{
  "best_global_step": 40,
  "best_metric": 0.43451955914497375,
  "best_model_checkpoint": "ft_checkpoints/fold4_CU3/checkpoint-40",
  "epoch": 1.7391304347826086,
  "eval_steps": 10,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.6149529814720154,
      "learning_rate": 8e-05,
      "loss": 0.4473,
      "step": 5
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 1.3481638431549072,
      "learning_rate": 0.00018,
      "loss": 0.2751,
      "step": 10
    },
    {
      "epoch": 0.43478260869565216,
      "eval_loss": 0.4551287293434143,
      "eval_runtime": 4.9349,
      "eval_samples_per_second": 43.567,
      "eval_steps_per_second": 5.471,
      "step": 10
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.7840824127197266,
      "learning_rate": 0.0001864406779661017,
      "loss": 0.5286,
      "step": 15
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.8211029767990112,
      "learning_rate": 0.00016949152542372882,
      "loss": 0.497,
      "step": 20
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.4426790177822113,
      "eval_runtime": 5.1609,
      "eval_samples_per_second": 41.659,
      "eval_steps_per_second": 5.232,
      "step": 20
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.8198596835136414,
      "learning_rate": 0.00015254237288135592,
      "loss": 0.5088,
      "step": 25
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.8266681432723999,
      "learning_rate": 0.00013559322033898305,
      "loss": 0.368,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.4371105134487152,
      "eval_runtime": 4.9664,
      "eval_samples_per_second": 43.291,
      "eval_steps_per_second": 5.437,
      "step": 30
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.9265542030334473,
      "learning_rate": 0.00011864406779661017,
      "loss": 0.325,
      "step": 35
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.8554236888885498,
      "learning_rate": 0.00010169491525423729,
      "loss": 0.36,
      "step": 40
    },
    {
      "epoch": 1.7391304347826086,
      "eval_loss": 0.43451955914497375,
      "eval_runtime": 5.1657,
      "eval_samples_per_second": 41.621,
      "eval_steps_per_second": 5.227,
      "step": 40
    }
  ],
  "logging_steps": 5,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7911388407250944.0,
  "train_batch_size": 40,
  "trial_name": null,
  "trial_params": null
}