{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9950617283950618,
  "eval_steps": 100,
  "global_step": 202,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.3113946318626404,
      "learning_rate": 0.00019988322268323268,
      "loss": 1.1897,
      "step": 10
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.25871261954307556,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.6655,
      "step": 20
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.13192948698997498,
      "learning_rate": 0.0001932129465573568,
      "loss": 0.363,
      "step": 30
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.1178111806511879,
      "learning_rate": 0.00018619696668800492,
      "loss": 0.2902,
      "step": 40
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.06365109980106354,
      "learning_rate": 0.00017694853065861662,
      "loss": 0.2627,
      "step": 50
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.06805580109357834,
      "learning_rate": 0.0001657071681043731,
      "loss": 0.2479,
      "step": 60
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.05795082449913025,
      "learning_rate": 0.0001527640244106133,
      "loss": 0.248,
      "step": 70
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.054490040987730026,
      "learning_rate": 0.0001384543202002851,
      "loss": 0.2374,
      "step": 80
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.050945691764354706,
      "learning_rate": 0.00012314866929589432,
      "loss": 0.2364,
      "step": 90
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.05336359888315201,
      "learning_rate": 0.00010724348001617625,
      "loss": 0.2314,
      "step": 100
    },
    {
      "epoch": 0.9876543209876543,
      "eval_loss": 0.23581312596797943,
      "eval_runtime": 270.7343,
      "eval_samples_per_second": 0.665,
      "eval_steps_per_second": 0.665,
      "step": 100
    },
    {
      "epoch": 1.0864197530864197,
      "grad_norm": 0.052394308149814606,
      "learning_rate": 9.115068840886417e-05,
      "loss": 0.2339,
      "step": 110
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.06545981019735336,
      "learning_rate": 7.528708932343304e-05,
      "loss": 0.2301,
      "step": 120
    },
    {
      "epoch": 1.2839506172839505,
      "grad_norm": 0.06937788426876068,
      "learning_rate": 6.006354164343046e-05,
      "loss": 0.2322,
      "step": 130
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.07582119852304459,
      "learning_rate": 4.587432725720687e-05,
      "loss": 0.2234,
      "step": 140
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.11781789362430573,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.2164,
      "step": 150
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.08647400885820389,
      "learning_rate": 2.2032564593677774e-05,
      "loss": 0.2197,
      "step": 160
    },
    {
      "epoch": 1.6790123456790123,
      "grad_norm": 0.09350328147411346,
      "learning_rate": 1.2997505445856084e-05,
      "loss": 0.2194,
      "step": 170
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.14273136854171753,
      "learning_rate": 6.215765206679569e-06,
      "loss": 0.2219,
      "step": 180
    },
    {
      "epoch": 1.876543209876543,
      "grad_norm": 0.10584201663732529,
      "learning_rate": 1.8629873860586566e-06,
      "loss": 0.2298,
      "step": 190
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.08690895885229111,
      "learning_rate": 5.190664313851068e-08,
      "loss": 0.2228,
      "step": 200
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.2289411574602127,
      "eval_runtime": 273.2063,
      "eval_samples_per_second": 0.659,
      "eval_steps_per_second": 0.659,
      "step": 200
    },
    {
      "epoch": 1.9950617283950618,
      "step": 202,
      "total_flos": 1.2609051312227942e+17,
      "train_loss": 0.3101574260704588,
      "train_runtime": 14633.2305,
      "train_samples_per_second": 0.221,
      "train_steps_per_second": 0.014
    },
    {
      "epoch": 1.9950617283950618,
      "eval_loss": 0.22894252836704254,
      "eval_runtime": 273.8519,
      "eval_samples_per_second": 0.657,
      "eval_steps_per_second": 0.657,
      "step": 202
    }
  ],
  "logging_steps": 10,
  "max_steps": 202,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2609051312227942e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}