{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.989010989010989,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 31.073850631713867,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.5967,
      "step": 1
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 32.91181182861328,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.723,
      "step": 2
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 31.494897842407227,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6125,
      "step": 3
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 30.80953598022461,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.58,
      "step": 4
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 31.269071578979492,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.5977,
      "step": 5
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 30.687875747680664,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.5588,
      "step": 6
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 31.30279541015625,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.5731,
      "step": 7
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 31.384830474853516,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.561,
      "step": 8
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 30.58422088623047,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.4872,
      "step": 9
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 30.883068084716797,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.5257,
      "step": 10
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 32.198814392089844,
      "learning_rate": 5.5e-07,
      "loss": 2.6286,
      "step": 11
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 31.001300811767578,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.4632,
      "step": 12
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 31.106016159057617,
      "learning_rate": 6.5e-07,
      "loss": 2.4274,
      "step": 13
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 31.180011749267578,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.3864,
      "step": 14
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 30.95736312866211,
      "learning_rate": 7.5e-07,
      "loss": 2.2977,
      "step": 15
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 31.67963218688965,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.2632,
      "step": 16
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 32.420562744140625,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.1983,
      "step": 17
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 32.46091079711914,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.0623,
      "step": 18
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 31.34447479248047,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.8633,
      "step": 19
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 31.65386962890625,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7861,
      "step": 20
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 30.12110137939453,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.6408,
      "step": 21
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 28.824857711791992,
      "learning_rate": 1.1e-06,
      "loss": 1.5022,
      "step": 22
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 27.37271499633789,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.3799,
      "step": 23
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 26.869949340820312,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.2699,
      "step": 24
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 26.696306228637695,
      "learning_rate": 1.25e-06,
      "loss": 1.107,
      "step": 25
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 29.182300567626953,
      "learning_rate": 1.3e-06,
      "loss": 0.9981,
      "step": 26
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 28.117998123168945,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7886,
      "step": 27
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 27.153093338012695,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.6565,
      "step": 28
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 24.350711822509766,
      "learning_rate": 1.45e-06,
      "loss": 0.5143,
      "step": 29
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 21.189594268798828,
      "learning_rate": 1.5e-06,
      "loss": 0.3953,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.57811009028096e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}