{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9230769230769234,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 31.073850631713867,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.5967,
      "step": 1
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 32.91181182861328,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.723,
      "step": 2
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 31.494897842407227,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6125,
      "step": 3
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 30.80953598022461,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.58,
      "step": 4
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 31.269071578979492,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.5977,
      "step": 5
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 30.687875747680664,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.5588,
      "step": 6
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 31.30279541015625,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.5731,
      "step": 7
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 31.384830474853516,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.561,
      "step": 8
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 30.58422088623047,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.4872,
      "step": 9
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 30.883068084716797,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.5257,
      "step": 10
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 32.198814392089844,
      "learning_rate": 5.5e-07,
      "loss": 2.6286,
      "step": 11
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 31.001300811767578,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.4632,
      "step": 12
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 31.106016159057617,
      "learning_rate": 6.5e-07,
      "loss": 2.4274,
      "step": 13
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 31.180011749267578,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.3864,
      "step": 14
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 30.95736312866211,
      "learning_rate": 7.5e-07,
      "loss": 2.2977,
      "step": 15
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 31.67963218688965,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.2632,
      "step": 16
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 32.420562744140625,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.1983,
      "step": 17
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 32.46091079711914,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.0623,
      "step": 18
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 31.34447479248047,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.8633,
      "step": 19
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 31.65386962890625,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7861,
      "step": 20
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 30.12110137939453,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.6408,
      "step": 21
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 28.824857711791992,
      "learning_rate": 1.1e-06,
      "loss": 1.5022,
      "step": 22
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 27.37271499633789,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.3799,
      "step": 23
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 26.869949340820312,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.2699,
      "step": 24
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 26.696306228637695,
      "learning_rate": 1.25e-06,
      "loss": 1.107,
      "step": 25
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 29.182300567626953,
      "learning_rate": 1.3e-06,
      "loss": 0.9981,
      "step": 26
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 28.117998123168945,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7886,
      "step": 27
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 27.153093338012695,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.6565,
      "step": 28
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 24.350711822509766,
      "learning_rate": 1.45e-06,
      "loss": 0.5143,
      "step": 29
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 21.189594268798828,
      "learning_rate": 1.5e-06,
      "loss": 0.3953,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 21.189594268798828,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.2703,
      "step": 31
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 25.850399017333984,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.2846,
      "step": 32
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 7.641750335693359,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.1964,
      "step": 33
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 5.204587459564209,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.195,
      "step": 34
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 5.610931396484375,
      "learning_rate": 1.75e-06,
      "loss": 0.2097,
      "step": 35
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 3.679949998855591,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.1428,
      "step": 36
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 2.877136707305908,
      "learning_rate": 1.85e-06,
      "loss": 0.1506,
      "step": 37
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.788109302520752,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.1384,
      "step": 38
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 1.154598355293274,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.1255,
      "step": 39
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 1.1099777221679688,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1291,
      "step": 40
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 1.022336483001709,
      "learning_rate": 2.05e-06,
      "loss": 0.1149,
      "step": 41
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.8197290897369385,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.1175,
      "step": 42
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 1.283385992050171,
      "learning_rate": 2.15e-06,
      "loss": 0.1137,
      "step": 43
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.9875780344009399,
      "learning_rate": 2.2e-06,
      "loss": 0.117,
      "step": 44
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5812683701515198,
      "learning_rate": 2.25e-06,
      "loss": 0.1089,
      "step": 45
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.8154236674308777,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1102,
      "step": 46
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.6170194149017334,
      "learning_rate": 2.35e-06,
      "loss": 0.1108,
      "step": 47
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.8121249675750732,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.1077,
      "step": 48
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.7454224824905396,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.1089,
      "step": 49
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 1.021628499031067,
      "learning_rate": 2.5e-06,
      "loss": 0.1075,
      "step": 50
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.8242588639259338,
      "learning_rate": 2.55e-06,
      "loss": 0.1056,
      "step": 51
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.7174047827720642,
      "learning_rate": 2.6e-06,
      "loss": 0.1062,
      "step": 52
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.676979660987854,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.1062,
      "step": 53
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.44768354296684265,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.1073,
      "step": 54
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 1.0064852237701416,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.1033,
      "step": 55
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 1.3364107608795166,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.1041,
      "step": 56
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.187800645828247,
      "learning_rate": 2.85e-06,
      "loss": 0.1054,
      "step": 57
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 1.457709550857544,
      "learning_rate": 2.9e-06,
      "loss": 0.1163,
      "step": 58
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.1929093599319458,
      "learning_rate": 2.95e-06,
      "loss": 0.1049,
      "step": 59
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.6893891096115112,
      "learning_rate": 3e-06,
      "loss": 0.1023,
      "step": 60
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.7837490439414978,
      "learning_rate": 3.05e-06,
      "loss": 0.1014,
      "step": 61
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7837490439414978,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.1324,
      "step": 62
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 2.488649845123291,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.1017,
      "step": 63
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 1.104415774345398,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.1019,
      "step": 64
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.9327191710472107,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0996,
      "step": 65
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 1.17020583152771,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0979,
      "step": 66
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.6745622754096985,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0924,
      "step": 67
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.8487798571586609,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0993,
      "step": 68
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 1.7320159673690796,
      "learning_rate": 3.45e-06,
      "loss": 0.0929,
      "step": 69
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 1.8361762762069702,
      "learning_rate": 3.5e-06,
      "loss": 0.0931,
      "step": 70
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.8804886341094971,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0905,
      "step": 71
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 1.29473876953125,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0959,
      "step": 72
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 1.2560906410217285,
      "learning_rate": 3.65e-06,
      "loss": 0.0954,
      "step": 73
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 1.2681041955947876,
      "learning_rate": 3.7e-06,
      "loss": 0.0935,
      "step": 74
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.6790293455123901,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0958,
      "step": 75
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.250998854637146,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0916,
      "step": 76
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 1.1952019929885864,
      "learning_rate": 3.85e-06,
      "loss": 0.094,
      "step": 77
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 1.381598711013794,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0892,
      "step": 78
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.9761469960212708,
      "learning_rate": 3.95e-06,
      "loss": 0.091,
      "step": 79
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 1.5026003122329712,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0917,
      "step": 80
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 3.112177848815918,
      "learning_rate": 4.05e-06,
      "loss": 0.0891,
      "step": 81
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 1.4188305139541626,
      "learning_rate": 4.1e-06,
      "loss": 0.0856,
      "step": 82
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.1930654048919678,
      "learning_rate": 4.15e-06,
      "loss": 0.0796,
      "step": 83
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 1.2071819305419922,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0849,
      "step": 84
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 1.8237779140472412,
      "learning_rate": 4.25e-06,
      "loss": 0.0809,
      "step": 85
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 1.8066545724868774,
      "learning_rate": 4.3e-06,
      "loss": 0.0822,
      "step": 86
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 1.541412591934204,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0737,
      "step": 87
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.6204791069030762,
      "learning_rate": 4.4e-06,
      "loss": 0.0701,
      "step": 88
    },
    {
      "epoch": 2.89010989010989,
      "grad_norm": 1.6418696641921997,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0693,
      "step": 89
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.4522324800491333,
      "learning_rate": 4.5e-06,
      "loss": 0.0701,
      "step": 90
    }
  ],
  "logging_steps": 1,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.231332415471616e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}