{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.962025316455696,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0379746835443038,
      "grad_norm": 7.233742025484269,
      "learning_rate": 1.25e-06,
      "loss": 1.1454,
      "step": 1
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 6.785754420499863,
      "learning_rate": 2.5e-06,
      "loss": 1.0457,
      "step": 2
    },
    {
      "epoch": 0.11392405063291139,
      "grad_norm": 6.873560922195714,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.1087,
      "step": 3
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 6.070068194853726,
      "learning_rate": 5e-06,
      "loss": 1.0456,
      "step": 4
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 4.899244783161146,
      "learning_rate": 6.25e-06,
      "loss": 1.057,
      "step": 5
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 2.734094670545256,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.9376,
      "step": 6
    },
    {
      "epoch": 0.26582278481012656,
      "grad_norm": 5.184706319498115,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.005,
      "step": 7
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 5.1930383025881985,
      "learning_rate": 1e-05,
      "loss": 1.0426,
      "step": 8
    },
    {
      "epoch": 0.34177215189873417,
      "grad_norm": 5.102463875196109,
      "learning_rate": 9.994965332706574e-06,
      "loss": 0.9493,
      "step": 9
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 5.025744107415969,
      "learning_rate": 9.979871469976197e-06,
      "loss": 1.0027,
      "step": 10
    },
    {
      "epoch": 0.4177215189873418,
      "grad_norm": 3.296364051224896,
      "learning_rate": 9.954748808839675e-06,
      "loss": 0.964,
      "step": 11
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 2.1787192069360835,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.8481,
      "step": 12
    },
    {
      "epoch": 0.4936708860759494,
      "grad_norm": 2.465515260993728,
      "learning_rate": 9.874639560909118e-06,
      "loss": 0.8781,
      "step": 13
    },
    {
      "epoch": 0.5316455696202531,
      "grad_norm": 2.26642714838209,
      "learning_rate": 9.819814303479268e-06,
      "loss": 0.8506,
      "step": 14
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 1.685223036374424,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8877,
      "step": 15
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.8107951485066331,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.8791,
      "step": 16
    },
    {
      "epoch": 0.6455696202531646,
      "grad_norm": 1.9474784785519363,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.868,
      "step": 17
    },
    {
      "epoch": 0.6835443037974683,
      "grad_norm": 1.3097181398173738,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.8441,
      "step": 18
    },
    {
      "epoch": 0.7215189873417721,
      "grad_norm": 1.1972264295529598,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.835,
      "step": 19
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 1.2739805854924195,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.8192,
      "step": 20
    },
    {
      "epoch": 0.7974683544303798,
      "grad_norm": 0.943212312683219,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.8329,
      "step": 21
    },
    {
      "epoch": 0.8354430379746836,
      "grad_norm": 0.848387324073507,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.851,
      "step": 22
    },
    {
      "epoch": 0.8734177215189873,
      "grad_norm": 0.8721315678974946,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.7609,
      "step": 23
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 0.8412362369012817,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.7978,
      "step": 24
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 0.7847676879285055,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.778,
      "step": 25
    },
    {
      "epoch": 0.9873417721518988,
      "grad_norm": 0.8562323541981702,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.7742,
      "step": 26
    },
    {
      "epoch": 1.0253164556962024,
      "grad_norm": 1.2393087482576586,
      "learning_rate": 8.289693629698564e-06,
      "loss": 1.2449,
      "step": 27
    },
    {
      "epoch": 1.0632911392405062,
      "grad_norm": 0.7079703595122016,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.7647,
      "step": 28
    },
    {
      "epoch": 1.1012658227848102,
      "grad_norm": 0.6381254299067906,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.7681,
      "step": 29
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 0.5592906812359777,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.7634,
      "step": 30
    },
    {
      "epoch": 1.1772151898734178,
      "grad_norm": 0.6690288012490828,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.7772,
      "step": 31
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 0.5551831494766208,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.7518,
      "step": 32
    },
    {
      "epoch": 1.2531645569620253,
      "grad_norm": 0.682247888876666,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.8852,
      "step": 33
    },
    {
      "epoch": 1.2911392405063291,
      "grad_norm": 0.49353460164668184,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.6812,
      "step": 34
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 0.4852974078578067,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.7192,
      "step": 35
    },
    {
      "epoch": 1.3670886075949367,
      "grad_norm": 0.6729026623142048,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.823,
      "step": 36
    },
    {
      "epoch": 1.4050632911392404,
      "grad_norm": 0.5868998382593021,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.6688,
      "step": 37
    },
    {
      "epoch": 1.4430379746835442,
      "grad_norm": 0.5900143860620642,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.7767,
      "step": 38
    },
    {
      "epoch": 1.481012658227848,
      "grad_norm": 0.520696165551,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.8102,
      "step": 39
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 0.5849614948848969,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.7481,
      "step": 40
    },
    {
      "epoch": 1.5569620253164556,
      "grad_norm": 0.4842009922615296,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.7064,
      "step": 41
    },
    {
      "epoch": 1.5949367088607596,
      "grad_norm": 0.6090712826518998,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.7456,
      "step": 42
    },
    {
      "epoch": 1.6329113924050633,
      "grad_norm": 0.49266162920233386,
      "learning_rate": 5e-06,
      "loss": 0.6681,
      "step": 43
    },
    {
      "epoch": 1.6708860759493671,
      "grad_norm": 0.5613984339121264,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.7413,
      "step": 44
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 0.5648308497308961,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.8398,
      "step": 45
    },
    {
      "epoch": 1.7468354430379747,
      "grad_norm": 0.5334838340280534,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.759,
      "step": 46
    },
    {
      "epoch": 1.7848101265822784,
      "grad_norm": 0.5447346237199453,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.718,
      "step": 47
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 0.4865524447115485,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.7301,
      "step": 48
    },
    {
      "epoch": 1.8607594936708862,
      "grad_norm": 0.47825378497206067,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.7541,
      "step": 49
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.5921763533888591,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.7953,
      "step": 50
    },
    {
      "epoch": 1.9367088607594938,
      "grad_norm": 0.4829282828230368,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.6552,
      "step": 51
    },
    {
      "epoch": 1.9746835443037973,
      "grad_norm": 0.5114037014726881,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.8745,
      "step": 52
    },
    {
      "epoch": 2.0126582278481013,
      "grad_norm": 0.7859262170640012,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.0096,
      "step": 53
    },
    {
      "epoch": 2.050632911392405,
      "grad_norm": 0.46684696405174964,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.7132,
      "step": 54
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 0.517786067233843,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.854,
      "step": 55
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 0.455128154085124,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.6703,
      "step": 56
    },
    {
      "epoch": 2.1645569620253164,
      "grad_norm": 0.4407016628670742,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.7363,
      "step": 57
    },
    {
      "epoch": 2.2025316455696204,
      "grad_norm": 0.4403792631608705,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.7298,
      "step": 58
    },
    {
      "epoch": 2.240506329113924,
      "grad_norm": 0.4623680749681796,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.7518,
      "step": 59
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 0.44326842914736825,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.7075,
      "step": 60
    },
    {
      "epoch": 2.3164556962025316,
      "grad_norm": 0.4283289272602202,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.7032,
      "step": 61
    },
    {
      "epoch": 2.3544303797468356,
      "grad_norm": 0.5041856093680451,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.7191,
      "step": 62
    },
    {
      "epoch": 2.392405063291139,
      "grad_norm": 0.4741511129487454,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.7263,
      "step": 63
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 0.4363770783544496,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.7362,
      "step": 64
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 0.43255109702632855,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.681,
      "step": 65
    },
    {
      "epoch": 2.5063291139240507,
      "grad_norm": 0.4066191475356962,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.7316,
      "step": 66
    },
    {
      "epoch": 2.5443037974683547,
      "grad_norm": 0.40393602082830354,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.6585,
      "step": 67
    },
    {
      "epoch": 2.5822784810126582,
      "grad_norm": 0.4378157851570328,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.7468,
      "step": 68
    },
    {
      "epoch": 2.620253164556962,
      "grad_norm": 0.39439431826838517,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.6613,
      "step": 69
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 0.43181499146604313,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.7306,
      "step": 70
    },
    {
      "epoch": 2.6962025316455698,
      "grad_norm": 0.42106461119949756,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.7387,
      "step": 71
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 0.4140210199949433,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.7686,
      "step": 72
    },
    {
      "epoch": 2.7721518987341773,
      "grad_norm": 0.43164253148923615,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.7474,
      "step": 73
    },
    {
      "epoch": 2.810126582278481,
      "grad_norm": 0.366892032697455,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.6236,
      "step": 74
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 0.3812258333922781,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.7079,
      "step": 75
    },
    {
      "epoch": 2.8860759493670884,
      "grad_norm": 0.40957061725247956,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.7319,
      "step": 76
    },
    {
      "epoch": 2.9240506329113924,
      "grad_norm": 0.3707924195450794,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.7077,
      "step": 77
    },
    {
      "epoch": 2.962025316455696,
      "grad_norm": 0.4328169844138338,
      "learning_rate": 0.0,
      "loss": 0.7367,
      "step": 78
    },
    {
      "epoch": 2.962025316455696,
      "step": 78,
      "total_flos": 75607304601600.0,
      "train_loss": 0.8077984360548166,
      "train_runtime": 1430.59,
      "train_samples_per_second": 5.243,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 1,
  "max_steps": 78,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 75607304601600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}