{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.31496062992125984,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015748031496062992,
      "grad_norm": 5.510926246643066,
      "learning_rate": 1.9894179894179895e-05,
      "loss": 0.9249,
      "step": 1
    },
    {
      "epoch": 0.031496062992125984,
      "grad_norm": 8.61505126953125,
      "learning_rate": 1.978835978835979e-05,
      "loss": 0.8445,
      "step": 2
    },
    {
      "epoch": 0.047244094488188976,
      "grad_norm": 7.036591529846191,
      "learning_rate": 1.9682539682539684e-05,
      "loss": 0.9654,
      "step": 3
    },
    {
      "epoch": 0.06299212598425197,
      "grad_norm": 5.803933143615723,
      "learning_rate": 1.9576719576719577e-05,
      "loss": 0.9276,
      "step": 4
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 5.716428756713867,
      "learning_rate": 1.947089947089947e-05,
      "loss": 0.9241,
      "step": 5
    },
    {
      "epoch": 0.07874015748031496,
      "eval_accuracy": 0.5678496868475992,
      "eval_loss": 0.6996241807937622,
      "eval_runtime": 108.7291,
      "eval_samples_per_second": 4.405,
      "eval_steps_per_second": 0.552,
      "step": 5
    },
    {
      "epoch": 0.09448818897637795,
      "grad_norm": 7.55866813659668,
      "learning_rate": 1.9365079365079367e-05,
      "loss": 0.9947,
      "step": 6
    },
    {
      "epoch": 0.11023622047244094,
      "grad_norm": 6.801171779632568,
      "learning_rate": 1.925925925925926e-05,
      "loss": 0.972,
      "step": 7
    },
    {
      "epoch": 0.12598425196850394,
      "grad_norm": 4.845946311950684,
      "learning_rate": 1.9153439153439156e-05,
      "loss": 0.6478,
      "step": 8
    },
    {
      "epoch": 0.14173228346456693,
      "grad_norm": 10.487945556640625,
      "learning_rate": 1.904761904761905e-05,
      "loss": 0.8597,
      "step": 9
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 5.452786445617676,
      "learning_rate": 1.8941798941798943e-05,
      "loss": 0.7708,
      "step": 10
    },
    {
      "epoch": 0.15748031496062992,
      "eval_accuracy": 0.6659707724425887,
      "eval_loss": 0.6283570528030396,
      "eval_runtime": 108.7155,
      "eval_samples_per_second": 4.406,
      "eval_steps_per_second": 0.552,
      "step": 10
    },
    {
      "epoch": 0.1732283464566929,
      "grad_norm": 4.522532939910889,
      "learning_rate": 1.8835978835978836e-05,
      "loss": 0.6848,
      "step": 11
    },
    {
      "epoch": 0.1889763779527559,
      "grad_norm": 6.4987688064575195,
      "learning_rate": 1.8730158730158732e-05,
      "loss": 0.6644,
      "step": 12
    },
    {
      "epoch": 0.2047244094488189,
      "grad_norm": 4.2297682762146,
      "learning_rate": 1.8624338624338625e-05,
      "loss": 0.7227,
      "step": 13
    },
    {
      "epoch": 0.2204724409448819,
      "grad_norm": 6.5658063888549805,
      "learning_rate": 1.851851851851852e-05,
      "loss": 0.6991,
      "step": 14
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 6.549685001373291,
      "learning_rate": 1.8412698412698415e-05,
      "loss": 0.7875,
      "step": 15
    },
    {
      "epoch": 0.23622047244094488,
      "eval_accuracy": 0.7244258872651357,
      "eval_loss": 0.5749094486236572,
      "eval_runtime": 108.7121,
      "eval_samples_per_second": 4.406,
      "eval_steps_per_second": 0.552,
      "step": 15
    },
    {
      "epoch": 0.25196850393700787,
      "grad_norm": 3.6349198818206787,
      "learning_rate": 1.8306878306878308e-05,
      "loss": 0.5732,
      "step": 16
    },
    {
      "epoch": 0.2677165354330709,
      "grad_norm": 4.741979598999023,
      "learning_rate": 1.82010582010582e-05,
      "loss": 0.5774,
      "step": 17
    },
    {
      "epoch": 0.28346456692913385,
      "grad_norm": 4.751223087310791,
      "learning_rate": 1.8095238095238097e-05,
      "loss": 0.5738,
      "step": 18
    },
    {
      "epoch": 0.2992125984251969,
      "grad_norm": 5.214819431304932,
      "learning_rate": 1.798941798941799e-05,
      "loss": 0.7182,
      "step": 19
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 5.566962718963623,
      "learning_rate": 1.7883597883597884e-05,
      "loss": 0.6575,
      "step": 20
    },
    {
      "epoch": 0.31496062992125984,
      "eval_accuracy": 0.7390396659707724,
      "eval_loss": 0.5360159873962402,
      "eval_runtime": 108.7252,
      "eval_samples_per_second": 4.406,
      "eval_steps_per_second": 0.552,
      "step": 20
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 189,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}