{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0931098696461825,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00186219739292365,
      "grad_norm": 1.2520835399627686,
      "learning_rate": 1e-05,
      "loss": 2.8913,
      "step": 1
    },
    {
      "epoch": 0.00186219739292365,
      "eval_loss": 3.0129952430725098,
      "eval_runtime": 49.6998,
      "eval_samples_per_second": 9.115,
      "eval_steps_per_second": 1.147,
      "step": 1
    },
    {
      "epoch": 0.0037243947858473,
      "grad_norm": 1.2519779205322266,
      "learning_rate": 2e-05,
      "loss": 2.998,
      "step": 2
    },
    {
      "epoch": 0.00558659217877095,
      "grad_norm": 1.3494188785552979,
      "learning_rate": 3e-05,
      "loss": 2.8813,
      "step": 3
    },
    {
      "epoch": 0.0074487895716946,
      "grad_norm": 1.2448559999465942,
      "learning_rate": 4e-05,
      "loss": 2.7729,
      "step": 4
    },
    {
      "epoch": 0.00931098696461825,
      "grad_norm": 1.2326918840408325,
      "learning_rate": 5e-05,
      "loss": 2.6081,
      "step": 5
    },
    {
      "epoch": 0.00931098696461825,
      "eval_loss": 2.978092670440674,
      "eval_runtime": 49.246,
      "eval_samples_per_second": 9.199,
      "eval_steps_per_second": 1.157,
      "step": 5
    },
    {
      "epoch": 0.0111731843575419,
      "grad_norm": 1.4368785619735718,
      "learning_rate": 6e-05,
      "loss": 3.0386,
      "step": 6
    },
    {
      "epoch": 0.01303538175046555,
      "grad_norm": 1.380092978477478,
      "learning_rate": 7e-05,
      "loss": 2.6338,
      "step": 7
    },
    {
      "epoch": 0.0148975791433892,
      "grad_norm": 1.4608924388885498,
      "learning_rate": 8e-05,
      "loss": 2.6547,
      "step": 8
    },
    {
      "epoch": 0.01675977653631285,
      "grad_norm": 1.2979212999343872,
      "learning_rate": 9e-05,
      "loss": 2.829,
      "step": 9
    },
    {
      "epoch": 0.0186219739292365,
      "grad_norm": 1.2908484935760498,
      "learning_rate": 0.0001,
      "loss": 2.7966,
      "step": 10
    },
    {
      "epoch": 0.0186219739292365,
      "eval_loss": 2.7287378311157227,
      "eval_runtime": 49.2643,
      "eval_samples_per_second": 9.195,
      "eval_steps_per_second": 1.157,
      "step": 10
    },
    {
      "epoch": 0.020484171322160148,
      "grad_norm": 1.6551676988601685,
      "learning_rate": 9.98458666866564e-05,
      "loss": 2.842,
      "step": 11
    },
    {
      "epoch": 0.0223463687150838,
      "grad_norm": 1.767666220664978,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.6801,
      "step": 12
    },
    {
      "epoch": 0.024208566108007448,
      "grad_norm": 1.4233036041259766,
      "learning_rate": 9.861849601988383e-05,
      "loss": 2.454,
      "step": 13
    },
    {
      "epoch": 0.0260707635009311,
      "grad_norm": 4.678153991699219,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5042,
      "step": 14
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 1.258413314819336,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2727,
      "step": 15
    },
    {
      "epoch": 0.027932960893854747,
      "eval_loss": 2.4857091903686523,
      "eval_runtime": 49.2763,
      "eval_samples_per_second": 9.193,
      "eval_steps_per_second": 1.157,
      "step": 15
    },
    {
      "epoch": 0.0297951582867784,
      "grad_norm": 1.3240501880645752,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.3633,
      "step": 16
    },
    {
      "epoch": 0.03165735567970205,
      "grad_norm": 1.5432164669036865,
      "learning_rate": 9.263200821770461e-05,
      "loss": 2.5207,
      "step": 17
    },
    {
      "epoch": 0.0335195530726257,
      "grad_norm": 1.4234057664871216,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6374,
      "step": 18
    },
    {
      "epoch": 0.035381750465549346,
      "grad_norm": 1.2782092094421387,
      "learning_rate": 8.802029828000156e-05,
      "loss": 2.2372,
      "step": 19
    },
    {
      "epoch": 0.037243947858473,
      "grad_norm": 1.1257778406143188,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.173,
      "step": 20
    },
    {
      "epoch": 0.037243947858473,
      "eval_loss": 2.3156802654266357,
      "eval_runtime": 49.2765,
      "eval_samples_per_second": 9.193,
      "eval_steps_per_second": 1.157,
      "step": 20
    },
    {
      "epoch": 0.03910614525139665,
      "grad_norm": 1.1322994232177734,
      "learning_rate": 8.247240241650918e-05,
      "loss": 2.2937,
      "step": 21
    },
    {
      "epoch": 0.040968342644320296,
      "grad_norm": 1.0842132568359375,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1673,
      "step": 22
    },
    {
      "epoch": 0.04283054003724395,
      "grad_norm": 1.0566719770431519,
      "learning_rate": 7.612492823579745e-05,
      "loss": 1.9895,
      "step": 23
    },
    {
      "epoch": 0.0446927374301676,
      "grad_norm": 1.3491997718811035,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.116,
      "step": 24
    },
    {
      "epoch": 0.04655493482309125,
      "grad_norm": 1.1620092391967773,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1376,
      "step": 25
    },
    {
      "epoch": 0.04655493482309125,
      "eval_loss": 2.1697986125946045,
      "eval_runtime": 49.2966,
      "eval_samples_per_second": 9.189,
      "eval_steps_per_second": 1.156,
      "step": 25
    },
    {
      "epoch": 0.048417132216014895,
      "grad_norm": 1.0937061309814453,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1448,
      "step": 26
    },
    {
      "epoch": 0.05027932960893855,
      "grad_norm": 1.082903265953064,
      "learning_rate": 6.167226819279528e-05,
      "loss": 2.0361,
      "step": 27
    },
    {
      "epoch": 0.0521415270018622,
      "grad_norm": 1.4357037544250488,
      "learning_rate": 5.782172325201155e-05,
      "loss": 2.2307,
      "step": 28
    },
    {
      "epoch": 0.054003724394785846,
      "grad_norm": 1.0995923280715942,
      "learning_rate": 5.392295478639225e-05,
      "loss": 2.0975,
      "step": 29
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 1.0289602279663086,
      "learning_rate": 5e-05,
      "loss": 1.8657,
      "step": 30
    },
    {
      "epoch": 0.055865921787709494,
      "eval_loss": 2.066453695297241,
      "eval_runtime": 49.2696,
      "eval_samples_per_second": 9.194,
      "eval_steps_per_second": 1.157,
      "step": 30
    },
    {
      "epoch": 0.05772811918063315,
      "grad_norm": 1.096411943435669,
      "learning_rate": 4.607704521360776e-05,
      "loss": 2.0965,
      "step": 31
    },
    {
      "epoch": 0.0595903165735568,
      "grad_norm": 1.0694092512130737,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.0698,
      "step": 32
    },
    {
      "epoch": 0.061452513966480445,
      "grad_norm": 1.118601679801941,
      "learning_rate": 3.832773180720475e-05,
      "loss": 2.1493,
      "step": 33
    },
    {
      "epoch": 0.0633147113594041,
      "grad_norm": 1.0171372890472412,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0332,
      "step": 34
    },
    {
      "epoch": 0.06517690875232775,
      "grad_norm": 1.0827255249023438,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.993,
      "step": 35
    },
    {
      "epoch": 0.06517690875232775,
      "eval_loss": 2.005394697189331,
      "eval_runtime": 49.3447,
      "eval_samples_per_second": 9.18,
      "eval_steps_per_second": 1.155,
      "step": 35
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": 1.0604010820388794,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.8807,
      "step": 36
    },
    {
      "epoch": 0.06890130353817504,
      "grad_norm": 1.0425511598587036,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 1.9859,
      "step": 37
    },
    {
      "epoch": 0.07076350093109869,
      "grad_norm": 1.0914885997772217,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.9077,
      "step": 38
    },
    {
      "epoch": 0.07262569832402235,
      "grad_norm": 1.1516059637069702,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 2.2016,
      "step": 39
    },
    {
      "epoch": 0.074487895716946,
      "grad_norm": 1.0635038614273071,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0021,
      "step": 40
    },
    {
      "epoch": 0.074487895716946,
      "eval_loss": 1.9731868505477905,
      "eval_runtime": 49.321,
      "eval_samples_per_second": 9.185,
      "eval_steps_per_second": 1.156,
      "step": 40
    },
    {
      "epoch": 0.07635009310986965,
      "grad_norm": 1.2229695320129395,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 2.0167,
      "step": 41
    },
    {
      "epoch": 0.0782122905027933,
      "grad_norm": 1.044442057609558,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8081,
      "step": 42
    },
    {
      "epoch": 0.08007448789571694,
      "grad_norm": 1.0942388772964478,
      "learning_rate": 7.367991782295391e-06,
      "loss": 2.2174,
      "step": 43
    },
    {
      "epoch": 0.08193668528864059,
      "grad_norm": 1.0910190343856812,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.1796,
      "step": 44
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 1.2429304122924805,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7848,
      "step": 45
    },
    {
      "epoch": 0.08379888268156424,
      "eval_loss": 1.9582425355911255,
      "eval_runtime": 49.2697,
      "eval_samples_per_second": 9.194,
      "eval_steps_per_second": 1.157,
      "step": 45
    },
    {
      "epoch": 0.0856610800744879,
      "grad_norm": 0.9983396530151367,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.8316,
      "step": 46
    },
    {
      "epoch": 0.08752327746741155,
      "grad_norm": 1.012921690940857,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 1.8607,
      "step": 47
    },
    {
      "epoch": 0.0893854748603352,
      "grad_norm": 0.9606110453605652,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.886,
      "step": 48
    },
    {
      "epoch": 0.09124767225325885,
      "grad_norm": 1.0702084302902222,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 2.1066,
      "step": 49
    },
    {
      "epoch": 0.0931098696461825,
      "grad_norm": 1.0214251279830933,
      "learning_rate": 0.0,
      "loss": 2.0748,
      "step": 50
    },
    {
      "epoch": 0.0931098696461825,
      "eval_loss": 1.9558095932006836,
      "eval_runtime": 49.3038,
      "eval_samples_per_second": 9.188,
      "eval_steps_per_second": 1.156,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.70943641780224e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}