{
  "best_global_step": 196,
  "best_metric": 1.4676804542541504,
  "best_model_checkpoint": "./models/codet5-sequenced/checkpoint-196",
  "epoch": 13.067796610169491,
  "eval_steps": 7,
  "global_step": 196,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 35.061439514160156,
      "learning_rate": 0.0,
      "loss": 6.9968,
      "step": 1
    },
    {
      "epoch": 0.4745762711864407,
      "eval_loss": 3.7553770542144775,
      "eval_runtime": 31.376,
      "eval_samples_per_second": 4.143,
      "eval_steps_per_second": 0.223,
      "step": 7
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 2.471144676208496,
      "learning_rate": 0.00012857142857142855,
      "loss": 4.9711,
      "step": 10
    },
    {
      "epoch": 0.9491525423728814,
      "eval_loss": 2.576092481613159,
      "eval_runtime": 32.5287,
      "eval_samples_per_second": 3.996,
      "eval_steps_per_second": 0.215,
      "step": 14
    },
    {
      "epoch": 1.3389830508474576,
      "grad_norm": 0.970221757888794,
      "learning_rate": 0.0002714285714285714,
      "loss": 2.7955,
      "step": 20
    },
    {
      "epoch": 1.4067796610169492,
      "eval_loss": 2.0272090435028076,
      "eval_runtime": 32.8232,
      "eval_samples_per_second": 3.961,
      "eval_steps_per_second": 0.213,
      "step": 21
    },
    {
      "epoch": 1.8813559322033897,
      "eval_loss": 1.794872760772705,
      "eval_runtime": 32.1072,
      "eval_samples_per_second": 4.049,
      "eval_steps_per_second": 0.218,
      "step": 28
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.253476619720459,
      "learning_rate": 0.00028823529411764703,
      "loss": 1.9943,
      "step": 30
    },
    {
      "epoch": 2.3389830508474576,
      "eval_loss": 1.6869820356369019,
      "eval_runtime": 33.6053,
      "eval_samples_per_second": 3.868,
      "eval_steps_per_second": 0.208,
      "step": 35
    },
    {
      "epoch": 2.6779661016949152,
      "grad_norm": 0.17588205635547638,
      "learning_rate": 0.00027352941176470583,
      "loss": 1.7476,
      "step": 40
    },
    {
      "epoch": 2.8135593220338984,
      "eval_loss": 1.633076548576355,
      "eval_runtime": 31.3432,
      "eval_samples_per_second": 4.148,
      "eval_steps_per_second": 0.223,
      "step": 42
    },
    {
      "epoch": 3.2711864406779663,
      "eval_loss": 1.595025658607483,
      "eval_runtime": 32.6382,
      "eval_samples_per_second": 3.983,
      "eval_steps_per_second": 0.214,
      "step": 49
    },
    {
      "epoch": 3.3389830508474576,
      "grad_norm": 0.1354854702949524,
      "learning_rate": 0.0002588235294117647,
      "loss": 1.6567,
      "step": 50
    },
    {
      "epoch": 3.7457627118644066,
      "eval_loss": 1.5682227611541748,
      "eval_runtime": 32.3796,
      "eval_samples_per_second": 4.015,
      "eval_steps_per_second": 0.216,
      "step": 56
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.14623650908470154,
      "learning_rate": 0.0002441176470588235,
      "loss": 1.6035,
      "step": 60
    },
    {
      "epoch": 4.203389830508475,
      "eval_loss": 1.5545539855957031,
      "eval_runtime": 32.9074,
      "eval_samples_per_second": 3.95,
      "eval_steps_per_second": 0.213,
      "step": 63
    },
    {
      "epoch": 4.677966101694915,
      "grad_norm": 0.08996161818504333,
      "learning_rate": 0.0002294117647058823,
      "loss": 1.5737,
      "step": 70
    },
    {
      "epoch": 4.677966101694915,
      "eval_loss": 1.5401841402053833,
      "eval_runtime": 36.4472,
      "eval_samples_per_second": 3.567,
      "eval_steps_per_second": 0.192,
      "step": 70
    },
    {
      "epoch": 5.135593220338983,
      "eval_loss": 1.5304237604141235,
      "eval_runtime": 33.0897,
      "eval_samples_per_second": 3.929,
      "eval_steps_per_second": 0.212,
      "step": 77
    },
    {
      "epoch": 5.338983050847458,
      "grad_norm": 0.12378664314746857,
      "learning_rate": 0.00021470588235294116,
      "loss": 1.5575,
      "step": 80
    },
    {
      "epoch": 5.610169491525424,
      "eval_loss": 1.5213029384613037,
      "eval_runtime": 31.2672,
      "eval_samples_per_second": 4.158,
      "eval_steps_per_second": 0.224,
      "step": 84
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1171395406126976,
      "learning_rate": 0.00019999999999999998,
      "loss": 1.5386,
      "step": 90
    },
    {
      "epoch": 6.067796610169491,
      "eval_loss": 1.5130056142807007,
      "eval_runtime": 33.1459,
      "eval_samples_per_second": 3.922,
      "eval_steps_per_second": 0.211,
      "step": 91
    },
    {
      "epoch": 6.5423728813559325,
      "eval_loss": 1.5062706470489502,
      "eval_runtime": 32.4291,
      "eval_samples_per_second": 4.009,
      "eval_steps_per_second": 0.216,
      "step": 98
    },
    {
      "epoch": 6.677966101694915,
      "grad_norm": 0.06857075542211533,
      "learning_rate": 0.0001852941176470588,
      "loss": 1.5288,
      "step": 100
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.5011202096939087,
      "eval_runtime": 32.7571,
      "eval_samples_per_second": 3.969,
      "eval_steps_per_second": 0.214,
      "step": 105
    },
    {
      "epoch": 7.338983050847458,
      "grad_norm": 0.07266195118427277,
      "learning_rate": 0.00017058823529411763,
      "loss": 1.5196,
      "step": 110
    },
    {
      "epoch": 7.47457627118644,
      "eval_loss": 1.49434232711792,
      "eval_runtime": 33.5153,
      "eval_samples_per_second": 3.879,
      "eval_steps_per_second": 0.209,
      "step": 112
    },
    {
      "epoch": 7.9491525423728815,
      "eval_loss": 1.493066430091858,
      "eval_runtime": 32.6462,
      "eval_samples_per_second": 3.982,
      "eval_steps_per_second": 0.214,
      "step": 119
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.09790726006031036,
      "learning_rate": 0.00015588235294117646,
      "loss": 1.5098,
      "step": 120
    },
    {
      "epoch": 8.40677966101695,
      "eval_loss": 1.4890639781951904,
      "eval_runtime": 33.9906,
      "eval_samples_per_second": 3.825,
      "eval_steps_per_second": 0.206,
      "step": 126
    },
    {
      "epoch": 8.677966101694915,
      "grad_norm": 0.08605582267045975,
      "learning_rate": 0.00014117647058823528,
      "loss": 1.504,
      "step": 130
    },
    {
      "epoch": 8.88135593220339,
      "eval_loss": 1.4857922792434692,
      "eval_runtime": 33.6557,
      "eval_samples_per_second": 3.863,
      "eval_steps_per_second": 0.208,
      "step": 133
    },
    {
      "epoch": 9.338983050847457,
      "grad_norm": 0.07982663810253143,
      "learning_rate": 0.0001264705882352941,
      "loss": 1.501,
      "step": 140
    },
    {
      "epoch": 9.338983050847457,
      "eval_loss": 1.4824906587600708,
      "eval_runtime": 33.5066,
      "eval_samples_per_second": 3.88,
      "eval_steps_per_second": 0.209,
      "step": 140
    },
    {
      "epoch": 9.813559322033898,
      "eval_loss": 1.478973150253296,
      "eval_runtime": 33.5484,
      "eval_samples_per_second": 3.875,
      "eval_steps_per_second": 0.209,
      "step": 147
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.07402677834033966,
      "learning_rate": 0.00011176470588235293,
      "loss": 1.4941,
      "step": 150
    },
    {
      "epoch": 10.271186440677965,
      "eval_loss": 1.476096749305725,
      "eval_runtime": 33.087,
      "eval_samples_per_second": 3.929,
      "eval_steps_per_second": 0.212,
      "step": 154
    },
    {
      "epoch": 10.677966101694915,
      "grad_norm": 0.0733569785952568,
      "learning_rate": 9.705882352941176e-05,
      "loss": 1.4894,
      "step": 160
    },
    {
      "epoch": 10.745762711864407,
      "eval_loss": 1.4757354259490967,
      "eval_runtime": 33.5743,
      "eval_samples_per_second": 3.872,
      "eval_steps_per_second": 0.208,
      "step": 161
    },
    {
      "epoch": 11.203389830508474,
      "eval_loss": 1.4727975130081177,
      "eval_runtime": 33.5918,
      "eval_samples_per_second": 3.87,
      "eval_steps_per_second": 0.208,
      "step": 168
    },
    {
      "epoch": 11.338983050847457,
      "grad_norm": 0.07810712605714798,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.4887,
      "step": 170
    },
    {
      "epoch": 11.677966101694915,
      "eval_loss": 1.4703751802444458,
      "eval_runtime": 33.6902,
      "eval_samples_per_second": 3.859,
      "eval_steps_per_second": 0.208,
      "step": 175
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.0885886400938034,
      "learning_rate": 6.76470588235294e-05,
      "loss": 1.4844,
      "step": 180
    },
    {
      "epoch": 12.135593220338983,
      "eval_loss": 1.4694443941116333,
      "eval_runtime": 33.5918,
      "eval_samples_per_second": 3.87,
      "eval_steps_per_second": 0.208,
      "step": 182
    },
    {
      "epoch": 12.610169491525424,
      "eval_loss": 1.47074556350708,
      "eval_runtime": 33.0341,
      "eval_samples_per_second": 3.935,
      "eval_steps_per_second": 0.212,
      "step": 189
    },
    {
      "epoch": 12.677966101694915,
      "grad_norm": 0.07929002493619919,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.48,
      "step": 190
    },
    {
      "epoch": 13.067796610169491,
      "eval_loss": 1.4676804542541504,
      "eval_runtime": 33.3819,
      "eval_samples_per_second": 3.894,
      "eval_steps_per_second": 0.21,
      "step": 196
    }
  ],
  "logging_steps": 10,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 28,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2586720180633600.0,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}