{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9979633401221996,
  "eval_steps": 200,
  "global_step": 245,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004073319755600814,
      "grad_norm": 49.20765561486543,
      "learning_rate": 3.846153846153847e-07,
      "loss": 4.7582,
      "step": 1
    },
    {
      "epoch": 0.020366598778004074,
      "grad_norm": 49.16830472275932,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 4.7542,
      "step": 5
    },
    {
      "epoch": 0.04073319755600815,
      "grad_norm": 47.93735350681692,
      "learning_rate": 3.846153846153847e-06,
      "loss": 4.675,
      "step": 10
    },
    {
      "epoch": 0.06109979633401222,
      "grad_norm": 34.85227976138109,
      "learning_rate": 4.999083215558211e-06,
      "loss": 4.1995,
      "step": 15
    },
    {
      "epoch": 0.0814663951120163,
      "grad_norm": 28.623178088461376,
      "learning_rate": 4.988777111066646e-06,
      "loss": 3.3879,
      "step": 20
    },
    {
      "epoch": 0.10183299389002037,
      "grad_norm": 14.704442306463271,
      "learning_rate": 4.967066306353816e-06,
      "loss": 2.5321,
      "step": 25
    },
    {
      "epoch": 0.12219959266802444,
      "grad_norm": 12.620738205233762,
      "learning_rate": 4.934050290127733e-06,
      "loss": 2.403,
      "step": 30
    },
    {
      "epoch": 0.1425661914460285,
      "grad_norm": 7.513981453630628,
      "learning_rate": 4.88988035667903e-06,
      "loss": 2.0794,
      "step": 35
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 5.5173642810506704,
      "learning_rate": 4.834758912582217e-06,
      "loss": 1.8869,
      "step": 40
    },
    {
      "epoch": 0.18329938900203666,
      "grad_norm": 4.641628513012735,
      "learning_rate": 4.7689385491773934e-06,
      "loss": 1.7749,
      "step": 45
    },
    {
      "epoch": 0.20366598778004075,
      "grad_norm": 4.064482253605761,
      "learning_rate": 4.692720885082693e-06,
      "loss": 1.7059,
      "step": 50
    },
    {
      "epoch": 0.2240325865580448,
      "grad_norm": 3.658952575458924,
      "learning_rate": 4.606455184041623e-06,
      "loss": 1.6527,
      "step": 55
    },
    {
      "epoch": 0.24439918533604887,
      "grad_norm": 3.3953108181872107,
      "learning_rate": 4.510536754438923e-06,
      "loss": 1.6071,
      "step": 60
    },
    {
      "epoch": 0.26476578411405294,
      "grad_norm": 3.1218567201858343,
      "learning_rate": 4.4054051378190915e-06,
      "loss": 1.5756,
      "step": 65
    },
    {
      "epoch": 0.285132382892057,
      "grad_norm": 3.018107484342879,
      "learning_rate": 4.2915420947086124e-06,
      "loss": 1.5449,
      "step": 70
    },
    {
      "epoch": 0.3054989816700611,
      "grad_norm": 2.7503856611169613,
      "learning_rate": 4.169469396971739e-06,
      "loss": 1.5139,
      "step": 75
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 2.614277144865713,
      "learning_rate": 4.039746436816277e-06,
      "loss": 1.4955,
      "step": 80
    },
    {
      "epoch": 0.34623217922606925,
      "grad_norm": 2.6742965366944467,
      "learning_rate": 3.9029676634059565e-06,
      "loss": 1.4554,
      "step": 85
    },
    {
      "epoch": 0.3665987780040733,
      "grad_norm": 2.542019317330229,
      "learning_rate": 3.7597598588260196e-06,
      "loss": 1.4344,
      "step": 90
    },
    {
      "epoch": 0.3869653767820774,
      "grad_norm": 2.5392741563301526,
      "learning_rate": 3.6107792658847597e-06,
      "loss": 1.428,
      "step": 95
    },
    {
      "epoch": 0.4073319755600815,
      "grad_norm": 2.352402399841174,
      "learning_rate": 3.4567085809127247e-06,
      "loss": 1.393,
      "step": 100
    },
    {
      "epoch": 0.42769857433808556,
      "grad_norm": 2.3051986813347836,
      "learning_rate": 3.29825382533995e-06,
      "loss": 1.3776,
      "step": 105
    },
    {
      "epoch": 0.4480651731160896,
      "grad_norm": 2.1913216414316015,
      "learning_rate": 3.1361411103870455e-06,
      "loss": 1.3703,
      "step": 110
    },
    {
      "epoch": 0.4684317718940937,
      "grad_norm": 2.0799262464815906,
      "learning_rate": 2.971113309695796e-06,
      "loss": 1.3551,
      "step": 115
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 2.1304438840612856,
      "learning_rate": 2.8039266551467876e-06,
      "loss": 1.3534,
      "step": 120
    },
    {
      "epoch": 0.5091649694501018,
      "grad_norm": 2.02651856945392,
      "learning_rate": 2.6353472714635443e-06,
      "loss": 1.3451,
      "step": 125
    },
    {
      "epoch": 0.5295315682281059,
      "grad_norm": 2.0213666994205073,
      "learning_rate": 2.466147665483196e-06,
      "loss": 1.3331,
      "step": 130
    },
    {
      "epoch": 0.5498981670061099,
      "grad_norm": 1.9063782318669384,
      "learning_rate": 2.2971031861814225e-06,
      "loss": 1.3302,
      "step": 135
    },
    {
      "epoch": 0.570264765784114,
      "grad_norm": 1.8510885600426448,
      "learning_rate": 2.128988471673435e-06,
      "loss": 1.3234,
      "step": 140
    },
    {
      "epoch": 0.5906313645621182,
      "grad_norm": 1.896713719309073,
      "learning_rate": 1.96257389947244e-06,
      "loss": 1.3309,
      "step": 145
    },
    {
      "epoch": 0.6109979633401222,
      "grad_norm": 1.7860315803999223,
      "learning_rate": 1.798622056272104e-06,
      "loss": 1.3166,
      "step": 150
    },
    {
      "epoch": 0.6313645621181263,
      "grad_norm": 1.7091260049598365,
      "learning_rate": 1.6378842434300746e-06,
      "loss": 1.3097,
      "step": 155
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 1.7668975196315897,
      "learning_rate": 1.481097034165998e-06,
      "loss": 1.3138,
      "step": 160
    },
    {
      "epoch": 0.6720977596741344,
      "grad_norm": 1.6213484424303142,
      "learning_rate": 1.328978898250525e-06,
      "loss": 1.2958,
      "step": 165
    },
    {
      "epoch": 0.6924643584521385,
      "grad_norm": 1.7070168750433874,
      "learning_rate": 1.1822269096524813e-06,
      "loss": 1.3088,
      "step": 170
    },
    {
      "epoch": 0.7128309572301426,
      "grad_norm": 1.6819401904260896,
      "learning_rate": 1.041513552231265e-06,
      "loss": 1.2866,
      "step": 175
    },
    {
      "epoch": 0.7331975560081466,
      "grad_norm": 1.6322096567129587,
      "learning_rate": 9.074836381122313e-07,
      "loss": 1.2968,
      "step": 180
    },
    {
      "epoch": 0.7535641547861507,
      "grad_norm": 1.7724019182054933,
      "learning_rate": 7.807513528664415e-07,
      "loss": 1.2945,
      "step": 185
    },
    {
      "epoch": 0.7739307535641547,
      "grad_norm": 1.6740383527430804,
      "learning_rate": 6.618974410351248e-07,
      "loss": 1.2947,
      "step": 190
    },
    {
      "epoch": 0.7942973523421588,
      "grad_norm": 1.5843813663357698,
      "learning_rate": 5.51466544896021e-07,
      "loss": 1.296,
      "step": 195
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 1.604642517306322,
      "learning_rate": 4.499647086666029e-07,
      "loss": 1.3086,
      "step": 200
    },
    {
      "epoch": 0.814663951120163,
      "eval_loss": 1.2994157075881958,
      "eval_runtime": 57.8527,
      "eval_samples_per_second": 120.202,
      "eval_steps_per_second": 1.884,
      "step": 200
    },
    {
      "epoch": 0.835030549898167,
      "grad_norm": 1.5963773663289895,
      "learning_rate": 3.578570595810274e-07,
      "loss": 1.2945,
      "step": 205
    },
    {
      "epoch": 0.8553971486761711,
      "grad_norm": 1.6106215658321952,
      "learning_rate": 2.7556567646717907e-07,
      "loss": 1.2817,
      "step": 210
    },
    {
      "epoch": 0.8757637474541752,
      "grad_norm": 1.5304515921043562,
      "learning_rate": 2.0346765559094566e-07,
      "loss": 1.2951,
      "step": 215
    },
    {
      "epoch": 0.8961303462321792,
      "grad_norm": 1.595543511408829,
      "learning_rate": 1.4189338263089242e-07,
      "loss": 1.2854,
      "step": 220
    },
    {
      "epoch": 0.9164969450101833,
      "grad_norm": 1.6367393626714526,
      "learning_rate": 9.112501870194273e-08,
      "loss": 1.29,
      "step": 225
    },
    {
      "epoch": 0.9368635437881874,
      "grad_norm": 1.525279082901764,
      "learning_rate": 5.1395207365770586e-08,
      "loss": 1.283,
      "step": 230
    },
    {
      "epoch": 0.9572301425661914,
      "grad_norm": 1.6110003829594048,
      "learning_rate": 2.2886008552983064e-08,
      "loss": 1.2891,
      "step": 235
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 1.5366047109816883,
      "learning_rate": 5.7280642823301366e-09,
      "loss": 1.2847,
      "step": 240
    },
    {
      "epoch": 0.9979633401221996,
      "grad_norm": 1.4989602574206755,
      "learning_rate": 0.0,
      "loss": 1.287,
      "step": 245
    },
    {
      "epoch": 0.9979633401221996,
      "step": 245,
      "total_flos": 154525407117312.0,
      "train_loss": 1.684320724253752,
      "train_runtime": 2040.7023,
      "train_samples_per_second": 30.788,
      "train_steps_per_second": 0.12
    }
  ],
  "logging_steps": 5,
  "max_steps": 245,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 154525407117312.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}