{
  "best_metric": 0.7631701231002808,
  "best_model_checkpoint": "/content/drive/MyDrive/phifinetuning/checkpoint-900",
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.2222509384155273,
      "learning_rate": 4.8076923076923084e-05,
      "loss": 1.6033,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 0.8335134387016296,
      "eval_runtime": 37.6636,
      "eval_samples_per_second": 13.275,
      "eval_steps_per_second": 6.638,
      "step": 100
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.4819945096969604,
      "learning_rate": 4.423076923076923e-05,
      "loss": 0.8012,
      "step": 200
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.7985976934432983,
      "eval_runtime": 37.7173,
      "eval_samples_per_second": 13.257,
      "eval_steps_per_second": 6.628,
      "step": 200
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.55106782913208,
      "learning_rate": 4.038461538461539e-05,
      "loss": 0.7797,
      "step": 300
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.7857877016067505,
      "eval_runtime": 37.6971,
      "eval_samples_per_second": 13.264,
      "eval_steps_per_second": 6.632,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.5318647623062134,
      "learning_rate": 3.653846153846154e-05,
      "loss": 0.7596,
      "step": 400
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.7795276641845703,
      "eval_runtime": 37.5491,
      "eval_samples_per_second": 13.316,
      "eval_steps_per_second": 6.658,
      "step": 400
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 1.8573933839797974,
      "learning_rate": 3.269230769230769e-05,
      "loss": 0.7589,
      "step": 500
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 0.7731402516365051,
      "eval_runtime": 37.6647,
      "eval_samples_per_second": 13.275,
      "eval_steps_per_second": 6.638,
      "step": 500
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.813819408416748,
      "learning_rate": 2.8846153846153845e-05,
      "loss": 0.7521,
      "step": 600
    },
    {
      "epoch": 1.3333333333333333,
      "eval_loss": 0.7700384259223938,
      "eval_runtime": 37.5855,
      "eval_samples_per_second": 13.303,
      "eval_steps_per_second": 6.651,
      "step": 600
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 1.8046315908432007,
      "learning_rate": 2.5e-05,
      "loss": 0.745,
      "step": 700
    },
    {
      "epoch": 1.5555555555555556,
      "eval_loss": 0.7672878503799438,
      "eval_runtime": 37.6,
      "eval_samples_per_second": 13.298,
      "eval_steps_per_second": 6.649,
      "step": 700
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 2.0249922275543213,
      "learning_rate": 2.1153846153846154e-05,
      "loss": 0.744,
      "step": 800
    },
    {
      "epoch": 1.7777777777777777,
      "eval_loss": 0.7661193013191223,
      "eval_runtime": 37.5596,
      "eval_samples_per_second": 13.312,
      "eval_steps_per_second": 6.656,
      "step": 800
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8335964679718018,
      "learning_rate": 1.730769230769231e-05,
      "loss": 0.7521,
      "step": 900
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7631701231002808,
      "eval_runtime": 37.716,
      "eval_samples_per_second": 13.257,
      "eval_steps_per_second": 6.628,
      "step": 900
    }
  ],
  "logging_steps": 100,
  "max_steps": 1350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.48980558010368e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}