{
  "best_metric": 0.4873640835285187,
  "best_model_checkpoint": "output_pipe/4/origin/checkpoint-200",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 944,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.6054024696350098,
      "learning_rate": 2.8322147651006714e-05,
      "loss": 0.6523,
      "step": 100
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 1.5572692155838013,
      "learning_rate": 2.4966442953020137e-05,
      "loss": 0.5213,
      "step": 200
    },
    {
      "epoch": 0.847457627118644,
      "eval_accuracy": 0.7546468401486989,
      "eval_f1": 0.7545886311627465,
      "eval_loss": 0.4873640835285187,
      "eval_matthews_correlation": 0.5136204005519472,
      "eval_precision": 0.757240412999415,
      "eval_recall": 0.756380707046741,
      "eval_runtime": 0.4764,
      "eval_samples_per_second": 3952.419,
      "eval_steps_per_second": 62.97,
      "step": 200
    },
    {
      "epoch": 1.271186440677966,
      "grad_norm": 2.912567377090454,
      "learning_rate": 2.1610738255033557e-05,
      "loss": 0.4243,
      "step": 300
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 3.009249687194824,
      "learning_rate": 1.825503355704698e-05,
      "loss": 0.3561,
      "step": 400
    },
    {
      "epoch": 1.694915254237288,
      "eval_accuracy": 0.7567711099309612,
      "eval_f1": 0.7551546157602462,
      "eval_loss": 0.5137989521026611,
      "eval_matthews_correlation": 0.5326379449702427,
      "eval_precision": 0.7716787064732773,
      "eval_recall": 0.7610649764430736,
      "eval_runtime": 0.4747,
      "eval_samples_per_second": 3966.427,
      "eval_steps_per_second": 63.193,
      "step": 400
    },
    {
      "epoch": 2.1186440677966103,
      "grad_norm": 9.79773235321045,
      "learning_rate": 1.4899328859060403e-05,
      "loss": 0.2884,
      "step": 500
    },
    {
      "epoch": 2.542372881355932,
      "grad_norm": 6.196119785308838,
      "learning_rate": 1.1543624161073825e-05,
      "loss": 0.0992,
      "step": 600
    },
    {
      "epoch": 2.542372881355932,
      "eval_accuracy": 0.7673924588422729,
      "eval_f1": 0.7673871448846009,
      "eval_loss": 0.6910274624824524,
      "eval_matthews_correlation": 0.5376904599032052,
      "eval_precision": 0.768957383485309,
      "eval_recall": 0.7687331231852128,
      "eval_runtime": 0.4743,
      "eval_samples_per_second": 3970.373,
      "eval_steps_per_second": 63.256,
      "step": 600
    },
    {
      "epoch": 2.9661016949152543,
      "grad_norm": 5.558084964752197,
      "learning_rate": 8.18791946308725e-06,
      "loss": 0.0961,
      "step": 700
    },
    {
      "epoch": 3.389830508474576,
      "grad_norm": 4.1897196769714355,
      "learning_rate": 4.832214765100671e-06,
      "loss": 0.0399,
      "step": 800
    },
    {
      "epoch": 3.389830508474576,
      "eval_accuracy": 0.7652681890600106,
      "eval_f1": 0.7651775234741784,
      "eval_loss": 1.0188117027282715,
      "eval_matthews_correlation": 0.5355988651772904,
      "eval_precision": 0.7684172890513269,
      "eval_recall": 0.7671829983391519,
      "eval_runtime": 0.4754,
      "eval_samples_per_second": 3960.7,
      "eval_steps_per_second": 63.102,
      "step": 800
    },
    {
      "epoch": 3.8135593220338984,
      "grad_norm": 9.25539779663086,
      "learning_rate": 1.5100671140939598e-06,
      "loss": 0.0296,
      "step": 900
    },
    {
      "epoch": 4.0,
      "step": 944,
      "total_flos": 4056474731991360.0,
      "train_loss": 0.2665235818821495,
      "train_runtime": 83.9458,
      "train_samples_per_second": 717.797,
      "train_steps_per_second": 11.245
    }
  ],
  "logging_steps": 100,
  "max_steps": 944,
  "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": 4056474731991360.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}