{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0204081632653061,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04081632653061224,
      "eval_loss": 2.0148518085479736,
      "eval_runtime": 0.5957,
      "eval_samples_per_second": 18.467,
      "eval_steps_per_second": 10.073,
      "step": 1
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 1.1381850242614746,
      "learning_rate": 6e-05,
      "loss": 8.3085,
      "step": 3
    },
    {
      "epoch": 0.20408163265306123,
      "eval_loss": 1.9805481433868408,
      "eval_runtime": 0.5895,
      "eval_samples_per_second": 18.66,
      "eval_steps_per_second": 10.178,
      "step": 5
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 1.0049192905426025,
      "learning_rate": 0.00012,
      "loss": 7.6209,
      "step": 6
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 1.2996903657913208,
      "learning_rate": 0.00018,
      "loss": 8.1239,
      "step": 9
    },
    {
      "epoch": 0.40816326530612246,
      "eval_loss": 1.771777629852295,
      "eval_runtime": 0.5899,
      "eval_samples_per_second": 18.648,
      "eval_steps_per_second": 10.172,
      "step": 10
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 1.439874291419983,
      "learning_rate": 0.0001913545457642601,
      "loss": 7.0544,
      "step": 12
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 1.7839900255203247,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.2674,
      "step": 15
    },
    {
      "epoch": 0.6122448979591837,
      "eval_loss": 1.4947052001953125,
      "eval_runtime": 0.5946,
      "eval_samples_per_second": 18.499,
      "eval_steps_per_second": 10.091,
      "step": 15
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 2.0306122303009033,
      "learning_rate": 8.954715367323468e-05,
      "loss": 5.9176,
      "step": 18
    },
    {
      "epoch": 0.8163265306122449,
      "eval_loss": 1.380954623222351,
      "eval_runtime": 0.5915,
      "eval_samples_per_second": 18.597,
      "eval_steps_per_second": 10.144,
      "step": 20
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.9328445196151733,
      "learning_rate": 3.308693936411421e-05,
      "loss": 5.5331,
      "step": 21
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 1.9156503677368164,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 5.4735,
      "step": 24
    },
    {
      "epoch": 1.0204081632653061,
      "eval_loss": 1.3589625358581543,
      "eval_runtime": 0.5912,
      "eval_samples_per_second": 18.607,
      "eval_steps_per_second": 10.149,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1502344327987200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}