{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.146509341199607,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03933136676499508,
      "grad_norm": 0.481609046459198,
      "learning_rate": 0.00015,
      "loss": 2.0722,
      "step": 5
    },
    {
      "epoch": 0.07866273352999016,
      "grad_norm": 0.15720224380493164,
      "learning_rate": 0.0003,
      "loss": 1.4825,
      "step": 10
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 0.06716315448284149,
      "learning_rate": 0.00029759999999999997,
      "loss": 1.3333,
      "step": 15
    },
    {
      "epoch": 0.15732546705998032,
      "grad_norm": 0.06133478134870529,
      "learning_rate": 0.00029519999999999997,
      "loss": 1.2341,
      "step": 20
    },
    {
      "epoch": 0.19665683382497542,
      "grad_norm": 0.07264667749404907,
      "learning_rate": 0.00029279999999999996,
      "loss": 1.1756,
      "step": 25
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 0.07928217202425003,
      "learning_rate": 0.00029039999999999996,
      "loss": 1.1197,
      "step": 30
    },
    {
      "epoch": 0.2753195673549656,
      "grad_norm": 0.09420346468687057,
      "learning_rate": 0.00028799999999999995,
      "loss": 1.0834,
      "step": 35
    },
    {
      "epoch": 0.31465093411996065,
      "grad_norm": 0.0862259566783905,
      "learning_rate": 0.00028559999999999995,
      "loss": 1.044,
      "step": 40
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.09086894243955612,
      "learning_rate": 0.00028319999999999994,
      "loss": 1.0205,
      "step": 45
    },
    {
      "epoch": 0.39331366764995085,
      "grad_norm": 0.08469890058040619,
      "learning_rate": 0.0002808,
      "loss": 0.9798,
      "step": 50
    },
    {
      "epoch": 0.4326450344149459,
      "grad_norm": 0.10012397915124893,
      "learning_rate": 0.0002784,
      "loss": 0.9811,
      "step": 55
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 0.08633492887020111,
      "learning_rate": 0.000276,
      "loss": 0.9556,
      "step": 60
    },
    {
      "epoch": 0.511307767944936,
      "grad_norm": 0.09879346191883087,
      "learning_rate": 0.0002736,
      "loss": 0.9446,
      "step": 65
    },
    {
      "epoch": 0.5506391347099312,
      "grad_norm": 0.08795857429504395,
      "learning_rate": 0.0002712,
      "loss": 0.9228,
      "step": 70
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 0.0837111845612526,
      "learning_rate": 0.0002688,
      "loss": 0.9279,
      "step": 75
    },
    {
      "epoch": 0.6293018682399213,
      "grad_norm": 0.08551318198442459,
      "learning_rate": 0.00026639999999999997,
      "loss": 0.9267,
      "step": 80
    },
    {
      "epoch": 0.6686332350049164,
      "grad_norm": 0.08481767773628235,
      "learning_rate": 0.00026399999999999997,
      "loss": 0.9082,
      "step": 85
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.100365050137043,
      "learning_rate": 0.00026159999999999996,
      "loss": 0.9028,
      "step": 90
    },
    {
      "epoch": 0.7472959685349065,
      "grad_norm": 0.08463772386312485,
      "learning_rate": 0.00025919999999999996,
      "loss": 0.8866,
      "step": 95
    },
    {
      "epoch": 0.7866273352999017,
      "grad_norm": 0.09628409892320633,
      "learning_rate": 0.00025679999999999995,
      "loss": 0.8787,
      "step": 100
    },
    {
      "epoch": 0.7866273352999017,
      "eval_loss": 0.8853636980056763,
      "eval_runtime": 24.3719,
      "eval_samples_per_second": 6.729,
      "eval_steps_per_second": 0.862,
      "step": 100
    },
    {
      "epoch": 0.8259587020648967,
      "grad_norm": 0.08835043758153915,
      "learning_rate": 0.00025439999999999995,
      "loss": 0.8786,
      "step": 105
    },
    {
      "epoch": 0.8652900688298918,
      "grad_norm": 0.09190791845321655,
      "learning_rate": 0.00025199999999999995,
      "loss": 0.8693,
      "step": 110
    },
    {
      "epoch": 0.904621435594887,
      "grad_norm": 0.08965795487165451,
      "learning_rate": 0.00024959999999999994,
      "loss": 0.8772,
      "step": 115
    },
    {
      "epoch": 0.943952802359882,
      "grad_norm": 0.09055910259485245,
      "learning_rate": 0.0002472,
      "loss": 0.867,
      "step": 120
    },
    {
      "epoch": 0.983284169124877,
      "grad_norm": 0.09172637015581131,
      "learning_rate": 0.0002448,
      "loss": 0.8536,
      "step": 125
    },
    {
      "epoch": 1.022615535889872,
      "grad_norm": 0.10374542325735092,
      "learning_rate": 0.00024239999999999998,
      "loss": 0.9888,
      "step": 130
    },
    {
      "epoch": 1.0619469026548674,
      "grad_norm": 0.08842068910598755,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8443,
      "step": 135
    },
    {
      "epoch": 1.1012782694198624,
      "grad_norm": 0.0736837387084961,
      "learning_rate": 0.0002376,
      "loss": 0.8457,
      "step": 140
    },
    {
      "epoch": 1.1406096361848574,
      "grad_norm": 0.07575016468763351,
      "learning_rate": 0.0002352,
      "loss": 0.8335,
      "step": 145
    },
    {
      "epoch": 1.1799410029498525,
      "grad_norm": 0.07092955708503723,
      "learning_rate": 0.0002328,
      "loss": 0.8246,
      "step": 150
    },
    {
      "epoch": 1.2192723697148475,
      "grad_norm": 0.077423095703125,
      "learning_rate": 0.0002304,
      "loss": 0.823,
      "step": 155
    },
    {
      "epoch": 1.2586037364798428,
      "grad_norm": 0.07389391213655472,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.819,
      "step": 160
    },
    {
      "epoch": 1.2979351032448379,
      "grad_norm": 0.08229434490203857,
      "learning_rate": 0.00022559999999999998,
      "loss": 0.8181,
      "step": 165
    },
    {
      "epoch": 1.337266470009833,
      "grad_norm": 0.07665972411632538,
      "learning_rate": 0.00022319999999999998,
      "loss": 0.8118,
      "step": 170
    },
    {
      "epoch": 1.376597836774828,
      "grad_norm": 0.09001573175191879,
      "learning_rate": 0.00022079999999999997,
      "loss": 0.8157,
      "step": 175
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.07965826243162155,
      "learning_rate": 0.00021839999999999997,
      "loss": 0.8111,
      "step": 180
    },
    {
      "epoch": 1.455260570304818,
      "grad_norm": 0.08642959594726562,
      "learning_rate": 0.00021599999999999996,
      "loss": 0.8003,
      "step": 185
    },
    {
      "epoch": 1.494591937069813,
      "grad_norm": 0.0749087929725647,
      "learning_rate": 0.00021359999999999996,
      "loss": 0.7975,
      "step": 190
    },
    {
      "epoch": 1.5339233038348081,
      "grad_norm": 0.08575734496116638,
      "learning_rate": 0.00021119999999999996,
      "loss": 0.7888,
      "step": 195
    },
    {
      "epoch": 1.5732546705998034,
      "grad_norm": 0.0887129157781601,
      "learning_rate": 0.00020879999999999998,
      "loss": 0.7857,
      "step": 200
    },
    {
      "epoch": 1.5732546705998034,
      "eval_loss": 0.8026237487792969,
      "eval_runtime": 24.2397,
      "eval_samples_per_second": 6.766,
      "eval_steps_per_second": 0.866,
      "step": 200
    },
    {
      "epoch": 1.6125860373647984,
      "grad_norm": 0.0926935002207756,
      "learning_rate": 0.00020639999999999998,
      "loss": 0.7877,
      "step": 205
    },
    {
      "epoch": 1.6519174041297935,
      "grad_norm": 0.08537031710147858,
      "learning_rate": 0.000204,
      "loss": 0.7767,
      "step": 210
    },
    {
      "epoch": 1.6912487708947888,
      "grad_norm": 0.0766814798116684,
      "learning_rate": 0.0002016,
      "loss": 0.785,
      "step": 215
    },
    {
      "epoch": 1.7305801376597838,
      "grad_norm": 0.08394207805395126,
      "learning_rate": 0.0001992,
      "loss": 0.7832,
      "step": 220
    },
    {
      "epoch": 1.7699115044247788,
      "grad_norm": 0.0813060775399208,
      "learning_rate": 0.00019679999999999999,
      "loss": 0.7766,
      "step": 225
    },
    {
      "epoch": 1.809242871189774,
      "grad_norm": 0.08242856711149216,
      "learning_rate": 0.00019439999999999998,
      "loss": 0.7775,
      "step": 230
    },
    {
      "epoch": 1.848574237954769,
      "grad_norm": 0.07610878348350525,
      "learning_rate": 0.00019199999999999998,
      "loss": 0.7736,
      "step": 235
    },
    {
      "epoch": 1.887905604719764,
      "grad_norm": 0.08326178044080734,
      "learning_rate": 0.00018959999999999997,
      "loss": 0.7753,
      "step": 240
    },
    {
      "epoch": 1.927236971484759,
      "grad_norm": 0.09425383061170578,
      "learning_rate": 0.0001872,
      "loss": 0.7577,
      "step": 245
    },
    {
      "epoch": 1.966568338249754,
      "grad_norm": 0.08694498240947723,
      "learning_rate": 0.0001848,
      "loss": 0.7606,
      "step": 250
    },
    {
      "epoch": 2.005899705014749,
      "grad_norm": 0.22805309295654297,
      "learning_rate": 0.0001824,
      "loss": 0.8871,
      "step": 255
    },
    {
      "epoch": 2.045231071779744,
      "grad_norm": 0.09610473364591599,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.7315,
      "step": 260
    },
    {
      "epoch": 2.084562438544739,
      "grad_norm": 0.09666857868432999,
      "learning_rate": 0.00017759999999999998,
      "loss": 0.7315,
      "step": 265
    },
    {
      "epoch": 2.1238938053097347,
      "grad_norm": 0.09328849613666534,
      "learning_rate": 0.00017519999999999998,
      "loss": 0.7344,
      "step": 270
    },
    {
      "epoch": 2.1632251720747298,
      "grad_norm": 0.08137473464012146,
      "learning_rate": 0.00017279999999999997,
      "loss": 0.7347,
      "step": 275
    },
    {
      "epoch": 2.202556538839725,
      "grad_norm": 0.08166103810071945,
      "learning_rate": 0.00017039999999999997,
      "loss": 0.7281,
      "step": 280
    },
    {
      "epoch": 2.24188790560472,
      "grad_norm": 0.08074019104242325,
      "learning_rate": 0.000168,
      "loss": 0.7345,
      "step": 285
    },
    {
      "epoch": 2.281219272369715,
      "grad_norm": 0.08479057997465134,
      "learning_rate": 0.0001656,
      "loss": 0.726,
      "step": 290
    },
    {
      "epoch": 2.32055063913471,
      "grad_norm": 0.08091601729393005,
      "learning_rate": 0.0001632,
      "loss": 0.7184,
      "step": 295
    },
    {
      "epoch": 2.359882005899705,
      "grad_norm": 0.08470489084720612,
      "learning_rate": 0.0001608,
      "loss": 0.7233,
      "step": 300
    },
    {
      "epoch": 2.359882005899705,
      "eval_loss": 0.7612683176994324,
      "eval_runtime": 24.27,
      "eval_samples_per_second": 6.757,
      "eval_steps_per_second": 0.865,
      "step": 300
    },
    {
      "epoch": 2.3992133726647,
      "grad_norm": 0.08677177131175995,
      "learning_rate": 0.0001584,
      "loss": 0.721,
      "step": 305
    },
    {
      "epoch": 2.438544739429695,
      "grad_norm": 0.08474377542734146,
      "learning_rate": 0.000156,
      "loss": 0.7141,
      "step": 310
    },
    {
      "epoch": 2.47787610619469,
      "grad_norm": 0.08565227687358856,
      "learning_rate": 0.0001536,
      "loss": 0.7173,
      "step": 315
    },
    {
      "epoch": 2.5172074729596856,
      "grad_norm": 0.08714301139116287,
      "learning_rate": 0.0001512,
      "loss": 0.7274,
      "step": 320
    },
    {
      "epoch": 2.5565388397246807,
      "grad_norm": 0.0934271439909935,
      "learning_rate": 0.00014879999999999998,
      "loss": 0.7263,
      "step": 325
    },
    {
      "epoch": 2.5958702064896757,
      "grad_norm": 0.08581375330686569,
      "learning_rate": 0.00014639999999999998,
      "loss": 0.7248,
      "step": 330
    },
    {
      "epoch": 2.6352015732546707,
      "grad_norm": 0.08378680050373077,
      "learning_rate": 0.00014399999999999998,
      "loss": 0.721,
      "step": 335
    },
    {
      "epoch": 2.674532940019666,
      "grad_norm": 0.08449660986661911,
      "learning_rate": 0.00014159999999999997,
      "loss": 0.7156,
      "step": 340
    },
    {
      "epoch": 2.713864306784661,
      "grad_norm": 0.08646751940250397,
      "learning_rate": 0.0001392,
      "loss": 0.7094,
      "step": 345
    },
    {
      "epoch": 2.753195673549656,
      "grad_norm": 0.08911272883415222,
      "learning_rate": 0.0001368,
      "loss": 0.709,
      "step": 350
    },
    {
      "epoch": 2.792527040314651,
      "grad_norm": 0.0970829427242279,
      "learning_rate": 0.0001344,
      "loss": 0.7107,
      "step": 355
    },
    {
      "epoch": 2.831858407079646,
      "grad_norm": 0.0854572132229805,
      "learning_rate": 0.00013199999999999998,
      "loss": 0.7148,
      "step": 360
    },
    {
      "epoch": 2.871189773844641,
      "grad_norm": 0.08210612088441849,
      "learning_rate": 0.00012959999999999998,
      "loss": 0.7132,
      "step": 365
    },
    {
      "epoch": 2.910521140609636,
      "grad_norm": 0.0925467386841774,
      "learning_rate": 0.00012719999999999997,
      "loss": 0.7201,
      "step": 370
    },
    {
      "epoch": 2.949852507374631,
      "grad_norm": 0.09149914979934692,
      "learning_rate": 0.00012479999999999997,
      "loss": 0.7086,
      "step": 375
    },
    {
      "epoch": 2.989183874139626,
      "grad_norm": 0.0827464610338211,
      "learning_rate": 0.0001224,
      "loss": 0.7102,
      "step": 380
    },
    {
      "epoch": 3.0285152409046217,
      "grad_norm": 0.09861475974321365,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.8086,
      "step": 385
    },
    {
      "epoch": 3.0678466076696167,
      "grad_norm": 0.09810496121644974,
      "learning_rate": 0.0001176,
      "loss": 0.6784,
      "step": 390
    },
    {
      "epoch": 3.1071779744346117,
      "grad_norm": 0.08657824248075485,
      "learning_rate": 0.0001152,
      "loss": 0.6818,
      "step": 395
    },
    {
      "epoch": 3.146509341199607,
      "grad_norm": 0.08861815184354782,
      "learning_rate": 0.00011279999999999999,
      "loss": 0.6755,
      "step": 400
    },
    {
      "epoch": 3.146509341199607,
      "eval_loss": 0.7408613562583923,
      "eval_runtime": 24.2895,
      "eval_samples_per_second": 6.752,
      "eval_steps_per_second": 0.865,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 635,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0292300729210634e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}