{
  "best_global_step": 4000,
  "best_metric": 0.7102092504501343,
  "best_model_checkpoint": "/Data/data_chess/checkpoint-4000",
  "epoch": 0.2694691457828079,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006736728644570197,
      "grad_norm": 0.7572135925292969,
      "learning_rate": 0.0006644295302013424,
      "loss": 2.9711,
      "step": 100
    },
    {
      "epoch": 0.013473457289140393,
      "grad_norm": 0.6671218276023865,
      "learning_rate": 0.0009999714348540981,
      "loss": 1.607,
      "step": 200
    },
    {
      "epoch": 0.02021018593371059,
      "grad_norm": 0.5963013172149658,
      "learning_rate": 0.0009997429332697315,
      "loss": 1.2186,
      "step": 300
    },
    {
      "epoch": 0.026946914578280787,
      "grad_norm": 0.46841374039649963,
      "learning_rate": 0.0009992860345329128,
      "loss": 1.0664,
      "step": 400
    },
    {
      "epoch": 0.03368364322285099,
      "grad_norm": 0.44179075956344604,
      "learning_rate": 0.0009986009474597423,
      "loss": 1.0087,
      "step": 500
    },
    {
      "epoch": 0.03368364322285099,
      "eval_loss": 0.919044017791748,
      "eval_runtime": 4.0503,
      "eval_samples_per_second": 1234.464,
      "eval_steps_per_second": 19.505,
      "step": 500
    },
    {
      "epoch": 0.04042037186742118,
      "grad_norm": 0.396930456161499,
      "learning_rate": 0.0009976879851550707,
      "loss": 0.9759,
      "step": 600
    },
    {
      "epoch": 0.04715710051199138,
      "grad_norm": 0.39025160670280457,
      "learning_rate": 0.0009965475648694023,
      "loss": 0.9506,
      "step": 700
    },
    {
      "epoch": 0.05389382915656157,
      "grad_norm": 0.3577525317668915,
      "learning_rate": 0.0009951802078081975,
      "loss": 0.9323,
      "step": 800
    },
    {
      "epoch": 0.060630557801131774,
      "grad_norm": 0.3586902618408203,
      "learning_rate": 0.0009935865388936683,
      "loss": 0.9148,
      "step": 900
    },
    {
      "epoch": 0.06736728644570197,
      "grad_norm": 0.3558438718318939,
      "learning_rate": 0.0009917672864791695,
      "loss": 0.8993,
      "step": 1000
    },
    {
      "epoch": 0.06736728644570197,
      "eval_loss": 0.8303639888763428,
      "eval_runtime": 4.0434,
      "eval_samples_per_second": 1236.578,
      "eval_steps_per_second": 19.538,
      "step": 1000
    },
    {
      "epoch": 0.07410401509027216,
      "grad_norm": 0.33415552973747253,
      "learning_rate": 0.0009897232820163203,
      "loss": 0.887,
      "step": 1100
    },
    {
      "epoch": 0.08084074373484236,
      "grad_norm": 0.3328455686569214,
      "learning_rate": 0.0009874554596750068,
      "loss": 0.8764,
      "step": 1200
    },
    {
      "epoch": 0.08757747237941256,
      "grad_norm": 0.34494221210479736,
      "learning_rate": 0.000984964855916438,
      "loss": 0.8687,
      "step": 1300
    },
    {
      "epoch": 0.09431420102398276,
      "grad_norm": 0.3205359876155853,
      "learning_rate": 0.0009822526090194543,
      "loss": 0.8616,
      "step": 1400
    },
    {
      "epoch": 0.10105092966855295,
      "grad_norm": 0.31778866052627563,
      "learning_rate": 0.0009793199585602988,
      "loss": 0.8531,
      "step": 1500
    },
    {
      "epoch": 0.10105092966855295,
      "eval_loss": 0.7877992391586304,
      "eval_runtime": 4.0459,
      "eval_samples_per_second": 1235.828,
      "eval_steps_per_second": 19.526,
      "step": 1500
    },
    {
      "epoch": 0.10778765831312315,
      "grad_norm": 0.2896178066730499,
      "learning_rate": 0.0009761682448460969,
      "loss": 0.845,
      "step": 1600
    },
    {
      "epoch": 0.11452438695769335,
      "grad_norm": 0.30994096398353577,
      "learning_rate": 0.0009727989083022944,
      "loss": 0.8422,
      "step": 1700
    },
    {
      "epoch": 0.12126111560226355,
      "grad_norm": 0.2902910113334656,
      "learning_rate": 0.0009692134888143424,
      "loss": 0.8343,
      "step": 1800
    },
    {
      "epoch": 0.12799784424683375,
      "grad_norm": 0.30568113923072815,
      "learning_rate": 0.0009654136250239245,
      "loss": 0.8302,
      "step": 1900
    },
    {
      "epoch": 0.13473457289140395,
      "grad_norm": 0.2924252152442932,
      "learning_rate": 0.0009614010535800489,
      "loss": 0.8237,
      "step": 2000
    },
    {
      "epoch": 0.13473457289140395,
      "eval_loss": 0.7636091113090515,
      "eval_runtime": 4.0523,
      "eval_samples_per_second": 1233.862,
      "eval_steps_per_second": 19.495,
      "step": 2000
    },
    {
      "epoch": 0.14147130153597412,
      "grad_norm": 0.2940412163734436,
      "learning_rate": 0.0009571776083453492,
      "loss": 0.8196,
      "step": 2100
    },
    {
      "epoch": 0.14820803018054432,
      "grad_norm": 0.2964770495891571,
      "learning_rate": 0.0009527452195579558,
      "loss": 0.8155,
      "step": 2200
    },
    {
      "epoch": 0.15494475882511452,
      "grad_norm": 0.29473844170570374,
      "learning_rate": 0.0009481059129493202,
      "loss": 0.8126,
      "step": 2300
    },
    {
      "epoch": 0.16168148746968472,
      "grad_norm": 0.26849669218063354,
      "learning_rate": 0.0009432618088183964,
      "loss": 0.81,
      "step": 2400
    },
    {
      "epoch": 0.16841821611425492,
      "grad_norm": 0.30280986428260803,
      "learning_rate": 0.0009382151210626026,
      "loss": 0.8071,
      "step": 2500
    },
    {
      "epoch": 0.16841821611425492,
      "eval_loss": 0.7478171586990356,
      "eval_runtime": 4.0503,
      "eval_samples_per_second": 1234.482,
      "eval_steps_per_second": 19.505,
      "step": 2500
    },
    {
      "epoch": 0.17515494475882512,
      "grad_norm": 0.31329289078712463,
      "learning_rate": 0.0009329681561660051,
      "loss": 0.8021,
      "step": 2600
    },
    {
      "epoch": 0.18189167340339532,
      "grad_norm": 0.2696886360645294,
      "learning_rate": 0.0009275233121451872,
      "loss": 0.8008,
      "step": 2700
    },
    {
      "epoch": 0.18862840204796552,
      "grad_norm": 0.26912084221839905,
      "learning_rate": 0.0009218830774532855,
      "loss": 0.7973,
      "step": 2800
    },
    {
      "epoch": 0.1953651306925357,
      "grad_norm": 0.27081477642059326,
      "learning_rate": 0.0009160500298426945,
      "loss": 0.7935,
      "step": 2900
    },
    {
      "epoch": 0.2021018593371059,
      "grad_norm": 0.27368906140327454,
      "learning_rate": 0.0009100268351869579,
      "loss": 0.7908,
      "step": 3000
    },
    {
      "epoch": 0.2021018593371059,
      "eval_loss": 0.7335129976272583,
      "eval_runtime": 4.0548,
      "eval_samples_per_second": 1233.113,
      "eval_steps_per_second": 19.483,
      "step": 3000
    },
    {
      "epoch": 0.2088385879816761,
      "grad_norm": 0.32002657651901245,
      "learning_rate": 0.0009038162462623858,
      "loss": 0.787,
      "step": 3100
    },
    {
      "epoch": 0.2155753166262463,
      "grad_norm": 0.25296279788017273,
      "learning_rate": 0.0008974211014899564,
      "loss": 0.7873,
      "step": 3200
    },
    {
      "epoch": 0.2223120452708165,
      "grad_norm": 0.27432960271835327,
      "learning_rate": 0.0008908443236380743,
      "loss": 0.7827,
      "step": 3300
    },
    {
      "epoch": 0.2290487739153867,
      "grad_norm": 0.2552671730518341,
      "learning_rate": 0.0008840889184867782,
      "loss": 0.7793,
      "step": 3400
    },
    {
      "epoch": 0.2357855025599569,
      "grad_norm": 0.27509957551956177,
      "learning_rate": 0.0008771579734540138,
      "loss": 0.7781,
      "step": 3500
    },
    {
      "epoch": 0.2357855025599569,
      "eval_loss": 0.7217926383018494,
      "eval_runtime": 4.0438,
      "eval_samples_per_second": 1236.453,
      "eval_steps_per_second": 19.536,
      "step": 3500
    },
    {
      "epoch": 0.2425222312045271,
      "grad_norm": 0.25811567902565,
      "learning_rate": 0.0008700546561845919,
      "loss": 0.7764,
      "step": 3600
    },
    {
      "epoch": 0.24925895984909727,
      "grad_norm": 0.26611506938934326,
      "learning_rate": 0.000862782213102482,
      "loss": 0.7744,
      "step": 3700
    },
    {
      "epoch": 0.2559956884936675,
      "grad_norm": 0.2390570193529129,
      "learning_rate": 0.0008553439679271025,
      "loss": 0.7717,
      "step": 3800
    },
    {
      "epoch": 0.2627324171382377,
      "grad_norm": 0.26289165019989014,
      "learning_rate": 0.0008477433201542824,
      "loss": 0.769,
      "step": 3900
    },
    {
      "epoch": 0.2694691457828079,
      "grad_norm": 0.2603146731853485,
      "learning_rate": 0.0008399837435025926,
      "loss": 0.7658,
      "step": 4000
    },
    {
      "epoch": 0.2694691457828079,
      "eval_loss": 0.7102092504501343,
      "eval_runtime": 4.0458,
      "eval_samples_per_second": 1235.853,
      "eval_steps_per_second": 19.526,
      "step": 4000
    }
  ],
  "logging_steps": 100,
  "max_steps": 14844,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 493989888000000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}