{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.820512820512821,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 2.4217140674591064,
      "learning_rate": 1.6260162601626018e-05,
      "loss": 2.138,
      "step": 100
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 6.815347194671631,
      "learning_rate": 1.9981460480193124e-05,
      "loss": 1.6003,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4732680320739746,
      "eval_runtime": 15.0324,
      "eval_samples_per_second": 36.255,
      "eval_steps_per_second": 4.59,
      "step": 273
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 1.7914855480194092,
      "learning_rate": 1.9902166320971888e-05,
      "loss": 1.4491,
      "step": 300
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 1.6955766677856445,
      "learning_rate": 1.9760958702967613e-05,
      "loss": 1.3738,
      "step": 400
    },
    {
      "epoch": 1.8315018315018317,
      "grad_norm": 1.5401254892349243,
      "learning_rate": 1.955872052914858e-05,
      "loss": 1.3584,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.352551817893982,
      "eval_runtime": 15.087,
      "eval_samples_per_second": 36.124,
      "eval_steps_per_second": 4.573,
      "step": 546
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 1.4598904848098755,
      "learning_rate": 1.929671629704323e-05,
      "loss": 1.3216,
      "step": 600
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 1.4998373985290527,
      "learning_rate": 1.8976584192448447e-05,
      "loss": 1.2805,
      "step": 700
    },
    {
      "epoch": 2.9304029304029307,
      "grad_norm": 1.5303151607513428,
      "learning_rate": 1.8600325846645762e-05,
      "loss": 1.2576,
      "step": 800
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.277264952659607,
      "eval_runtime": 15.0223,
      "eval_samples_per_second": 36.279,
      "eval_steps_per_second": 4.593,
      "step": 819
    },
    {
      "epoch": 3.2967032967032965,
      "grad_norm": 1.9848594665527344,
      "learning_rate": 1.817029382116864e-05,
      "loss": 1.191,
      "step": 900
    },
    {
      "epoch": 3.663003663003663,
      "grad_norm": 2.3116588592529297,
      "learning_rate": 1.768917689837254e-05,
      "loss": 1.1488,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2125439643859863,
      "eval_runtime": 15.0709,
      "eval_samples_per_second": 36.162,
      "eval_steps_per_second": 4.578,
      "step": 1092
    },
    {
      "epoch": 4.029304029304029,
      "grad_norm": 1.7878159284591675,
      "learning_rate": 1.7159983269778783e-05,
      "loss": 1.1323,
      "step": 1100
    },
    {
      "epoch": 4.395604395604396,
      "grad_norm": 1.716820240020752,
      "learning_rate": 1.6586021727307247e-05,
      "loss": 1.1049,
      "step": 1200
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 1.9888262748718262,
      "learning_rate": 1.597088097500016e-05,
      "loss": 1.0953,
      "step": 1300
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1914163827896118,
      "eval_runtime": 15.0388,
      "eval_samples_per_second": 36.24,
      "eval_steps_per_second": 4.588,
      "step": 1365
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 2.7528648376464844,
      "learning_rate": 1.5318407190590678e-05,
      "loss": 1.0856,
      "step": 1400
    },
    {
      "epoch": 5.4945054945054945,
      "grad_norm": 2.673952579498291,
      "learning_rate": 1.4632679977212965e-05,
      "loss": 1.0621,
      "step": 1500
    },
    {
      "epoch": 5.860805860805861,
      "grad_norm": 2.82629132270813,
      "learning_rate": 1.3917986855616088e-05,
      "loss": 1.0526,
      "step": 1600
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.1818946599960327,
      "eval_runtime": 15.0308,
      "eval_samples_per_second": 36.259,
      "eval_steps_per_second": 4.591,
      "step": 1638
    },
    {
      "epoch": 6.227106227106227,
      "grad_norm": 2.4375030994415283,
      "learning_rate": 1.317879645636958e-05,
      "loss": 1.0628,
      "step": 1700
    },
    {
      "epoch": 6.593406593406593,
      "grad_norm": 2.1613872051239014,
      "learning_rate": 1.2419730579676861e-05,
      "loss": 1.0322,
      "step": 1800
    },
    {
      "epoch": 6.95970695970696,
      "grad_norm": 2.790818214416504,
      "learning_rate": 1.1645535297492982e-05,
      "loss": 1.0387,
      "step": 1900
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.1750704050064087,
      "eval_runtime": 15.0518,
      "eval_samples_per_second": 36.208,
      "eval_steps_per_second": 4.584,
      "step": 1911
    },
    {
      "epoch": 7.326007326007326,
      "grad_norm": 3.714703321456909,
      "learning_rate": 1.0861051278631194e-05,
      "loss": 1.0207,
      "step": 2000
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 3.773744821548462,
      "learning_rate": 1.0071183522401078e-05,
      "loss": 1.0147,
      "step": 2100
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.173836588859558,
      "eval_runtime": 15.0207,
      "eval_samples_per_second": 36.283,
      "eval_steps_per_second": 4.594,
      "step": 2184
    },
    {
      "epoch": 8.058608058608058,
      "grad_norm": 2.6176517009735107,
      "learning_rate": 9.280870690019201e-06,
      "loss": 1.0227,
      "step": 2200
    },
    {
      "epoch": 8.424908424908425,
      "grad_norm": 2.5360729694366455,
      "learning_rate": 8.495054225548138e-06,
      "loss": 0.9955,
      "step": 2300
    },
    {
      "epoch": 8.791208791208792,
      "grad_norm": 3.0869531631469727,
      "learning_rate": 7.7186474594357e-06,
      "loss": 1.0011,
      "step": 2400
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.1736818552017212,
      "eval_runtime": 15.0704,
      "eval_samples_per_second": 36.164,
      "eval_steps_per_second": 4.579,
      "step": 2457
    },
    {
      "epoch": 9.157509157509157,
      "grad_norm": 4.066312789916992,
      "learning_rate": 6.956504887834985e-06,
      "loss": 0.9794,
      "step": 2500
    },
    {
      "epoch": 9.523809523809524,
      "grad_norm": 4.211170673370361,
      "learning_rate": 6.2133918197868756e-06,
      "loss": 0.9796,
      "step": 2600
    },
    {
      "epoch": 9.89010989010989,
      "grad_norm": 3.3649957180023193,
      "learning_rate": 5.493954582046381e-06,
      "loss": 0.9863,
      "step": 2700
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1735256910324097,
      "eval_runtime": 15.0245,
      "eval_samples_per_second": 36.274,
      "eval_steps_per_second": 4.593,
      "step": 2730
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 3.101034641265869,
      "learning_rate": 4.802691467847735e-06,
      "loss": 0.9777,
      "step": 2800
    },
    {
      "epoch": 10.622710622710622,
      "grad_norm": 2.788987398147583,
      "learning_rate": 4.143924611251489e-06,
      "loss": 0.9686,
      "step": 2900
    },
    {
      "epoch": 10.989010989010989,
      "grad_norm": 4.374148845672607,
      "learning_rate": 3.521772962929798e-06,
      "loss": 0.9575,
      "step": 3000
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.1749252080917358,
      "eval_runtime": 15.0567,
      "eval_samples_per_second": 36.197,
      "eval_steps_per_second": 4.583,
      "step": 3003
    },
    {
      "epoch": 11.355311355311356,
      "grad_norm": 5.036626815795898,
      "learning_rate": 2.9401265363591637e-06,
      "loss": 0.9641,
      "step": 3100
    },
    {
      "epoch": 11.72161172161172,
      "grad_norm": 4.363086700439453,
      "learning_rate": 2.402622085446806e-06,
      "loss": 0.9464,
      "step": 3200
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1757398843765259,
      "eval_runtime": 15.0319,
      "eval_samples_per_second": 36.256,
      "eval_steps_per_second": 4.59,
      "step": 3276
    },
    {
      "epoch": 12.087912087912088,
      "grad_norm": 3.048525094985962,
      "learning_rate": 1.9126203656666918e-06,
      "loss": 0.9857,
      "step": 3300
    },
    {
      "epoch": 12.454212454212454,
      "grad_norm": 4.559013843536377,
      "learning_rate": 1.473185120880295e-06,
      "loss": 0.9532,
      "step": 3400
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 3.2386648654937744,
      "learning_rate": 1.0870639272274263e-06,
      "loss": 0.9575,
      "step": 3500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4095,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 1.4255446710512026e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}