{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 537,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0186219739292365,
      "grad_norm": 1.3874553442001343,
      "learning_rate": 9.98134328358209e-05,
      "loss": 1.8326,
      "step": 10
    },
    {
      "epoch": 0.037243947858473,
      "grad_norm": 0.7816306352615356,
      "learning_rate": 9.94402985074627e-05,
      "loss": 1.314,
      "step": 20
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 0.748516857624054,
      "learning_rate": 9.906716417910448e-05,
      "loss": 1.2913,
      "step": 30
    },
    {
      "epoch": 0.074487895716946,
      "grad_norm": 0.7102469205856323,
      "learning_rate": 9.869402985074628e-05,
      "loss": 1.2041,
      "step": 40
    },
    {
      "epoch": 0.0931098696461825,
      "grad_norm": 0.7098786234855652,
      "learning_rate": 9.832089552238806e-05,
      "loss": 1.1642,
      "step": 50
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.6812120676040649,
      "learning_rate": 9.794776119402985e-05,
      "loss": 1.1717,
      "step": 60
    },
    {
      "epoch": 0.1303538175046555,
      "grad_norm": 0.6887907981872559,
      "learning_rate": 9.757462686567165e-05,
      "loss": 1.169,
      "step": 70
    },
    {
      "epoch": 0.148975791433892,
      "grad_norm": 0.685250461101532,
      "learning_rate": 9.720149253731343e-05,
      "loss": 1.0856,
      "step": 80
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 0.7008183002471924,
      "learning_rate": 9.682835820895523e-05,
      "loss": 1.0955,
      "step": 90
    },
    {
      "epoch": 0.186219739292365,
      "grad_norm": 0.6370360255241394,
      "learning_rate": 9.645522388059703e-05,
      "loss": 1.0581,
      "step": 100
    },
    {
      "epoch": 0.2048417132216015,
      "grad_norm": 0.7338399887084961,
      "learning_rate": 9.608208955223881e-05,
      "loss": 1.0287,
      "step": 110
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.6552614569664001,
      "learning_rate": 9.57089552238806e-05,
      "loss": 1.0256,
      "step": 120
    },
    {
      "epoch": 0.24208566108007448,
      "grad_norm": 0.6847032308578491,
      "learning_rate": 9.533582089552238e-05,
      "loss": 0.9911,
      "step": 130
    },
    {
      "epoch": 0.260707635009311,
      "grad_norm": 0.7163254618644714,
      "learning_rate": 9.496268656716418e-05,
      "loss": 1.0316,
      "step": 140
    },
    {
      "epoch": 0.27932960893854747,
      "grad_norm": 0.6374409794807434,
      "learning_rate": 9.458955223880598e-05,
      "loss": 1.0137,
      "step": 150
    },
    {
      "epoch": 0.297951582867784,
      "grad_norm": 1.027390718460083,
      "learning_rate": 9.421641791044776e-05,
      "loss": 0.9583,
      "step": 160
    },
    {
      "epoch": 0.3165735567970205,
      "grad_norm": 0.6466365456581116,
      "learning_rate": 9.384328358208956e-05,
      "loss": 0.9578,
      "step": 170
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 0.6674121022224426,
      "learning_rate": 9.347014925373135e-05,
      "loss": 0.9662,
      "step": 180
    },
    {
      "epoch": 0.3538175046554935,
      "grad_norm": 0.6532049179077148,
      "learning_rate": 9.309701492537313e-05,
      "loss": 0.9258,
      "step": 190
    },
    {
      "epoch": 0.37243947858473,
      "grad_norm": 0.6357593536376953,
      "learning_rate": 9.272388059701493e-05,
      "loss": 0.8891,
      "step": 200
    },
    {
      "epoch": 0.39106145251396646,
      "grad_norm": 0.6210165619850159,
      "learning_rate": 9.235074626865672e-05,
      "loss": 0.8979,
      "step": 210
    },
    {
      "epoch": 0.409683426443203,
      "grad_norm": 0.6325780749320984,
      "learning_rate": 9.197761194029851e-05,
      "loss": 0.9028,
      "step": 220
    },
    {
      "epoch": 0.42830540037243947,
      "grad_norm": 0.6363133788108826,
      "learning_rate": 9.16044776119403e-05,
      "loss": 0.9283,
      "step": 230
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 0.5902472138404846,
      "learning_rate": 9.12313432835821e-05,
      "loss": 0.8592,
      "step": 240
    },
    {
      "epoch": 0.4655493482309125,
      "grad_norm": 0.6462955474853516,
      "learning_rate": 9.08582089552239e-05,
      "loss": 0.8595,
      "step": 250
    },
    {
      "epoch": 0.48417132216014896,
      "grad_norm": 0.6341489553451538,
      "learning_rate": 9.048507462686568e-05,
      "loss": 0.8372,
      "step": 260
    },
    {
      "epoch": 0.5027932960893855,
      "grad_norm": 0.6504695415496826,
      "learning_rate": 9.011194029850746e-05,
      "loss": 0.8458,
      "step": 270
    },
    {
      "epoch": 0.521415270018622,
      "grad_norm": 0.6562509536743164,
      "learning_rate": 8.973880597014925e-05,
      "loss": 0.8211,
      "step": 280
    },
    {
      "epoch": 0.5400372439478585,
      "grad_norm": 0.622184693813324,
      "learning_rate": 8.936567164179105e-05,
      "loss": 0.8278,
      "step": 290
    },
    {
      "epoch": 0.5586592178770949,
      "grad_norm": 0.6273349523544312,
      "learning_rate": 8.899253731343285e-05,
      "loss": 0.8188,
      "step": 300
    },
    {
      "epoch": 0.5772811918063314,
      "grad_norm": 0.6405043601989746,
      "learning_rate": 8.861940298507463e-05,
      "loss": 0.8646,
      "step": 310
    },
    {
      "epoch": 0.595903165735568,
      "grad_norm": 0.6616275310516357,
      "learning_rate": 8.824626865671643e-05,
      "loss": 0.8606,
      "step": 320
    },
    {
      "epoch": 0.6145251396648045,
      "grad_norm": 0.6546701192855835,
      "learning_rate": 8.787313432835821e-05,
      "loss": 0.8271,
      "step": 330
    },
    {
      "epoch": 0.633147113594041,
      "grad_norm": 0.6446258425712585,
      "learning_rate": 8.75e-05,
      "loss": 0.805,
      "step": 340
    },
    {
      "epoch": 0.6517690875232774,
      "grad_norm": 0.6694822311401367,
      "learning_rate": 8.71268656716418e-05,
      "loss": 0.8237,
      "step": 350
    },
    {
      "epoch": 0.6703910614525139,
      "grad_norm": 0.5971983075141907,
      "learning_rate": 8.675373134328358e-05,
      "loss": 0.7784,
      "step": 360
    },
    {
      "epoch": 0.6890130353817505,
      "grad_norm": 0.5651050209999084,
      "learning_rate": 8.638059701492538e-05,
      "loss": 0.7345,
      "step": 370
    },
    {
      "epoch": 0.707635009310987,
      "grad_norm": 0.6789554357528687,
      "learning_rate": 8.600746268656717e-05,
      "loss": 0.8024,
      "step": 380
    },
    {
      "epoch": 0.7262569832402235,
      "grad_norm": 0.6168780326843262,
      "learning_rate": 8.563432835820896e-05,
      "loss": 0.7387,
      "step": 390
    },
    {
      "epoch": 0.74487895716946,
      "grad_norm": 0.6000941395759583,
      "learning_rate": 8.526119402985075e-05,
      "loss": 0.7403,
      "step": 400
    },
    {
      "epoch": 0.7635009310986964,
      "grad_norm": 0.6785574555397034,
      "learning_rate": 8.488805970149253e-05,
      "loss": 0.7653,
      "step": 410
    },
    {
      "epoch": 0.7821229050279329,
      "grad_norm": 0.6262904405593872,
      "learning_rate": 8.451492537313433e-05,
      "loss": 0.7421,
      "step": 420
    },
    {
      "epoch": 0.8007448789571695,
      "grad_norm": 0.6499343514442444,
      "learning_rate": 8.414179104477612e-05,
      "loss": 0.6831,
      "step": 430
    },
    {
      "epoch": 0.819366852886406,
      "grad_norm": 0.5795383453369141,
      "learning_rate": 8.376865671641791e-05,
      "loss": 0.7189,
      "step": 440
    },
    {
      "epoch": 0.8379888268156425,
      "grad_norm": 0.6257463097572327,
      "learning_rate": 8.339552238805971e-05,
      "loss": 0.7052,
      "step": 450
    },
    {
      "epoch": 0.8566108007448789,
      "grad_norm": 0.6415144801139832,
      "learning_rate": 8.30223880597015e-05,
      "loss": 0.703,
      "step": 460
    },
    {
      "epoch": 0.8752327746741154,
      "grad_norm": 0.6050721406936646,
      "learning_rate": 8.26492537313433e-05,
      "loss": 0.7093,
      "step": 470
    },
    {
      "epoch": 0.8938547486033519,
      "grad_norm": 0.63200443983078,
      "learning_rate": 8.227611940298508e-05,
      "loss": 0.711,
      "step": 480
    },
    {
      "epoch": 0.9124767225325885,
      "grad_norm": 0.7535350918769836,
      "learning_rate": 8.190298507462687e-05,
      "loss": 0.7101,
      "step": 490
    },
    {
      "epoch": 0.931098696461825,
      "grad_norm": 0.5603737831115723,
      "learning_rate": 8.152985074626866e-05,
      "loss": 0.6888,
      "step": 500
    },
    {
      "epoch": 0.9497206703910615,
      "grad_norm": 0.6010568141937256,
      "learning_rate": 8.115671641791045e-05,
      "loss": 0.702,
      "step": 510
    },
    {
      "epoch": 0.9683426443202979,
      "grad_norm": 0.6261228322982788,
      "learning_rate": 8.078358208955225e-05,
      "loss": 0.6634,
      "step": 520
    },
    {
      "epoch": 0.9869646182495344,
      "grad_norm": 0.5894924998283386,
      "learning_rate": 8.041044776119403e-05,
      "loss": 0.6782,
      "step": 530
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8664104342460632,
      "eval_runtime": 40.1805,
      "eval_samples_per_second": 10.005,
      "eval_steps_per_second": 1.269,
      "step": 537
    }
  ],
  "logging_steps": 10,
  "max_steps": 2685,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 8.800341942707159e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}