{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.048859139101969026,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009771827820393806,
      "grad_norm": 0.5417118072509766,
      "learning_rate": 4.995602247740044e-05,
      "loss": 1.378,
      "step": 100
    },
    {
      "epoch": 0.001954365564078761,
      "grad_norm": 0.6493918895721436,
      "learning_rate": 4.990715856340093e-05,
      "loss": 1.3304,
      "step": 200
    },
    {
      "epoch": 0.0029315483461181415,
      "grad_norm": 0.9062462449073792,
      "learning_rate": 4.9858294649401425e-05,
      "loss": 1.3284,
      "step": 300
    },
    {
      "epoch": 0.003908731128157522,
      "grad_norm": 0.750052273273468,
      "learning_rate": 4.9809430735401906e-05,
      "loss": 1.3166,
      "step": 400
    },
    {
      "epoch": 0.004885913910196903,
      "grad_norm": 0.6602022051811218,
      "learning_rate": 4.97605668214024e-05,
      "loss": 1.3166,
      "step": 500
    },
    {
      "epoch": 0.005863096692236283,
      "grad_norm": 0.4193927049636841,
      "learning_rate": 4.971170290740288e-05,
      "loss": 1.3098,
      "step": 600
    },
    {
      "epoch": 0.006840279474275663,
      "grad_norm": 0.6095415949821472,
      "learning_rate": 4.966283899340338e-05,
      "loss": 1.3103,
      "step": 700
    },
    {
      "epoch": 0.007817462256315045,
      "grad_norm": 0.9943467378616333,
      "learning_rate": 4.9613975079403865e-05,
      "loss": 1.3096,
      "step": 800
    },
    {
      "epoch": 0.008794645038354424,
      "grad_norm": 1.2263585329055786,
      "learning_rate": 4.9565111165404346e-05,
      "loss": 1.3067,
      "step": 900
    },
    {
      "epoch": 0.009771827820393805,
      "grad_norm": 0.7198677659034729,
      "learning_rate": 4.951624725140484e-05,
      "loss": 1.3041,
      "step": 1000
    },
    {
      "epoch": 0.010749010602433185,
      "grad_norm": 0.7370775938034058,
      "learning_rate": 4.946738333740533e-05,
      "loss": 1.302,
      "step": 1100
    },
    {
      "epoch": 0.011726193384472566,
      "grad_norm": 0.5109437704086304,
      "learning_rate": 4.941851942340582e-05,
      "loss": 1.3089,
      "step": 1200
    },
    {
      "epoch": 0.012703376166511945,
      "grad_norm": 0.1879555583000183,
      "learning_rate": 4.9369655509406305e-05,
      "loss": 1.3043,
      "step": 1300
    },
    {
      "epoch": 0.013680558948551327,
      "grad_norm": 0.951046884059906,
      "learning_rate": 4.932079159540679e-05,
      "loss": 1.3098,
      "step": 1400
    },
    {
      "epoch": 0.014657741730590706,
      "grad_norm": 0.2478829026222229,
      "learning_rate": 4.927192768140728e-05,
      "loss": 1.3026,
      "step": 1500
    },
    {
      "epoch": 0.01563492451263009,
      "grad_norm": 0.5585843324661255,
      "learning_rate": 4.9223063767407776e-05,
      "loss": 1.3014,
      "step": 1600
    },
    {
      "epoch": 0.016612107294669467,
      "grad_norm": 0.48532453179359436,
      "learning_rate": 4.917419985340826e-05,
      "loss": 1.2981,
      "step": 1700
    },
    {
      "epoch": 0.017589290076708848,
      "grad_norm": 0.4233573079109192,
      "learning_rate": 4.912533593940875e-05,
      "loss": 1.2992,
      "step": 1800
    },
    {
      "epoch": 0.01856647285874823,
      "grad_norm": 0.3272475600242615,
      "learning_rate": 4.9076472025409234e-05,
      "loss": 1.292,
      "step": 1900
    },
    {
      "epoch": 0.01954365564078761,
      "grad_norm": 0.5299385786056519,
      "learning_rate": 4.902760811140973e-05,
      "loss": 1.2963,
      "step": 2000
    },
    {
      "epoch": 0.02052083842282699,
      "grad_norm": 0.1614024043083191,
      "learning_rate": 4.8978744197410216e-05,
      "loss": 1.2945,
      "step": 2100
    },
    {
      "epoch": 0.02149802120486637,
      "grad_norm": 0.6039963960647583,
      "learning_rate": 4.8929880283410705e-05,
      "loss": 1.2913,
      "step": 2200
    },
    {
      "epoch": 0.02247520398690575,
      "grad_norm": 0.5772804021835327,
      "learning_rate": 4.888101636941119e-05,
      "loss": 1.2895,
      "step": 2300
    },
    {
      "epoch": 0.023452386768945132,
      "grad_norm": 0.7489622235298157,
      "learning_rate": 4.883215245541168e-05,
      "loss": 1.2847,
      "step": 2400
    },
    {
      "epoch": 0.024429569550984513,
      "grad_norm": 0.30208253860473633,
      "learning_rate": 4.878328854141217e-05,
      "loss": 1.2924,
      "step": 2500
    },
    {
      "epoch": 0.02540675233302389,
      "grad_norm": 0.36944472789764404,
      "learning_rate": 4.873442462741266e-05,
      "loss": 1.2916,
      "step": 2600
    },
    {
      "epoch": 0.026383935115063272,
      "grad_norm": 0.3268676698207855,
      "learning_rate": 4.8685560713413145e-05,
      "loss": 1.2893,
      "step": 2700
    },
    {
      "epoch": 0.027361117897102653,
      "grad_norm": 0.2795974910259247,
      "learning_rate": 4.863669679941363e-05,
      "loss": 1.282,
      "step": 2800
    },
    {
      "epoch": 0.028338300679142035,
      "grad_norm": 0.36298853158950806,
      "learning_rate": 4.858783288541413e-05,
      "loss": 1.2832,
      "step": 2900
    },
    {
      "epoch": 0.029315483461181412,
      "grad_norm": 0.5242423415184021,
      "learning_rate": 4.853896897141461e-05,
      "loss": 1.2819,
      "step": 3000
    },
    {
      "epoch": 0.030292666243220794,
      "grad_norm": 0.25340864062309265,
      "learning_rate": 4.8490105057415104e-05,
      "loss": 1.2809,
      "step": 3100
    },
    {
      "epoch": 0.03126984902526018,
      "grad_norm": 0.7241976261138916,
      "learning_rate": 4.844124114341559e-05,
      "loss": 1.2802,
      "step": 3200
    },
    {
      "epoch": 0.032247031807299556,
      "grad_norm": 0.5154001712799072,
      "learning_rate": 4.839237722941608e-05,
      "loss": 1.2748,
      "step": 3300
    },
    {
      "epoch": 0.033224214589338934,
      "grad_norm": 0.5323473811149597,
      "learning_rate": 4.834351331541657e-05,
      "loss": 1.284,
      "step": 3400
    },
    {
      "epoch": 0.03420139737137832,
      "grad_norm": 0.3947168290615082,
      "learning_rate": 4.8294649401417056e-05,
      "loss": 1.276,
      "step": 3500
    },
    {
      "epoch": 0.035178580153417696,
      "grad_norm": 0.4776057302951813,
      "learning_rate": 4.8245785487417544e-05,
      "loss": 1.2783,
      "step": 3600
    },
    {
      "epoch": 0.036155762935457074,
      "grad_norm": 0.4884164035320282,
      "learning_rate": 4.819692157341804e-05,
      "loss": 1.2745,
      "step": 3700
    },
    {
      "epoch": 0.03713294571749646,
      "grad_norm": 0.5210428833961487,
      "learning_rate": 4.814805765941852e-05,
      "loss": 1.2707,
      "step": 3800
    },
    {
      "epoch": 0.038110128499535836,
      "grad_norm": 0.46214359998703003,
      "learning_rate": 4.809919374541901e-05,
      "loss": 1.2727,
      "step": 3900
    },
    {
      "epoch": 0.03908731128157522,
      "grad_norm": 0.2656782865524292,
      "learning_rate": 4.8050329831419496e-05,
      "loss": 1.2694,
      "step": 4000
    },
    {
      "epoch": 0.0400644940636146,
      "grad_norm": 0.4923059940338135,
      "learning_rate": 4.8001465917419985e-05,
      "loss": 1.2665,
      "step": 4100
    },
    {
      "epoch": 0.04104167684565398,
      "grad_norm": 0.92928147315979,
      "learning_rate": 4.795260200342048e-05,
      "loss": 1.2627,
      "step": 4200
    },
    {
      "epoch": 0.04201885962769336,
      "grad_norm": 1.0651229619979858,
      "learning_rate": 4.790373808942096e-05,
      "loss": 1.2623,
      "step": 4300
    },
    {
      "epoch": 0.04299604240973274,
      "grad_norm": 0.9612557888031006,
      "learning_rate": 4.7854874175421456e-05,
      "loss": 1.2482,
      "step": 4400
    },
    {
      "epoch": 0.043973225191772124,
      "grad_norm": 1.0120874643325806,
      "learning_rate": 4.7806010261421944e-05,
      "loss": 1.2589,
      "step": 4500
    },
    {
      "epoch": 0.0449504079738115,
      "grad_norm": 0.6250020861625671,
      "learning_rate": 4.775714634742243e-05,
      "loss": 1.2499,
      "step": 4600
    },
    {
      "epoch": 0.04592759075585088,
      "grad_norm": 0.2850038707256317,
      "learning_rate": 4.770828243342292e-05,
      "loss": 1.2446,
      "step": 4700
    },
    {
      "epoch": 0.046904773537890264,
      "grad_norm": 1.2032625675201416,
      "learning_rate": 4.765941851942341e-05,
      "loss": 1.2238,
      "step": 4800
    },
    {
      "epoch": 0.04788195631992964,
      "grad_norm": 0.42024949193000793,
      "learning_rate": 4.7610554605423896e-05,
      "loss": 1.2255,
      "step": 4900
    },
    {
      "epoch": 0.048859139101969026,
      "grad_norm": 0.7451406121253967,
      "learning_rate": 4.756169069142439e-05,
      "loss": 1.2071,
      "step": 5000
    }
  ],
  "logging_steps": 100,
  "max_steps": 102335,
  "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": 6.27146158505984e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}