{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9826435246995995,
  "eval_steps": 3,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06408544726301736,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.7532,
      "step": 3
    },
    {
      "epoch": 0.12817089452603472,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.7468,
      "step": 6
    },
    {
      "epoch": 0.19225634178905207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.7691,
      "step": 9
    },
    {
      "epoch": 0.25634178905206945,
      "grad_norm": 0.14000944793224335,
      "learning_rate": 0.002,
      "loss": 0.7389,
      "step": 12
    },
    {
      "epoch": 0.3204272363150868,
      "grad_norm": 0.11092425882816315,
      "learning_rate": 0.0011547005383792518,
      "loss": 0.6552,
      "step": 15
    },
    {
      "epoch": 0.38451268357810414,
      "grad_norm": 0.2066473811864853,
      "learning_rate": 0.0008944271909999159,
      "loss": 0.6433,
      "step": 18
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.14052653312683105,
      "learning_rate": 0.0007071067811865475,
      "loss": 0.6242,
      "step": 21
    },
    {
      "epoch": 0.5126835781041389,
      "grad_norm": 0.17980274558067322,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.6288,
      "step": 24
    },
    {
      "epoch": 0.5767690253671562,
      "grad_norm": 6.837588310241699,
      "learning_rate": 0.0006324555320336759,
      "loss": 0.623,
      "step": 27
    },
    {
      "epoch": 0.6408544726301736,
      "grad_norm": 0.22490961849689484,
      "learning_rate": 0.0005547001962252292,
      "loss": 0.5772,
      "step": 30
    },
    {
      "epoch": 0.7049399198931909,
      "grad_norm": 0.17361482977867126,
      "learning_rate": 0.0005,
      "loss": 0.5786,
      "step": 33
    },
    {
      "epoch": 0.7690253671562083,
      "grad_norm": 0.17430518567562103,
      "learning_rate": 0.0004588314677411235,
      "loss": 0.5628,
      "step": 36
    },
    {
      "epoch": 0.8331108144192256,
      "grad_norm": 0.13419198989868164,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.5796,
      "step": 39
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.11218661814928055,
      "learning_rate": 0.0004,
      "loss": 0.5466,
      "step": 42
    },
    {
      "epoch": 0.9612817089452603,
      "grad_norm": 0.1503124088048935,
      "learning_rate": 0.0003779644730092272,
      "loss": 0.5637,
      "step": 45
    },
    {
      "epoch": 0.9826435246995995,
      "step": 46,
      "total_flos": 4.671973340489974e+17,
      "train_loss": 0.6387862938901653,
      "train_runtime": 498.0427,
      "train_samples_per_second": 12.023,
      "train_steps_per_second": 0.092
    }
  ],
  "logging_steps": 3,
  "max_steps": 46,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.671973340489974e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}