{
  "best_metric": 0.21111078560352325,
  "best_model_checkpoint": "plantuml-code-generation/checkpoint-200",
  "epoch": 9.30232558139535,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 59.56515884399414,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 7.4833,
      "step": 10
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 0.5965571999549866,
      "learning_rate": 7.2e-05,
      "loss": 1.2974,
      "step": 20
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.3513571321964264,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.6516,
      "step": 30
    },
    {
      "epoch": 1.2403100775193798,
      "grad_norm": 0.5511578917503357,
      "learning_rate": 0.000152,
      "loss": 0.5225,
      "step": 40
    },
    {
      "epoch": 1.550387596899225,
      "grad_norm": 0.6557414531707764,
      "learning_rate": 0.000192,
      "loss": 0.4245,
      "step": 50
    },
    {
      "epoch": 1.550387596899225,
      "eval_bleu_score": 66.6551,
      "eval_levenshtein_similarity": 0.6932,
      "eval_loss": 0.3688744604587555,
      "eval_runtime": 32.7473,
      "eval_samples_per_second": 7.879,
      "eval_steps_per_second": 1.008,
      "eval_structural_distance": 0.5696,
      "step": 50
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 0.278952032327652,
      "learning_rate": 0.00019360000000000002,
      "loss": 0.3261,
      "step": 60
    },
    {
      "epoch": 2.1705426356589146,
      "grad_norm": 0.31165850162506104,
      "learning_rate": 0.0001856,
      "loss": 0.2961,
      "step": 70
    },
    {
      "epoch": 2.4806201550387597,
      "grad_norm": 0.268346905708313,
      "learning_rate": 0.0001776,
      "loss": 0.2914,
      "step": 80
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 0.32657572627067566,
      "learning_rate": 0.0001696,
      "loss": 0.2602,
      "step": 90
    },
    {
      "epoch": 3.10077519379845,
      "grad_norm": 0.3043263554573059,
      "learning_rate": 0.00016160000000000002,
      "loss": 0.2299,
      "step": 100
    },
    {
      "epoch": 3.10077519379845,
      "eval_bleu_score": 73.7774,
      "eval_levenshtein_similarity": 0.7695,
      "eval_loss": 0.25513702630996704,
      "eval_runtime": 33.0142,
      "eval_samples_per_second": 7.815,
      "eval_steps_per_second": 1.0,
      "eval_structural_distance": 0.4371,
      "step": 100
    },
    {
      "epoch": 3.4108527131782944,
      "grad_norm": 0.2804100215435028,
      "learning_rate": 0.00015360000000000002,
      "loss": 0.218,
      "step": 110
    },
    {
      "epoch": 3.7209302325581395,
      "grad_norm": 0.3100726008415222,
      "learning_rate": 0.00014560000000000002,
      "loss": 0.2107,
      "step": 120
    },
    {
      "epoch": 4.0310077519379846,
      "grad_norm": 0.3075805902481079,
      "learning_rate": 0.00013759999999999998,
      "loss": 0.2051,
      "step": 130
    },
    {
      "epoch": 4.341085271317829,
      "grad_norm": 0.2779467701911926,
      "learning_rate": 0.0001296,
      "loss": 0.1664,
      "step": 140
    },
    {
      "epoch": 4.651162790697675,
      "grad_norm": 0.3230448365211487,
      "learning_rate": 0.0001216,
      "loss": 0.1643,
      "step": 150
    },
    {
      "epoch": 4.651162790697675,
      "eval_bleu_score": 76.5742,
      "eval_levenshtein_similarity": 0.7976,
      "eval_loss": 0.21526312828063965,
      "eval_runtime": 33.1871,
      "eval_samples_per_second": 7.774,
      "eval_steps_per_second": 0.994,
      "eval_structural_distance": 0.3959,
      "step": 150
    },
    {
      "epoch": 4.961240310077519,
      "grad_norm": 0.40676575899124146,
      "learning_rate": 0.0001136,
      "loss": 0.1852,
      "step": 160
    },
    {
      "epoch": 5.271317829457364,
      "grad_norm": 0.45079299807548523,
      "learning_rate": 0.0001056,
      "loss": 0.1434,
      "step": 170
    },
    {
      "epoch": 5.5813953488372094,
      "grad_norm": 0.37738654017448425,
      "learning_rate": 9.76e-05,
      "loss": 0.1404,
      "step": 180
    },
    {
      "epoch": 5.891472868217054,
      "grad_norm": 0.333663672208786,
      "learning_rate": 8.960000000000001e-05,
      "loss": 0.1435,
      "step": 190
    },
    {
      "epoch": 6.2015503875969,
      "grad_norm": 0.5026473999023438,
      "learning_rate": 8.16e-05,
      "loss": 0.1302,
      "step": 200
    },
    {
      "epoch": 6.2015503875969,
      "eval_bleu_score": 78.0329,
      "eval_levenshtein_similarity": 0.81,
      "eval_loss": 0.21111078560352325,
      "eval_runtime": 33.2323,
      "eval_samples_per_second": 7.764,
      "eval_steps_per_second": 0.993,
      "eval_structural_distance": 0.3777,
      "step": 200
    },
    {
      "epoch": 6.511627906976744,
      "grad_norm": 0.40623053908348083,
      "learning_rate": 7.36e-05,
      "loss": 0.1165,
      "step": 210
    },
    {
      "epoch": 6.821705426356589,
      "grad_norm": 0.48197492957115173,
      "learning_rate": 6.560000000000001e-05,
      "loss": 0.1335,
      "step": 220
    },
    {
      "epoch": 7.131782945736434,
      "grad_norm": 0.34860748052597046,
      "learning_rate": 5.76e-05,
      "loss": 0.1117,
      "step": 230
    },
    {
      "epoch": 7.441860465116279,
      "grad_norm": 0.42669615149497986,
      "learning_rate": 4.96e-05,
      "loss": 0.0981,
      "step": 240
    },
    {
      "epoch": 7.751937984496124,
      "grad_norm": 0.3821258544921875,
      "learning_rate": 4.16e-05,
      "loss": 0.0957,
      "step": 250
    },
    {
      "epoch": 7.751937984496124,
      "eval_bleu_score": 79.3173,
      "eval_levenshtein_similarity": 0.8195,
      "eval_loss": 0.2125212550163269,
      "eval_runtime": 33.1788,
      "eval_samples_per_second": 7.776,
      "eval_steps_per_second": 0.995,
      "eval_structural_distance": 0.3606,
      "step": 250
    },
    {
      "epoch": 8.062015503875969,
      "grad_norm": 0.32864922285079956,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.108,
      "step": 260
    },
    {
      "epoch": 8.372093023255815,
      "grad_norm": 0.5244048237800598,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 0.101,
      "step": 270
    },
    {
      "epoch": 8.682170542635658,
      "grad_norm": 0.3731113374233246,
      "learning_rate": 1.76e-05,
      "loss": 0.0852,
      "step": 280
    },
    {
      "epoch": 8.992248062015504,
      "grad_norm": 0.3745462894439697,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.0847,
      "step": 290
    },
    {
      "epoch": 9.30232558139535,
      "grad_norm": 0.4434490501880646,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0799,
      "step": 300
    },
    {
      "epoch": 9.30232558139535,
      "eval_bleu_score": 79.4831,
      "eval_levenshtein_similarity": 0.8236,
      "eval_loss": 0.2191912978887558,
      "eval_runtime": 33.1887,
      "eval_samples_per_second": 7.774,
      "eval_steps_per_second": 0.994,
      "eval_structural_distance": 0.3648,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.095129907209175e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}