{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 7.0608601570129395,
      "learning_rate": 1.25e-06,
      "loss": 1.2679,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 7.067531585693359,
      "learning_rate": 2.5e-06,
      "loss": 1.2707,
      "step": 2
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 6.489712715148926,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.2554,
      "step": 3
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 6.55590295791626,
      "learning_rate": 5e-06,
      "loss": 1.2633,
      "step": 4
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 4.567355632781982,
      "learning_rate": 6.25e-06,
      "loss": 1.2071,
      "step": 5
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.7389402389526367,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1099,
      "step": 6
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 5.802897930145264,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.1594,
      "step": 7
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 6.028085231781006,
      "learning_rate": 1e-05,
      "loss": 1.1568,
      "step": 8
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 5.590550899505615,
      "learning_rate": 9.994965332706574e-06,
      "loss": 1.1096,
      "step": 9
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 5.91151237487793,
      "learning_rate": 9.979871469976197e-06,
      "loss": 1.1533,
      "step": 10
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 4.0487565994262695,
      "learning_rate": 9.954748808839675e-06,
      "loss": 1.1268,
      "step": 11
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.325029134750366,
      "learning_rate": 9.91964794299315e-06,
      "loss": 1.0529,
      "step": 12
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.120403528213501,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.053,
      "step": 13
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 2.1111786365509033,
      "learning_rate": 9.819814303479268e-06,
      "loss": 1.0544,
      "step": 14
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 1.6523377895355225,
      "learning_rate": 9.755282581475769e-06,
      "loss": 1.025,
      "step": 15
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2090944051742554,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.989,
      "step": 16
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 1.2429088354110718,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.984,
      "step": 17
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 1.128936529159546,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.951,
      "step": 18
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 0.9137685298919678,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.9472,
      "step": 19
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.9019792675971985,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.9495,
      "step": 20
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 1.2162680625915527,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.9878,
      "step": 21
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.1780152320861816,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.9995,
      "step": 22
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 0.8031172752380371,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.9525,
      "step": 23
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.8815509676933289,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.9715,
      "step": 24
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.7577799558639526,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.95,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8586682677268982,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.9302,
      "step": 26
    },
    {
      "epoch": 1.0384615384615385,
      "grad_norm": 0.7273011207580566,
      "learning_rate": 8.289693629698564e-06,
      "loss": 0.9184,
      "step": 27
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.7588111162185669,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.9135,
      "step": 28
    },
    {
      "epoch": 1.1153846153846154,
      "grad_norm": 0.7609086036682129,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.8805,
      "step": 29
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.6686831116676331,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.8966,
      "step": 30
    },
    {
      "epoch": 1.1923076923076923,
      "grad_norm": 0.7945602536201477,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.8821,
      "step": 31
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.8206145763397217,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.8761,
      "step": 32
    },
    {
      "epoch": 1.2692307692307692,
      "grad_norm": 0.7487725019454956,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.8529,
      "step": 33
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.8359059691429138,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.9053,
      "step": 34
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.7550702691078186,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.9207,
      "step": 35
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.7487111687660217,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.8847,
      "step": 36
    },
    {
      "epoch": 1.4230769230769231,
      "grad_norm": 0.6988634467124939,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.8799,
      "step": 37
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.6492851376533508,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.8546,
      "step": 38
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.6649678349494934,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.8679,
      "step": 39
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.6739174723625183,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.919,
      "step": 40
    },
    {
      "epoch": 1.5769230769230769,
      "grad_norm": 0.7400906682014465,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.8837,
      "step": 41
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.6494066119194031,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.9065,
      "step": 42
    },
    {
      "epoch": 1.6538461538461537,
      "grad_norm": 0.5957571864128113,
      "learning_rate": 5e-06,
      "loss": 0.9107,
      "step": 43
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.6231606006622314,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.891,
      "step": 44
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 0.6922110319137573,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.8803,
      "step": 45
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.5624760389328003,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.8856,
      "step": 46
    },
    {
      "epoch": 1.8076923076923077,
      "grad_norm": 0.5690933465957642,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.8768,
      "step": 47
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.6082056760787964,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.8983,
      "step": 48
    },
    {
      "epoch": 1.8846153846153846,
      "grad_norm": 0.5788046717643738,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.9199,
      "step": 49
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.6090818643569946,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.8637,
      "step": 50
    },
    {
      "epoch": 1.9615384615384617,
      "grad_norm": 0.5499722957611084,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.8961,
      "step": 51
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5419381856918335,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.8782,
      "step": 52
    },
    {
      "epoch": 2.0384615384615383,
      "grad_norm": 0.552922785282135,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.8562,
      "step": 53
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.5646542310714722,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.8634,
      "step": 54
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 0.567699134349823,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.8545,
      "step": 55
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.5519792437553406,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.8404,
      "step": 56
    },
    {
      "epoch": 2.1923076923076925,
      "grad_norm": 0.4923272132873535,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.8464,
      "step": 57
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.4754745662212372,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.8177,
      "step": 58
    },
    {
      "epoch": 2.269230769230769,
      "grad_norm": 0.4785245954990387,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.818,
      "step": 59
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.4648175835609436,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.8892,
      "step": 60
    },
    {
      "epoch": 2.3461538461538463,
      "grad_norm": 0.5224047303199768,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.8568,
      "step": 61
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.46491125226020813,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.8508,
      "step": 62
    },
    {
      "epoch": 2.423076923076923,
      "grad_norm": 0.5960954427719116,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.8127,
      "step": 63
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.47732099890708923,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.8405,
      "step": 64
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.4291718900203705,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.8333,
      "step": 65
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.4680764973163605,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.8573,
      "step": 66
    },
    {
      "epoch": 2.5769230769230766,
      "grad_norm": 0.479629248380661,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.8332,
      "step": 67
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.3852009177207947,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.8557,
      "step": 68
    },
    {
      "epoch": 2.6538461538461537,
      "grad_norm": 0.46463048458099365,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.8394,
      "step": 69
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.4415458142757416,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.8217,
      "step": 70
    },
    {
      "epoch": 2.730769230769231,
      "grad_norm": 0.4421484172344208,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.8341,
      "step": 71
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.407691091299057,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.8427,
      "step": 72
    },
    {
      "epoch": 2.8076923076923075,
      "grad_norm": 0.48776358366012573,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.8559,
      "step": 73
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.41832244396209717,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.8236,
      "step": 74
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 0.45950958132743835,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.8805,
      "step": 75
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.4031815826892853,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.8551,
      "step": 76
    },
    {
      "epoch": 2.9615384615384617,
      "grad_norm": 0.42409250140190125,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.857,
      "step": 77
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4406355023384094,
      "learning_rate": 0.0,
      "loss": 0.82,
      "step": 78
    },
    {
      "epoch": 3.0,
      "step": 78,
      "total_flos": 79584345915392.0,
      "train_loss": 0.9356000538055713,
      "train_runtime": 7473.6925,
      "train_samples_per_second": 1.002,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 1.0,
  "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": 79584345915392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}