{
  "best_metric": 0.31758370995521545,
  "best_model_checkpoint": "output_pipe/prom_core_notata/origin/checkpoint-600",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 2656,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15060240963855423,
      "grad_norm": 2.6122450828552246,
      "learning_rate": 2.9424405218726017e-05,
      "loss": 0.492,
      "step": 100
    },
    {
      "epoch": 0.30120481927710846,
      "grad_norm": 3.331883668899536,
      "learning_rate": 2.827321565617805e-05,
      "loss": 0.3811,
      "step": 200
    },
    {
      "epoch": 0.30120481927710846,
      "eval_accuracy": 0.844168079894479,
      "eval_f1": 0.8438998231922501,
      "eval_loss": 0.3547656834125519,
      "eval_matthews_correlation": 0.6941732916502827,
      "eval_precision": 0.8488631662773443,
      "eval_recall": 0.8453191719712101,
      "eval_runtime": 1.2495,
      "eval_samples_per_second": 4247.344,
      "eval_steps_per_second": 66.427,
      "step": 200
    },
    {
      "epoch": 0.45180722891566266,
      "grad_norm": 1.565757155418396,
      "learning_rate": 2.7122026093630083e-05,
      "loss": 0.3604,
      "step": 300
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 2.0966413021087646,
      "learning_rate": 2.597083653108212e-05,
      "loss": 0.3337,
      "step": 400
    },
    {
      "epoch": 0.6024096385542169,
      "eval_accuracy": 0.8618805351422649,
      "eval_f1": 0.8613509125193604,
      "eval_loss": 0.32256171107292175,
      "eval_matthews_correlation": 0.7257705478226737,
      "eval_precision": 0.8647857006053843,
      "eval_recall": 0.8609947478839368,
      "eval_runtime": 1.2685,
      "eval_samples_per_second": 4183.807,
      "eval_steps_per_second": 65.434,
      "step": 400
    },
    {
      "epoch": 0.7530120481927711,
      "grad_norm": 1.1383172273635864,
      "learning_rate": 2.481964696853415e-05,
      "loss": 0.3397,
      "step": 500
    },
    {
      "epoch": 0.9036144578313253,
      "grad_norm": 3.0221428871154785,
      "learning_rate": 2.3668457405986186e-05,
      "loss": 0.3159,
      "step": 600
    },
    {
      "epoch": 0.9036144578313253,
      "eval_accuracy": 0.866968155266629,
      "eval_f1": 0.8669429793472192,
      "eval_loss": 0.31758370995521545,
      "eval_matthews_correlation": 0.7358394132396464,
      "eval_precision": 0.8682598011305405,
      "eval_recall": 0.8675799261924673,
      "eval_runtime": 1.2509,
      "eval_samples_per_second": 4242.581,
      "eval_steps_per_second": 66.353,
      "step": 600
    },
    {
      "epoch": 1.0542168674698795,
      "grad_norm": 1.109787106513977,
      "learning_rate": 2.251726784343822e-05,
      "loss": 0.2776,
      "step": 700
    },
    {
      "epoch": 1.2048192771084336,
      "grad_norm": 3.197042465209961,
      "learning_rate": 2.1366078280890252e-05,
      "loss": 0.2057,
      "step": 800
    },
    {
      "epoch": 1.2048192771084336,
      "eval_accuracy": 0.866591294516676,
      "eval_f1": 0.8659984222336663,
      "eval_loss": 0.3502357602119446,
      "eval_matthews_correlation": 0.7358186808574204,
      "eval_precision": 0.8702189774301005,
      "eval_recall": 0.8656141122593988,
      "eval_runtime": 1.2536,
      "eval_samples_per_second": 4233.519,
      "eval_steps_per_second": 66.211,
      "step": 800
    },
    {
      "epoch": 1.355421686746988,
      "grad_norm": 2.543020486831665,
      "learning_rate": 2.021488871834229e-05,
      "loss": 0.2111,
      "step": 900
    },
    {
      "epoch": 1.5060240963855422,
      "grad_norm": 2.1183950901031494,
      "learning_rate": 1.9063699155794322e-05,
      "loss": 0.201,
      "step": 1000
    },
    {
      "epoch": 1.5060240963855422,
      "eval_accuracy": 0.8677218767665348,
      "eval_f1": 0.8677173631147045,
      "eval_loss": 0.33947083353996277,
      "eval_matthews_correlation": 0.7357722352510246,
      "eval_precision": 0.8678261795869671,
      "eval_recall": 0.8679460654310853,
      "eval_runtime": 1.2471,
      "eval_samples_per_second": 4255.356,
      "eval_steps_per_second": 66.553,
      "step": 1000
    },
    {
      "epoch": 1.6566265060240963,
      "grad_norm": 1.9308195114135742,
      "learning_rate": 1.7912509593246355e-05,
      "loss": 0.1937,
      "step": 1100
    },
    {
      "epoch": 1.8072289156626506,
      "grad_norm": 3.0469839572906494,
      "learning_rate": 1.6761320030698388e-05,
      "loss": 0.2008,
      "step": 1200
    },
    {
      "epoch": 1.8072289156626506,
      "eval_accuracy": 0.8679103071415112,
      "eval_f1": 0.867875610956949,
      "eval_loss": 0.3506290316581726,
      "eval_matthews_correlation": 0.7357734812824095,
      "eval_precision": 0.8678440441253761,
      "eval_recall": 0.8679294421129176,
      "eval_runtime": 1.2694,
      "eval_samples_per_second": 4180.735,
      "eval_steps_per_second": 65.386,
      "step": 1200
    },
    {
      "epoch": 1.9578313253012047,
      "grad_norm": 2.669092893600464,
      "learning_rate": 1.5610130468150424e-05,
      "loss": 0.2032,
      "step": 1300
    },
    {
      "epoch": 2.108433734939759,
      "grad_norm": 1.018779993057251,
      "learning_rate": 1.4458940905602456e-05,
      "loss": 0.0857,
      "step": 1400
    },
    {
      "epoch": 2.108433734939759,
      "eval_accuracy": 0.866968155266629,
      "eval_f1": 0.8669120125170288,
      "eval_loss": 0.5369625091552734,
      "eval_matthews_correlation": 0.7338250107809877,
      "eval_precision": 0.8669238704323894,
      "eval_recall": 0.8669011407006174,
      "eval_runtime": 1.25,
      "eval_samples_per_second": 4245.587,
      "eval_steps_per_second": 66.4,
      "step": 1400
    },
    {
      "epoch": 2.2590361445783134,
      "grad_norm": 0.7886415719985962,
      "learning_rate": 1.3307751343054489e-05,
      "loss": 0.0448,
      "step": 1500
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 1.834030032157898,
      "learning_rate": 1.2156561780506524e-05,
      "loss": 0.0436,
      "step": 1600
    },
    {
      "epoch": 2.4096385542168672,
      "eval_accuracy": 0.8639532692670059,
      "eval_f1": 0.8635816191675164,
      "eval_loss": 0.5898475646972656,
      "eval_matthews_correlation": 0.7289885454866504,
      "eval_precision": 0.8657342466278587,
      "eval_recall": 0.8632585028272428,
      "eval_runtime": 1.2478,
      "eval_samples_per_second": 4253.059,
      "eval_steps_per_second": 66.517,
      "step": 1600
    },
    {
      "epoch": 2.5602409638554215,
      "grad_norm": 4.06243896484375,
      "learning_rate": 1.1005372217958557e-05,
      "loss": 0.0421,
      "step": 1700
    },
    {
      "epoch": 2.710843373493976,
      "grad_norm": 1.1769578456878662,
      "learning_rate": 9.854182655410591e-06,
      "loss": 0.039,
      "step": 1800
    },
    {
      "epoch": 2.710843373493976,
      "eval_accuracy": 0.8662144337667232,
      "eval_f1": 0.8662079304389323,
      "eval_loss": 0.5943960547447205,
      "eval_matthews_correlation": 0.7327003607551781,
      "eval_precision": 0.8662847178923143,
      "eval_recall": 0.8664156545623336,
      "eval_runtime": 1.2548,
      "eval_samples_per_second": 4229.392,
      "eval_steps_per_second": 66.147,
      "step": 1800
    },
    {
      "epoch": 2.86144578313253,
      "grad_norm": 2.9796667098999023,
      "learning_rate": 8.702993092862626e-06,
      "loss": 0.0431,
      "step": 1900
    },
    {
      "epoch": 3.0120481927710845,
      "grad_norm": 0.06011148542165756,
      "learning_rate": 7.5518035303146585e-06,
      "loss": 0.0404,
      "step": 2000
    },
    {
      "epoch": 3.0120481927710845,
      "eval_accuracy": 0.861503674392312,
      "eval_f1": 0.8614255609018682,
      "eval_loss": 0.5846816897392273,
      "eval_matthews_correlation": 0.7228781268765005,
      "eval_precision": 0.8615070227953028,
      "eval_recall": 0.8613711168568119,
      "eval_runtime": 1.2512,
      "eval_samples_per_second": 4241.427,
      "eval_steps_per_second": 66.335,
      "step": 2000
    },
    {
      "epoch": 3.1626506024096384,
      "grad_norm": 2.1890785694122314,
      "learning_rate": 6.412125863392172e-06,
      "loss": 0.0103,
      "step": 2100
    },
    {
      "epoch": 3.3132530120481927,
      "grad_norm": 0.45505666732788086,
      "learning_rate": 5.260936300844206e-06,
      "loss": 0.0131,
      "step": 2200
    },
    {
      "epoch": 3.3132530120481927,
      "eval_accuracy": 0.8599962313925005,
      "eval_f1": 0.8599338477012316,
      "eval_loss": 0.6354616284370422,
      "eval_matthews_correlation": 0.719870690073612,
      "eval_precision": 0.8599553933898891,
      "eval_recall": 0.8599152978003515,
      "eval_runtime": 1.255,
      "eval_samples_per_second": 4228.711,
      "eval_steps_per_second": 66.136,
      "step": 2200
    },
    {
      "epoch": 3.463855421686747,
      "grad_norm": 0.060754936188459396,
      "learning_rate": 4.109746738296239e-06,
      "loss": 0.01,
      "step": 2300
    },
    {
      "epoch": 3.6144578313253013,
      "grad_norm": 1.6662099361419678,
      "learning_rate": 2.9585571757482733e-06,
      "loss": 0.0096,
      "step": 2400
    },
    {
      "epoch": 3.6144578313253013,
      "eval_accuracy": 0.8605615225174298,
      "eval_f1": 0.8604790858249838,
      "eval_loss": 0.6781471371650696,
      "eval_matthews_correlation": 0.7209934067313212,
      "eval_precision": 0.8605760169206037,
      "eval_recall": 0.8604174072568029,
      "eval_runtime": 1.2679,
      "eval_samples_per_second": 4185.581,
      "eval_steps_per_second": 65.461,
      "step": 2400
    },
    {
      "epoch": 3.765060240963855,
      "grad_norm": 0.031053327023983,
      "learning_rate": 1.807367613200307e-06,
      "loss": 0.0097,
      "step": 2500
    },
    {
      "epoch": 3.9156626506024095,
      "grad_norm": 1.6371121406555176,
      "learning_rate": 6.561780506523408e-07,
      "loss": 0.0075,
      "step": 2600
    },
    {
      "epoch": 3.9156626506024095,
      "eval_accuracy": 0.8620689655172413,
      "eval_f1": 0.8620189892409078,
      "eval_loss": 0.7003814578056335,
      "eval_matthews_correlation": 0.7240389585546707,
      "eval_precision": 0.8620090897337722,
      "eval_recall": 0.862029869119075,
      "eval_runtime": 1.2529,
      "eval_samples_per_second": 4235.844,
      "eval_steps_per_second": 66.247,
      "step": 2600
    },
    {
      "epoch": 4.0,
      "step": 2656,
      "total_flos": 8449435771093920.0,
      "train_loss": 0.15504802793758102,
      "train_runtime": 245.9871,
      "train_samples_per_second": 690.313,
      "train_steps_per_second": 10.797
    }
  ],
  "logging_steps": 100,
  "max_steps": 2656,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8449435771093920.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}