{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5732546705998034,
  "eval_steps": 100,
  "global_step": 200,
  "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
    }
  ],
  "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": 1.0146150364605317e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}