{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10149253731343283,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029850746268656717,
      "grad_norm": 8.253287036233855,
      "learning_rate": 9.090909090909091e-07,
      "loss": 2.2247,
      "step": 1
    },
    {
      "epoch": 0.005970149253731343,
      "grad_norm": 7.395570676912434,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 2.1255,
      "step": 2
    },
    {
      "epoch": 0.008955223880597015,
      "grad_norm": 8.228093047465732,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 2.1028,
      "step": 3
    },
    {
      "epoch": 0.011940298507462687,
      "grad_norm": 7.134217440402169,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 2.0029,
      "step": 4
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 5.937798020763942,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.907,
      "step": 5
    },
    {
      "epoch": 0.01791044776119403,
      "grad_norm": 5.559897081671283,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.859,
      "step": 6
    },
    {
      "epoch": 0.020895522388059702,
      "grad_norm": 5.0306441137723485,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.8198,
      "step": 7
    },
    {
      "epoch": 0.023880597014925373,
      "grad_norm": 3.514372505025641,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.5112,
      "step": 8
    },
    {
      "epoch": 0.026865671641791045,
      "grad_norm": 3.1293116769998894,
      "learning_rate": 8.181818181818183e-06,
      "loss": 1.4412,
      "step": 9
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 2.7656396768471456,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.4058,
      "step": 10
    },
    {
      "epoch": 0.03283582089552239,
      "grad_norm": 5.352646410247892,
      "learning_rate": 1e-05,
      "loss": 1.4371,
      "step": 11
    },
    {
      "epoch": 0.03582089552238806,
      "grad_norm": 4.381930202952016,
      "learning_rate": 9.99976495753613e-06,
      "loss": 1.4176,
      "step": 12
    },
    {
      "epoch": 0.03880597014925373,
      "grad_norm": 3.1514253661202765,
      "learning_rate": 9.999059852242508e-06,
      "loss": 1.2973,
      "step": 13
    },
    {
      "epoch": 0.041791044776119404,
      "grad_norm": 2.6485142204402696,
      "learning_rate": 9.997884750411004e-06,
      "loss": 1.1784,
      "step": 14
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 2.7946518315041007,
      "learning_rate": 9.996239762521152e-06,
      "loss": 1.3108,
      "step": 15
    },
    {
      "epoch": 0.04776119402985075,
      "grad_norm": 2.6114018043960003,
      "learning_rate": 9.994125043229753e-06,
      "loss": 1.102,
      "step": 16
    },
    {
      "epoch": 0.050746268656716415,
      "grad_norm": 2.3027638181918495,
      "learning_rate": 9.991540791356342e-06,
      "loss": 1.0699,
      "step": 17
    },
    {
      "epoch": 0.05373134328358209,
      "grad_norm": 2.204185879725156,
      "learning_rate": 9.98848724986449e-06,
      "loss": 1.1473,
      "step": 18
    },
    {
      "epoch": 0.056716417910447764,
      "grad_norm": 2.2090761147091817,
      "learning_rate": 9.98496470583896e-06,
      "loss": 1.1816,
      "step": 19
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 2.0223479706782737,
      "learning_rate": 9.980973490458728e-06,
      "loss": 1.1217,
      "step": 20
    },
    {
      "epoch": 0.0626865671641791,
      "grad_norm": 2.080473927553376,
      "learning_rate": 9.976513978965829e-06,
      "loss": 1.0251,
      "step": 21
    },
    {
      "epoch": 0.06567164179104477,
      "grad_norm": 2.3488846800450744,
      "learning_rate": 9.971586590630094e-06,
      "loss": 1.0279,
      "step": 22
    },
    {
      "epoch": 0.06865671641791045,
      "grad_norm": 2.1532960090217212,
      "learning_rate": 9.966191788709716e-06,
      "loss": 1.0126,
      "step": 23
    },
    {
      "epoch": 0.07164179104477612,
      "grad_norm": 2.055129377186085,
      "learning_rate": 9.960330080407712e-06,
      "loss": 1.0072,
      "step": 24
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 2.156877426415811,
      "learning_rate": 9.954002016824226e-06,
      "loss": 1.0349,
      "step": 25
    },
    {
      "epoch": 0.07761194029850746,
      "grad_norm": 1.9914221696004062,
      "learning_rate": 9.947208192904722e-06,
      "loss": 1.0244,
      "step": 26
    },
    {
      "epoch": 0.08059701492537313,
      "grad_norm": 1.9887204088063186,
      "learning_rate": 9.939949247384046e-06,
      "loss": 0.9912,
      "step": 27
    },
    {
      "epoch": 0.08358208955223881,
      "grad_norm": 2.110799590941847,
      "learning_rate": 9.93222586272637e-06,
      "loss": 1.0377,
      "step": 28
    },
    {
      "epoch": 0.08656716417910448,
      "grad_norm": 2.0583073599588473,
      "learning_rate": 9.924038765061042e-06,
      "loss": 1.0139,
      "step": 29
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 2.1723065119138196,
      "learning_rate": 9.915388724114301e-06,
      "loss": 0.9376,
      "step": 30
    },
    {
      "epoch": 0.09253731343283582,
      "grad_norm": 2.064005981064233,
      "learning_rate": 9.906276553136924e-06,
      "loss": 1.0226,
      "step": 31
    },
    {
      "epoch": 0.0955223880597015,
      "grad_norm": 2.122144912833922,
      "learning_rate": 9.896703108827758e-06,
      "loss": 0.9483,
      "step": 32
    },
    {
      "epoch": 0.09850746268656717,
      "grad_norm": 2.1876975651489246,
      "learning_rate": 9.886669291253178e-06,
      "loss": 0.8942,
      "step": 33
    },
    {
      "epoch": 0.10149253731343283,
      "grad_norm": 1.9606368757720636,
      "learning_rate": 9.876176043762467e-06,
      "loss": 0.885,
      "step": 34
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 335,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "total_flos": 2840270012416.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}