{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0033685156074556477,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011228385358185493,
      "eval_loss": 1.052726149559021,
      "eval_runtime": 175.2285,
      "eval_samples_per_second": 21.401,
      "eval_steps_per_second": 10.7,
      "step": 1
    },
    {
      "epoch": 0.00033685156074556477,
      "grad_norm": 0.9176195859909058,
      "learning_rate": 6e-05,
      "loss": 1.0446,
      "step": 3
    },
    {
      "epoch": 0.0006737031214911295,
      "grad_norm": 0.6426594257354736,
      "learning_rate": 0.00012,
      "loss": 0.9484,
      "step": 6
    },
    {
      "epoch": 0.0008982708286548395,
      "eval_loss": 0.9533997178077698,
      "eval_runtime": 175.3024,
      "eval_samples_per_second": 21.392,
      "eval_steps_per_second": 10.696,
      "step": 8
    },
    {
      "epoch": 0.0010105546822366943,
      "grad_norm": 0.5503889918327332,
      "learning_rate": 0.00018,
      "loss": 0.9387,
      "step": 9
    },
    {
      "epoch": 0.001347406242982259,
      "grad_norm": 0.563830554485321,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.908,
      "step": 12
    },
    {
      "epoch": 0.0016842578037278239,
      "grad_norm": 0.4135178029537201,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.8588,
      "step": 15
    },
    {
      "epoch": 0.001796541657309679,
      "eval_loss": 0.866192102432251,
      "eval_runtime": 173.4145,
      "eval_samples_per_second": 21.624,
      "eval_steps_per_second": 10.812,
      "step": 16
    },
    {
      "epoch": 0.0020211093644733886,
      "grad_norm": 0.4025917947292328,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9259,
      "step": 18
    },
    {
      "epoch": 0.0023579609252189536,
      "grad_norm": 0.3587353825569153,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.8104,
      "step": 21
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 0.32133132219314575,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.8045,
      "step": 24
    },
    {
      "epoch": 0.002694812485964518,
      "eval_loss": 0.8413432240486145,
      "eval_runtime": 173.551,
      "eval_samples_per_second": 21.607,
      "eval_steps_per_second": 10.804,
      "step": 24
    },
    {
      "epoch": 0.003031664046710083,
      "grad_norm": 0.38765057921409607,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.8635,
      "step": 27
    },
    {
      "epoch": 0.0033685156074556477,
      "grad_norm": 0.3531164228916168,
      "learning_rate": 0.0,
      "loss": 0.8456,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2290719960072192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}