{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.932862190812721,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 0.8506448268890381,
      "learning_rate": 4.972077065562821e-05,
      "loss": 0.4843,
      "num_input_tokens_seen": 89360,
      "step": 5
    },
    {
      "epoch": 0.2826855123674912,
      "grad_norm": 0.9152102470397949,
      "learning_rate": 4.888932014465352e-05,
      "loss": 0.271,
      "num_input_tokens_seen": 173680,
      "step": 10
    },
    {
      "epoch": 0.42402826855123676,
      "grad_norm": 1.011157512664795,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.3194,
      "num_input_tokens_seen": 256320,
      "step": 15
    },
    {
      "epoch": 0.5653710247349824,
      "grad_norm": 1.6936814785003662,
      "learning_rate": 4.5655969357899874e-05,
      "loss": 0.2881,
      "num_input_tokens_seen": 354080,
      "step": 20
    },
    {
      "epoch": 0.7067137809187279,
      "grad_norm": 1.1560394763946533,
      "learning_rate": 4.332629679574566e-05,
      "loss": 0.2433,
      "num_input_tokens_seen": 445120,
      "step": 25
    },
    {
      "epoch": 0.8480565371024735,
      "grad_norm": 0.8873085379600525,
      "learning_rate": 4.058724504646834e-05,
      "loss": 0.1921,
      "num_input_tokens_seen": 536160,
      "step": 30
    },
    {
      "epoch": 0.9893992932862191,
      "grad_norm": 1.321128487586975,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.1475,
      "num_input_tokens_seen": 622160,
      "step": 35
    },
    {
      "epoch": 1.1130742049469964,
      "grad_norm": 0.7232786417007446,
      "learning_rate": 3.413352560915988e-05,
      "loss": 0.1183,
      "num_input_tokens_seen": 702992,
      "step": 40
    },
    {
      "epoch": 1.254416961130742,
      "grad_norm": 0.3324046730995178,
      "learning_rate": 3.056302334890786e-05,
      "loss": 0.0833,
      "num_input_tokens_seen": 795712,
      "step": 45
    },
    {
      "epoch": 1.3957597173144876,
      "grad_norm": 1.0428584814071655,
      "learning_rate": 2.686825233966061e-05,
      "loss": 0.1549,
      "num_input_tokens_seen": 880032,
      "step": 50
    },
    {
      "epoch": 1.5371024734982333,
      "grad_norm": 1.143799066543579,
      "learning_rate": 2.3131747660339394e-05,
      "loss": 0.1048,
      "num_input_tokens_seen": 969392,
      "step": 55
    },
    {
      "epoch": 1.6784452296819787,
      "grad_norm": 1.4890297651290894,
      "learning_rate": 1.9436976651092144e-05,
      "loss": 0.1268,
      "num_input_tokens_seen": 1058752,
      "step": 60
    },
    {
      "epoch": 1.8197879858657244,
      "grad_norm": 0.581519365310669,
      "learning_rate": 1.5866474390840125e-05,
      "loss": 0.0301,
      "num_input_tokens_seen": 1143072,
      "step": 65
    },
    {
      "epoch": 1.96113074204947,
      "grad_norm": 3.71907639503479,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0827,
      "num_input_tokens_seen": 1234112,
      "step": 70
    },
    {
      "epoch": 2.0848056537102475,
      "grad_norm": 2.454533576965332,
      "learning_rate": 9.412754953531663e-06,
      "loss": 0.0773,
      "num_input_tokens_seen": 1303184,
      "step": 75
    },
    {
      "epoch": 2.2261484098939928,
      "grad_norm": 0.8271657228469849,
      "learning_rate": 6.673703204254347e-06,
      "loss": 0.0324,
      "num_input_tokens_seen": 1385824,
      "step": 80
    },
    {
      "epoch": 2.3674911660777385,
      "grad_norm": 2.187922716140747,
      "learning_rate": 4.344030642100133e-06,
      "loss": 0.0619,
      "num_input_tokens_seen": 1476864,
      "step": 85
    },
    {
      "epoch": 2.508833922261484,
      "grad_norm": 0.415667325258255,
      "learning_rate": 2.475778302439524e-06,
      "loss": 0.0218,
      "num_input_tokens_seen": 1569584,
      "step": 90
    },
    {
      "epoch": 2.65017667844523,
      "grad_norm": 0.7244300842285156,
      "learning_rate": 1.1106798553464804e-06,
      "loss": 0.0275,
      "num_input_tokens_seen": 1657264,
      "step": 95
    },
    {
      "epoch": 2.791519434628975,
      "grad_norm": 1.3010339736938477,
      "learning_rate": 2.7922934437178695e-07,
      "loss": 0.113,
      "num_input_tokens_seen": 1746624,
      "step": 100
    },
    {
      "epoch": 2.932862190812721,
      "grad_norm": 0.46601220965385437,
      "learning_rate": 0.0,
      "loss": 0.0585,
      "num_input_tokens_seen": 1841024,
      "step": 105
    },
    {
      "epoch": 2.932862190812721,
      "num_input_tokens_seen": 1841024,
      "step": 105,
      "total_flos": 1.3709875850379264e+16,
      "train_loss": 0.14471678897028878,
      "train_runtime": 4170.4867,
      "train_samples_per_second": 0.406,
      "train_steps_per_second": 0.025
    }
  ],
  "logging_steps": 5,
  "max_steps": 105,
  "num_input_tokens_seen": 1841024,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3709875850379264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}