{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001493521848980049,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.97840616326683e-05,
      "eval_loss": 1.939439058303833,
      "eval_runtime": 1047.3292,
      "eval_samples_per_second": 8.076,
      "eval_steps_per_second": 4.038,
      "step": 1
    },
    {
      "epoch": 0.0001493521848980049,
      "grad_norm": 0.8044071793556213,
      "learning_rate": 6e-05,
      "loss": 8.1195,
      "step": 3
    },
    {
      "epoch": 0.0002489203081633415,
      "eval_loss": 1.8925161361694336,
      "eval_runtime": 1051.6101,
      "eval_samples_per_second": 8.043,
      "eval_steps_per_second": 4.021,
      "step": 5
    },
    {
      "epoch": 0.0002987043697960098,
      "grad_norm": 1.4592093229293823,
      "learning_rate": 0.00012,
      "loss": 7.8469,
      "step": 6
    },
    {
      "epoch": 0.0004480565546940147,
      "grad_norm": 1.912136435508728,
      "learning_rate": 0.00018,
      "loss": 7.073,
      "step": 9
    },
    {
      "epoch": 0.000497840616326683,
      "eval_loss": 1.679373860359192,
      "eval_runtime": 1050.8718,
      "eval_samples_per_second": 8.049,
      "eval_steps_per_second": 4.024,
      "step": 10
    },
    {
      "epoch": 0.0005974087395920196,
      "grad_norm": 0.7066208720207214,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.7109,
      "step": 12
    },
    {
      "epoch": 0.0007467609244900245,
      "grad_norm": 0.9704435467720032,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.3098,
      "step": 15
    },
    {
      "epoch": 0.0007467609244900245,
      "eval_loss": 1.6141732931137085,
      "eval_runtime": 1051.2981,
      "eval_samples_per_second": 8.045,
      "eval_steps_per_second": 4.023,
      "step": 15
    },
    {
      "epoch": 0.0008961131093880294,
      "grad_norm": 1.287255048751831,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.4166,
      "step": 18
    },
    {
      "epoch": 0.000995681232653366,
      "eval_loss": 1.5906931161880493,
      "eval_runtime": 1051.8387,
      "eval_samples_per_second": 8.041,
      "eval_steps_per_second": 4.021,
      "step": 20
    },
    {
      "epoch": 0.0010454652942860343,
      "grad_norm": 1.2580655813217163,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.9454,
      "step": 21
    },
    {
      "epoch": 0.0011948174791840392,
      "grad_norm": 1.1114526987075806,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.4871,
      "step": 24
    },
    {
      "epoch": 0.0012446015408167075,
      "eval_loss": 1.5829719305038452,
      "eval_runtime": 1051.6343,
      "eval_samples_per_second": 8.043,
      "eval_steps_per_second": 4.021,
      "step": 25
    },
    {
      "epoch": 0.0013441696640820442,
      "grad_norm": 0.7479458451271057,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 6.6254,
      "step": 27
    },
    {
      "epoch": 0.001493521848980049,
      "grad_norm": 1.2524772882461548,
      "learning_rate": 0.0,
      "loss": 6.7665,
      "step": 30
    },
    {
      "epoch": 0.001493521848980049,
      "eval_loss": 1.5814976692199707,
      "eval_runtime": 1052.357,
      "eval_samples_per_second": 8.037,
      "eval_steps_per_second": 4.019,
      "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": 1.920218563608576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}