{
  "best_global_step": 2049,
  "best_metric": 0.6427525622254758,
  "best_model_checkpoint": "./saved_models/cbert/checkpoint-2049",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 3415,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14641288433382138,
      "grad_norm": 3.022106647491455,
      "learning_rate": 1.942020497803807e-05,
      "loss": 0.6936,
      "step": 100
    },
    {
      "epoch": 0.29282576866764276,
      "grad_norm": 1.8588309288024902,
      "learning_rate": 1.8834553440702785e-05,
      "loss": 0.6835,
      "step": 200
    },
    {
      "epoch": 0.43923865300146414,
      "grad_norm": 3.637296438217163,
      "learning_rate": 1.8248901903367496e-05,
      "loss": 0.6754,
      "step": 300
    },
    {
      "epoch": 0.5856515373352855,
      "grad_norm": 1.5142912864685059,
      "learning_rate": 1.766325036603221e-05,
      "loss": 0.6739,
      "step": 400
    },
    {
      "epoch": 0.7320644216691069,
      "grad_norm": 4.135972023010254,
      "learning_rate": 1.7077598828696925e-05,
      "loss": 0.6699,
      "step": 500
    },
    {
      "epoch": 0.8784773060029283,
      "grad_norm": 2.758687734603882,
      "learning_rate": 1.649194729136164e-05,
      "loss": 0.6775,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5995607613469985,
      "eval_loss": 0.6492753028869629,
      "eval_runtime": 1.5709,
      "eval_samples_per_second": 1739.163,
      "eval_steps_per_second": 54.747,
      "step": 683
    },
    {
      "epoch": 1.0248901903367496,
      "grad_norm": 4.188994407653809,
      "learning_rate": 1.5906295754026355e-05,
      "loss": 0.6622,
      "step": 700
    },
    {
      "epoch": 1.171303074670571,
      "grad_norm": 2.755507230758667,
      "learning_rate": 1.532064421669107e-05,
      "loss": 0.6485,
      "step": 800
    },
    {
      "epoch": 1.3177159590043923,
      "grad_norm": 4.434422016143799,
      "learning_rate": 1.4734992679355784e-05,
      "loss": 0.6422,
      "step": 900
    },
    {
      "epoch": 1.4641288433382138,
      "grad_norm": 3.1107141971588135,
      "learning_rate": 1.4149341142020499e-05,
      "loss": 0.6436,
      "step": 1000
    },
    {
      "epoch": 1.610541727672035,
      "grad_norm": 4.113313674926758,
      "learning_rate": 1.3563689604685213e-05,
      "loss": 0.6308,
      "step": 1100
    },
    {
      "epoch": 1.7569546120058566,
      "grad_norm": 5.160773754119873,
      "learning_rate": 1.2978038067349928e-05,
      "loss": 0.6223,
      "step": 1200
    },
    {
      "epoch": 1.903367496339678,
      "grad_norm": 2.9103806018829346,
      "learning_rate": 1.2392386530014641e-05,
      "loss": 0.6312,
      "step": 1300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6317715959004392,
      "eval_loss": 0.6276857256889343,
      "eval_runtime": 1.5723,
      "eval_samples_per_second": 1737.632,
      "eval_steps_per_second": 54.699,
      "step": 1366
    },
    {
      "epoch": 2.049780380673499,
      "grad_norm": 4.584695339202881,
      "learning_rate": 1.1806734992679356e-05,
      "loss": 0.6105,
      "step": 1400
    },
    {
      "epoch": 2.1961932650073206,
      "grad_norm": 11.84752368927002,
      "learning_rate": 1.122108345534407e-05,
      "loss": 0.5812,
      "step": 1500
    },
    {
      "epoch": 2.342606149341142,
      "grad_norm": 4.095500946044922,
      "learning_rate": 1.0635431918008785e-05,
      "loss": 0.589,
      "step": 1600
    },
    {
      "epoch": 2.4890190336749636,
      "grad_norm": 4.87593936920166,
      "learning_rate": 1.00497803806735e-05,
      "loss": 0.5835,
      "step": 1700
    },
    {
      "epoch": 2.6354319180087846,
      "grad_norm": 4.864409446716309,
      "learning_rate": 9.464128843338215e-06,
      "loss": 0.5877,
      "step": 1800
    },
    {
      "epoch": 2.781844802342606,
      "grad_norm": 5.729854583740234,
      "learning_rate": 8.87847730600293e-06,
      "loss": 0.5911,
      "step": 1900
    },
    {
      "epoch": 2.9282576866764276,
      "grad_norm": 9.67723560333252,
      "learning_rate": 8.292825768667644e-06,
      "loss": 0.5689,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6427525622254758,
      "eval_loss": 0.6189645528793335,
      "eval_runtime": 1.5647,
      "eval_samples_per_second": 1746.065,
      "eval_steps_per_second": 54.964,
      "step": 2049
    },
    {
      "epoch": 3.074670571010249,
      "grad_norm": 5.034663677215576,
      "learning_rate": 7.707174231332359e-06,
      "loss": 0.5712,
      "step": 2100
    },
    {
      "epoch": 3.22108345534407,
      "grad_norm": 4.707498550415039,
      "learning_rate": 7.1215226939970725e-06,
      "loss": 0.5292,
      "step": 2200
    },
    {
      "epoch": 3.3674963396778916,
      "grad_norm": 4.101770401000977,
      "learning_rate": 6.535871156661787e-06,
      "loss": 0.5367,
      "step": 2300
    },
    {
      "epoch": 3.513909224011713,
      "grad_norm": 6.7061614990234375,
      "learning_rate": 5.950219619326502e-06,
      "loss": 0.542,
      "step": 2400
    },
    {
      "epoch": 3.660322108345534,
      "grad_norm": 10.22519588470459,
      "learning_rate": 5.364568081991216e-06,
      "loss": 0.5486,
      "step": 2500
    },
    {
      "epoch": 3.8067349926793557,
      "grad_norm": 4.292933940887451,
      "learning_rate": 4.77891654465593e-06,
      "loss": 0.5331,
      "step": 2600
    },
    {
      "epoch": 3.953147877013177,
      "grad_norm": 4.438432216644287,
      "learning_rate": 4.193265007320644e-06,
      "loss": 0.5361,
      "step": 2700
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6295754026354319,
      "eval_loss": 0.633277177810669,
      "eval_runtime": 1.5589,
      "eval_samples_per_second": 1752.491,
      "eval_steps_per_second": 55.166,
      "step": 2732
    },
    {
      "epoch": 4.099560761346998,
      "grad_norm": 5.632227420806885,
      "learning_rate": 3.607613469985359e-06,
      "loss": 0.5327,
      "step": 2800
    },
    {
      "epoch": 4.24597364568082,
      "grad_norm": 8.069804191589355,
      "learning_rate": 3.0219619326500732e-06,
      "loss": 0.5111,
      "step": 2900
    },
    {
      "epoch": 4.392386530014641,
      "grad_norm": 7.2090840339660645,
      "learning_rate": 2.436310395314788e-06,
      "loss": 0.4965,
      "step": 3000
    },
    {
      "epoch": 4.538799414348462,
      "grad_norm": 10.964486122131348,
      "learning_rate": 1.8506588579795024e-06,
      "loss": 0.5082,
      "step": 3100
    },
    {
      "epoch": 4.685212298682284,
      "grad_norm": 4.838050365447998,
      "learning_rate": 1.2650073206442169e-06,
      "loss": 0.497,
      "step": 3200
    },
    {
      "epoch": 4.831625183016105,
      "grad_norm": 6.126997470855713,
      "learning_rate": 6.793557833089313e-07,
      "loss": 0.5137,
      "step": 3300
    },
    {
      "epoch": 4.978038067349927,
      "grad_norm": 13.103296279907227,
      "learning_rate": 9.370424597364569e-08,
      "loss": 0.5202,
      "step": 3400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6372620790629575,
      "eval_loss": 0.6495257019996643,
      "eval_runtime": 1.5569,
      "eval_samples_per_second": 1754.803,
      "eval_steps_per_second": 55.239,
      "step": 3415
    }
  ],
  "logging_steps": 100,
  "max_steps": 3415,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3218980489267200.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}