{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1893491124260355,
  "eval_steps": 20,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001183431952662722,
      "eval_loss": 11.76406478881836,
      "eval_runtime": 3.448,
      "eval_samples_per_second": 435.611,
      "eval_steps_per_second": 27.262,
      "step": 1
    },
    {
      "epoch": 0.011834319526627219,
      "grad_norm": 0.275390625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 11.764,
      "step": 10
    },
    {
      "epoch": 0.023668639053254437,
      "grad_norm": 0.1640625,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 11.7612,
      "step": 20
    },
    {
      "epoch": 0.023668639053254437,
      "eval_loss": 11.763768196105957,
      "eval_runtime": 3.4066,
      "eval_samples_per_second": 440.914,
      "eval_steps_per_second": 27.594,
      "step": 20
    },
    {
      "epoch": 0.03550295857988166,
      "grad_norm": 0.353515625,
      "learning_rate": 4.8e-05,
      "loss": 11.7612,
      "step": 30
    },
    {
      "epoch": 0.047337278106508875,
      "grad_norm": 0.197265625,
      "learning_rate": 6.400000000000001e-05,
      "loss": 11.7593,
      "step": 40
    },
    {
      "epoch": 0.047337278106508875,
      "eval_loss": 11.76196575164795,
      "eval_runtime": 3.4379,
      "eval_samples_per_second": 436.894,
      "eval_steps_per_second": 27.342,
      "step": 40
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.55078125,
      "learning_rate": 8e-05,
      "loss": 11.7623,
      "step": 50
    },
    {
      "epoch": 0.07100591715976332,
      "grad_norm": 0.259765625,
      "learning_rate": 9.6e-05,
      "loss": 11.758,
      "step": 60
    },
    {
      "epoch": 0.07100591715976332,
      "eval_loss": 11.75584888458252,
      "eval_runtime": 3.6091,
      "eval_samples_per_second": 416.17,
      "eval_steps_per_second": 26.045,
      "step": 60
    },
    {
      "epoch": 0.08284023668639054,
      "grad_norm": 0.2314453125,
      "learning_rate": 0.00011200000000000001,
      "loss": 11.7513,
      "step": 70
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 0.404296875,
      "learning_rate": 0.00012800000000000002,
      "loss": 11.7397,
      "step": 80
    },
    {
      "epoch": 0.09467455621301775,
      "eval_loss": 11.732006072998047,
      "eval_runtime": 3.4157,
      "eval_samples_per_second": 439.736,
      "eval_steps_per_second": 27.52,
      "step": 80
    },
    {
      "epoch": 0.10650887573964497,
      "grad_norm": 0.5,
      "learning_rate": 0.000144,
      "loss": 11.7175,
      "step": 90
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00016,
      "loss": 11.6553,
      "step": 100
    },
    {
      "epoch": 0.11834319526627218,
      "eval_loss": 11.619158744812012,
      "eval_runtime": 3.4756,
      "eval_samples_per_second": 432.159,
      "eval_steps_per_second": 27.046,
      "step": 100
    },
    {
      "epoch": 0.1301775147928994,
      "grad_norm": 0.453125,
      "learning_rate": 0.00017600000000000002,
      "loss": 11.5808,
      "step": 110
    },
    {
      "epoch": 0.14201183431952663,
      "grad_norm": 0.36328125,
      "learning_rate": 0.000192,
      "loss": 11.4893,
      "step": 120
    },
    {
      "epoch": 0.14201183431952663,
      "eval_loss": 11.44636344909668,
      "eval_runtime": 3.4158,
      "eval_samples_per_second": 439.727,
      "eval_steps_per_second": 27.52,
      "step": 120
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001999978128380225,
      "loss": 11.404,
      "step": 130
    },
    {
      "epoch": 0.16568047337278108,
      "grad_norm": 0.41015625,
      "learning_rate": 0.0001999803161162393,
      "loss": 11.3215,
      "step": 140
    },
    {
      "epoch": 0.16568047337278108,
      "eval_loss": 11.274709701538086,
      "eval_runtime": 3.4634,
      "eval_samples_per_second": 433.675,
      "eval_steps_per_second": 27.141,
      "step": 140
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.6953125,
      "learning_rate": 0.00019994532573409262,
      "loss": 11.2396,
      "step": 150
    },
    {
      "epoch": 0.1893491124260355,
      "grad_norm": 0.4296875,
      "learning_rate": 0.00019989284781388617,
      "loss": 11.1631,
      "step": 160
    },
    {
      "epoch": 0.1893491124260355,
      "eval_loss": 11.122227668762207,
      "eval_runtime": 3.3962,
      "eval_samples_per_second": 442.264,
      "eval_steps_per_second": 27.678,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 64864208814080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}