5e-05,
      "loss": 1.7503,
      "step": 250
    },
    {
      "epoch": 0.8054211035818006,
      "grad_norm": 67.0,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.687,
      "step": 260
    },
    {
      "epoch": 0.8363988383349468,
      "grad_norm": 103.0,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.7016,
      "step": 270
    },
    {
      "epoch": 0.8673765730880929,
      "grad_norm": 233.0,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.7346,
      "step": 280
    },
    {
      "epoch": 0.8983543078412392,
      "grad_norm": 92.5,
      "learning_rate": 2.9e-05,
      "loss": 1.656,
      "step": 290
    },
    {
      "epoch": 0.9293320425943853,
      "grad_norm": 47.25,
      "learning_rate": 3e-05,
      "loss": 1.5532,
      "step": 300
    },
    {
      "epoch": 0.9293320425943853,
      "eval_loss": 0.8598520755767822,
      "eval_runtime": 144.9013,
      "eval_samples_per_second": 10.352,
      "eval_steps_per_second": 2.588,
      "step": 300
    },
    {
      "epoch": 0.9603097773475314,
      "grad_norm": 188.0,
      "learning_rate": 3.1e-05,
      "loss": 1.5658,
      "step": 310
    },
    {
      "epoch": 0.9912875121006777,
      "grad_norm": 61.75,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.4423,
      "step": 320
    },
    {
      "epoch": 1.0222652468538238,
      "grad_norm": 48.5,
      "learning_rate": 3.3e-05,
      "loss": 1.5072,
      "step": 330
    },
    {
      "epoch": 1.05324298160697,
      "grad_norm": 72.5,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.4358,
      "step": 340
    },
    {
      "epoch": 1.084220716360116,
      "grad_norm": 498.0,
      "learning_rate": 3.5e-05,
      "loss": 1.3132,
      "step": 350
    },
    {
      "epoch": 1.1151984511132624,
      "grad_norm": 54.0,
      "learning_rate": 3.6e-05,
      "loss": 1.4264,
      "step": 360
    },
    {
      "epoch": 1.1461761858664086,
      "grad_norm": 61.75,
      "learning_rate": 3.7e-05,
      "loss": 1.3196,
      "step": 370
    },
    {
      "epoch": 1.1771539206195547,
      "grad_norm": 66.5,
      "learning_rate": 3.8e-05,
      "loss": 1.2922,
      "step": 380
    },
    {
      "epoch": 1.2081316553727008,
      "grad_norm": 41.25,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 1.4018,
      "step": 390
    },
    {
      "epoch": 1.239109390125847,
      "grad_norm": 52.5,
      "learning_rate": 4e-05,
      "loss": 1.1323,
      "step": 400
    },
    {
      "epoch": 1.239109390125847,
      "eval_loss": 0.31075239181518555,
      "eval_runtime": 144.8169,
      "eval_samples_per_second": 10.358,
      "eval_steps_per_second": 2.589,
      "step": 400
    },
    {
      "epoch": 1.2700871248789931,
      "grad_norm": 53.0,
      "learning_rate": 4.1e-05,
      "loss": 1.1657,
      "step": 410
    },
    {
      "epoch": 1.3010648596321395,
      "grad_norm": 888.0,
      "learning_rate": 4.2e-05,
      "loss": 1.1344,
      "step": 420
    },
    {
      "epoch": 1.3320425943852856,
      "grad_norm": 416.0,
      "learning_rate": 4.3e-05,
      "loss": 1.1697,
      "step": 430
    },
    {
      "epoch": 1.3630203291384317,
      "grad_norm": 960.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0632,
      "step": 440
    },
    {
      "epoch": 1.3939980638915779,
      "grad_norm": 42.5,
      "learning_rate": 4.5e-05,
      "loss": 0.9458,
      "step": 450
    },
    {
      "epoch": 1.424975798644724,
      "grad_norm": 35.5,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9597,
      "step": 460
    },
    {
      "epoch": 1.4559535333978704,
      "grad_norm": 90.0,
      "learning_rate": 4.7e-05,
      "loss": 0.8533,
      "step": 470
    },
    {
      "epoch": 1.4869312681510165,
      "grad_norm": 34.5,
      "learning_rate": 4.8e-05,
      "loss": 0.8736,
      "step": 480
    },
    {
      "epoch": 1.5179090029041626,
      "grad_norm": 16.0,
      "learning_rate": 4.9e-05,
      "loss": 0.9187,
      "step": 490
    },
    {
      "epoch": 1.5488867376573088,
      "grad_norm": 55.75,
      "learning_rate": 5e-05,
      "loss": 0.8223,
      "step": 500
    },
    {
      "epoch": 1.5488867376573088,
      "eval_loss": 0.17174342274665833,
      "eval_runtime": 144.8992,
      "eval_samples_per_second": 10.352,
      "eval_steps_per_second": 2.588,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 9660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.4733111165137715e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}