{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0443213296398892,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00221606648199446,
      "grad_norm": 0.7119107246398926,
      "learning_rate": 2e-05,
      "loss": 6.936,
      "step": 1
    },
    {
      "epoch": 0.00221606648199446,
      "eval_loss": 6.9400315284729,
      "eval_runtime": 1.9291,
      "eval_samples_per_second": 98.493,
      "eval_steps_per_second": 49.247,
      "step": 1
    },
    {
      "epoch": 0.00443213296398892,
      "grad_norm": 0.8452966213226318,
      "learning_rate": 4e-05,
      "loss": 6.9341,
      "step": 2
    },
    {
      "epoch": 0.006648199445983379,
      "grad_norm": 0.7140179872512817,
      "learning_rate": 6e-05,
      "loss": 6.9459,
      "step": 3
    },
    {
      "epoch": 0.00886426592797784,
      "grad_norm": 0.7129480838775635,
      "learning_rate": 8e-05,
      "loss": 6.9329,
      "step": 4
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.6473819017410278,
      "learning_rate": 0.0001,
      "loss": 6.9422,
      "step": 5
    },
    {
      "epoch": 0.0110803324099723,
      "eval_loss": 6.934447765350342,
      "eval_runtime": 0.7627,
      "eval_samples_per_second": 249.116,
      "eval_steps_per_second": 124.558,
      "step": 5
    },
    {
      "epoch": 0.013296398891966758,
      "grad_norm": 0.7442740797996521,
      "learning_rate": 0.00012,
      "loss": 6.9391,
      "step": 6
    },
    {
      "epoch": 0.01551246537396122,
      "grad_norm": 0.7291401028633118,
      "learning_rate": 0.00014,
      "loss": 6.9351,
      "step": 7
    },
    {
      "epoch": 0.01772853185595568,
      "grad_norm": 0.825867235660553,
      "learning_rate": 0.00016,
      "loss": 6.9273,
      "step": 8
    },
    {
      "epoch": 0.019944598337950138,
      "grad_norm": 0.9600035548210144,
      "learning_rate": 0.00018,
      "loss": 6.9133,
      "step": 9
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 0.7621235251426697,
      "learning_rate": 0.0002,
      "loss": 6.9247,
      "step": 10
    },
    {
      "epoch": 0.0221606648199446,
      "eval_loss": 6.914420127868652,
      "eval_runtime": 0.7613,
      "eval_samples_per_second": 249.558,
      "eval_steps_per_second": 124.779,
      "step": 10
    },
    {
      "epoch": 0.02437673130193906,
      "grad_norm": 0.8293081521987915,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.9267,
      "step": 11
    },
    {
      "epoch": 0.026592797783933517,
      "grad_norm": 0.7078577280044556,
      "learning_rate": 0.00018090169943749476,
      "loss": 6.9166,
      "step": 12
    },
    {
      "epoch": 0.028808864265927978,
      "grad_norm": 0.7808763980865479,
      "learning_rate": 0.00015877852522924732,
      "loss": 6.897,
      "step": 13
    },
    {
      "epoch": 0.03102493074792244,
      "grad_norm": 0.9316994547843933,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.889,
      "step": 14
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 0.7430341839790344,
      "learning_rate": 0.0001,
      "loss": 6.9076,
      "step": 15
    },
    {
      "epoch": 0.0332409972299169,
      "eval_loss": 6.8888044357299805,
      "eval_runtime": 0.7701,
      "eval_samples_per_second": 246.716,
      "eval_steps_per_second": 123.358,
      "step": 15
    },
    {
      "epoch": 0.03545706371191136,
      "grad_norm": 0.6504232287406921,
      "learning_rate": 6.909830056250527e-05,
      "loss": 6.9152,
      "step": 16
    },
    {
      "epoch": 0.037673130193905814,
      "grad_norm": 0.791231632232666,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.8909,
      "step": 17
    },
    {
      "epoch": 0.039889196675900275,
      "grad_norm": 0.7693294882774353,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 6.883,
      "step": 18
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.7056183815002441,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 6.8989,
      "step": 19
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 0.7791154384613037,
      "learning_rate": 0.0,
      "loss": 6.8869,
      "step": 20
    },
    {
      "epoch": 0.0443213296398892,
      "eval_loss": 6.881771564483643,
      "eval_runtime": 0.7678,
      "eval_samples_per_second": 247.475,
      "eval_steps_per_second": 123.737,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 125226885120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}