{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06513809275664409,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013027618551328818,
      "grad_norm": 14.949752807617188,
      "learning_rate": 4.0625e-06,
      "loss": 1.3439,
      "step": 1
    },
    {
      "epoch": 0.0026055237102657635,
      "grad_norm": 15.725403785705566,
      "learning_rate": 8.125e-06,
      "loss": 1.3354,
      "step": 2
    },
    {
      "epoch": 0.0039082855653986455,
      "grad_norm": 12.41278076171875,
      "learning_rate": 1.2187499999999998e-05,
      "loss": 1.3017,
      "step": 3
    },
    {
      "epoch": 0.005211047420531527,
      "grad_norm": 6.782334327697754,
      "learning_rate": 1.625e-05,
      "loss": 1.2634,
      "step": 4
    },
    {
      "epoch": 0.006513809275664409,
      "grad_norm": 3.730219841003418,
      "learning_rate": 2.03125e-05,
      "loss": 1.1704,
      "step": 5
    },
    {
      "epoch": 0.007816571130797291,
      "grad_norm": 2.547757863998413,
      "learning_rate": 2.4374999999999996e-05,
      "loss": 1.165,
      "step": 6
    },
    {
      "epoch": 0.009119332985930172,
      "grad_norm": 2.4353976249694824,
      "learning_rate": 2.8437499999999997e-05,
      "loss": 1.1567,
      "step": 7
    },
    {
      "epoch": 0.010422094841063054,
      "grad_norm": 2.218895673751831,
      "learning_rate": 3.25e-05,
      "loss": 1.0846,
      "step": 8
    },
    {
      "epoch": 0.011724856696195935,
      "grad_norm": 1.7433233261108398,
      "learning_rate": 3.6562499999999994e-05,
      "loss": 0.9816,
      "step": 9
    },
    {
      "epoch": 0.013027618551328817,
      "grad_norm": 1.6148579120635986,
      "learning_rate": 4.0625e-05,
      "loss": 1.0869,
      "step": 10
    },
    {
      "epoch": 0.0143303804064617,
      "grad_norm": 1.5065230131149292,
      "learning_rate": 4.4687499999999995e-05,
      "loss": 0.9625,
      "step": 11
    },
    {
      "epoch": 0.015633142261594582,
      "grad_norm": 1.4786823987960815,
      "learning_rate": 4.874999999999999e-05,
      "loss": 1.0489,
      "step": 12
    },
    {
      "epoch": 0.016935904116727463,
      "grad_norm": 1.2991230487823486,
      "learning_rate": 5.2812499999999996e-05,
      "loss": 0.9935,
      "step": 13
    },
    {
      "epoch": 0.018238665971860343,
      "grad_norm": 1.3199464082717896,
      "learning_rate": 5.687499999999999e-05,
      "loss": 1.0188,
      "step": 14
    },
    {
      "epoch": 0.019541427826993224,
      "grad_norm": 1.2793257236480713,
      "learning_rate": 6.09375e-05,
      "loss": 1.0265,
      "step": 15
    },
    {
      "epoch": 0.020844189682126108,
      "grad_norm": 1.2210655212402344,
      "learning_rate": 6.5e-05,
      "loss": 0.9019,
      "step": 16
    },
    {
      "epoch": 0.02214695153725899,
      "grad_norm": 1.3837445974349976,
      "learning_rate": 6.499971563731688e-05,
      "loss": 0.9487,
      "step": 17
    },
    {
      "epoch": 0.02344971339239187,
      "grad_norm": 1.2946529388427734,
      "learning_rate": 6.499886255424368e-05,
      "loss": 1.0031,
      "step": 18
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 1.3142110109329224,
      "learning_rate": 6.499744076570868e-05,
      "loss": 0.9941,
      "step": 19
    },
    {
      "epoch": 0.026055237102657634,
      "grad_norm": 1.8206599950790405,
      "learning_rate": 6.499545029659211e-05,
      "loss": 0.9767,
      "step": 20
    },
    {
      "epoch": 0.027357998957790515,
      "grad_norm": 1.2736281156539917,
      "learning_rate": 6.499289118172568e-05,
      "loss": 0.9194,
      "step": 21
    },
    {
      "epoch": 0.0286607608129234,
      "grad_norm": 1.8105640411376953,
      "learning_rate": 6.498976346589196e-05,
      "loss": 0.9853,
      "step": 22
    },
    {
      "epoch": 0.02996352266805628,
      "grad_norm": 1.4621827602386475,
      "learning_rate": 6.49860672038236e-05,
      "loss": 0.9896,
      "step": 23
    },
    {
      "epoch": 0.031266284523189164,
      "grad_norm": 1.212299108505249,
      "learning_rate": 6.498180246020238e-05,
      "loss": 0.9684,
      "step": 24
    },
    {
      "epoch": 0.032569046378322045,
      "grad_norm": 1.2274290323257446,
      "learning_rate": 6.49769693096581e-05,
      "loss": 0.9831,
      "step": 25
    },
    {
      "epoch": 0.033871808233454925,
      "grad_norm": 1.2909352779388428,
      "learning_rate": 6.49715678367672e-05,
      "loss": 0.9971,
      "step": 26
    },
    {
      "epoch": 0.035174570088587806,
      "grad_norm": 1.2330715656280518,
      "learning_rate": 6.49655981360514e-05,
      "loss": 0.9923,
      "step": 27
    },
    {
      "epoch": 0.03647733194372069,
      "grad_norm": 1.2433793544769287,
      "learning_rate": 6.495906031197591e-05,
      "loss": 0.9121,
      "step": 28
    },
    {
      "epoch": 0.03778009379885357,
      "grad_norm": 1.2374027967453003,
      "learning_rate": 6.49519544789477e-05,
      "loss": 0.9224,
      "step": 29
    },
    {
      "epoch": 0.03908285565398645,
      "grad_norm": 1.2204357385635376,
      "learning_rate": 6.494428076131346e-05,
      "loss": 0.919,
      "step": 30
    },
    {
      "epoch": 0.040385617509119336,
      "grad_norm": 1.1927292346954346,
      "learning_rate": 6.493603929335744e-05,
      "loss": 0.9589,
      "step": 31
    },
    {
      "epoch": 0.041688379364252216,
      "grad_norm": 1.1353641748428345,
      "learning_rate": 6.492723021929908e-05,
      "loss": 0.8869,
      "step": 32
    },
    {
      "epoch": 0.0429911412193851,
      "grad_norm": 1.212263822555542,
      "learning_rate": 6.49178536932905e-05,
      "loss": 0.8934,
      "step": 33
    },
    {
      "epoch": 0.04429390307451798,
      "grad_norm": 1.0893241167068481,
      "learning_rate": 6.49079098794138e-05,
      "loss": 0.8718,
      "step": 34
    },
    {
      "epoch": 0.04559666492965086,
      "grad_norm": 1.1801607608795166,
      "learning_rate": 6.489739895167818e-05,
      "loss": 0.9774,
      "step": 35
    },
    {
      "epoch": 0.04689942678478374,
      "grad_norm": 1.1302330493927002,
      "learning_rate": 6.488632109401691e-05,
      "loss": 0.9584,
      "step": 36
    },
    {
      "epoch": 0.04820218863991663,
      "grad_norm": 1.1432682275772095,
      "learning_rate": 6.487467650028411e-05,
      "loss": 0.9452,
      "step": 37
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 1.1399481296539307,
      "learning_rate": 6.486246537425133e-05,
      "loss": 0.9017,
      "step": 38
    },
    {
      "epoch": 0.05080771235018239,
      "grad_norm": 1.0911235809326172,
      "learning_rate": 6.484968792960403e-05,
      "loss": 0.9036,
      "step": 39
    },
    {
      "epoch": 0.05211047420531527,
      "grad_norm": 1.071078896522522,
      "learning_rate": 6.48363443899378e-05,
      "loss": 0.9273,
      "step": 40
    },
    {
      "epoch": 0.05341323606044815,
      "grad_norm": 1.053589105606079,
      "learning_rate": 6.482243498875449e-05,
      "loss": 0.8847,
      "step": 41
    },
    {
      "epoch": 0.05471599791558103,
      "grad_norm": 1.109771490097046,
      "learning_rate": 6.480795996945806e-05,
      "loss": 0.9364,
      "step": 42
    },
    {
      "epoch": 0.05601875977071391,
      "grad_norm": 1.1093286275863647,
      "learning_rate": 6.479291958535037e-05,
      "loss": 0.9088,
      "step": 43
    },
    {
      "epoch": 0.0573215216258468,
      "grad_norm": 1.0716255903244019,
      "learning_rate": 6.477731409962675e-05,
      "loss": 0.8885,
      "step": 44
    },
    {
      "epoch": 0.05862428348097968,
      "grad_norm": 1.1552095413208008,
      "learning_rate": 6.476114378537138e-05,
      "loss": 0.9736,
      "step": 45
    },
    {
      "epoch": 0.05992704533611256,
      "grad_norm": 1.1647394895553589,
      "learning_rate": 6.474440892555249e-05,
      "loss": 0.9138,
      "step": 46
    },
    {
      "epoch": 0.06122980719124544,
      "grad_norm": 1.1463412046432495,
      "learning_rate": 6.472710981301745e-05,
      "loss": 0.9204,
      "step": 47
    },
    {
      "epoch": 0.06253256904637833,
      "grad_norm": 1.175421118736267,
      "learning_rate": 6.470924675048762e-05,
      "loss": 0.9119,
      "step": 48
    },
    {
      "epoch": 0.06383533090151121,
      "grad_norm": 1.9249529838562012,
      "learning_rate": 6.469082005055304e-05,
      "loss": 0.8639,
      "step": 49
    },
    {
      "epoch": 0.06513809275664409,
      "grad_norm": 1.1802655458450317,
      "learning_rate": 6.467183003566701e-05,
      "loss": 0.9352,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 767,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.689981500994355e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}