{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 935,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26737967914438504,
      "grad_norm": 17.321611404418945,
      "learning_rate": 1.8994652406417113e-05,
      "loss": 4.3588,
      "step": 50
    },
    {
      "epoch": 0.5347593582887701,
      "grad_norm": 18.49687957763672,
      "learning_rate": 1.7925133689839573e-05,
      "loss": 3.7275,
      "step": 100
    },
    {
      "epoch": 0.8021390374331551,
      "grad_norm": 17.81402587890625,
      "learning_rate": 1.6855614973262032e-05,
      "loss": 3.1286,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.293884754180908,
      "eval_runtime": 2.4316,
      "eval_samples_per_second": 68.268,
      "eval_steps_per_second": 17.273,
      "step": 187
    },
    {
      "epoch": 1.0695187165775402,
      "grad_norm": 16.78999137878418,
      "learning_rate": 1.5786096256684492e-05,
      "loss": 2.5828,
      "step": 200
    },
    {
      "epoch": 1.3368983957219251,
      "grad_norm": 16.12043571472168,
      "learning_rate": 1.4716577540106953e-05,
      "loss": 2.0374,
      "step": 250
    },
    {
      "epoch": 1.6042780748663101,
      "grad_norm": 14.432710647583008,
      "learning_rate": 1.3647058823529413e-05,
      "loss": 1.5509,
      "step": 300
    },
    {
      "epoch": 1.8716577540106951,
      "grad_norm": 11.290574073791504,
      "learning_rate": 1.2577540106951873e-05,
      "loss": 1.1191,
      "step": 350
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7051454186439514,
      "eval_runtime": 2.4082,
      "eval_samples_per_second": 68.932,
      "eval_steps_per_second": 17.441,
      "step": 374
    },
    {
      "epoch": 2.1390374331550803,
      "grad_norm": 8.16003131866455,
      "learning_rate": 1.1508021390374334e-05,
      "loss": 0.7617,
      "step": 400
    },
    {
      "epoch": 2.406417112299465,
      "grad_norm": 4.7810235023498535,
      "learning_rate": 1.0438502673796794e-05,
      "loss": 0.5062,
      "step": 450
    },
    {
      "epoch": 2.6737967914438503,
      "grad_norm": 2.9582180976867676,
      "learning_rate": 9.368983957219252e-06,
      "loss": 0.3417,
      "step": 500
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 2.0482232570648193,
      "learning_rate": 8.299465240641711e-06,
      "loss": 0.2597,
      "step": 550
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.21000835299491882,
      "eval_runtime": 2.1552,
      "eval_samples_per_second": 77.023,
      "eval_steps_per_second": 19.488,
      "step": 561
    },
    {
      "epoch": 3.2085561497326203,
      "grad_norm": 1.4092211723327637,
      "learning_rate": 7.229946524064172e-06,
      "loss": 0.1864,
      "step": 600
    },
    {
      "epoch": 3.4759358288770055,
      "grad_norm": 0.9414141178131104,
      "learning_rate": 6.1604278074866315e-06,
      "loss": 0.1345,
      "step": 650
    },
    {
      "epoch": 3.7433155080213902,
      "grad_norm": 0.7395118474960327,
      "learning_rate": 5.090909090909091e-06,
      "loss": 0.1344,
      "step": 700
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.15455076098442078,
      "eval_runtime": 2.1122,
      "eval_samples_per_second": 78.59,
      "eval_steps_per_second": 19.884,
      "step": 748
    },
    {
      "epoch": 4.010695187165775,
      "grad_norm": 0.6380388736724854,
      "learning_rate": 4.021390374331552e-06,
      "loss": 0.1239,
      "step": 750
    },
    {
      "epoch": 4.278074866310161,
      "grad_norm": 0.6696634292602539,
      "learning_rate": 2.9518716577540106e-06,
      "loss": 0.1042,
      "step": 800
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.590194582939148,
      "learning_rate": 1.8823529411764707e-06,
      "loss": 0.1017,
      "step": 850
    },
    {
      "epoch": 4.81283422459893,
      "grad_norm": 0.47769060730934143,
      "learning_rate": 8.128342245989306e-07,
      "loss": 0.1022,
      "step": 900
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.15090639889240265,
      "eval_runtime": 2.1578,
      "eval_samples_per_second": 76.931,
      "eval_steps_per_second": 19.464,
      "step": 935
    }
  ],
  "logging_steps": 50,
  "max_steps": 935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 787640939839488.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}