{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7540056550424128,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03770028275212064,
      "grad_norm": 3.2918148040771484,
      "learning_rate": 4.9995083170283816e-05,
      "loss": 4.3742,
      "num_input_tokens_seen": 50544,
      "step": 5
    },
    {
      "epoch": 0.07540056550424128,
      "grad_norm": 3.0331127643585205,
      "learning_rate": 4.998033461515242e-05,
      "loss": 3.8434,
      "num_input_tokens_seen": 104080,
      "step": 10
    },
    {
      "epoch": 0.11310084825636192,
      "grad_norm": 3.322950601577759,
      "learning_rate": 4.9955760135896534e-05,
      "loss": 3.6027,
      "num_input_tokens_seen": 155776,
      "step": 15
    },
    {
      "epoch": 0.15080113100848255,
      "grad_norm": 2.7705531120300293,
      "learning_rate": 4.992136939879856e-05,
      "loss": 3.4102,
      "num_input_tokens_seen": 203184,
      "step": 20
    },
    {
      "epoch": 0.1885014137606032,
      "grad_norm": 3.4572091102600098,
      "learning_rate": 4.9877175931330346e-05,
      "loss": 3.153,
      "num_input_tokens_seen": 255744,
      "step": 25
    },
    {
      "epoch": 0.22620169651272384,
      "grad_norm": 2.0412893295288086,
      "learning_rate": 4.982319711683221e-05,
      "loss": 3.0949,
      "num_input_tokens_seen": 307808,
      "step": 30
    },
    {
      "epoch": 0.2639019792648445,
      "grad_norm": 2.0765998363494873,
      "learning_rate": 4.975945418767529e-05,
      "loss": 3.0392,
      "num_input_tokens_seen": 358192,
      "step": 35
    },
    {
      "epoch": 0.3016022620169651,
      "grad_norm": 2.2433698177337646,
      "learning_rate": 4.968597221690986e-05,
      "loss": 3.0685,
      "num_input_tokens_seen": 408832,
      "step": 40
    },
    {
      "epoch": 0.3393025447690858,
      "grad_norm": 2.7639973163604736,
      "learning_rate": 4.96027801084029e-05,
      "loss": 3.0385,
      "num_input_tokens_seen": 458368,
      "step": 45
    },
    {
      "epoch": 0.3770028275212064,
      "grad_norm": 2.0680019855499268,
      "learning_rate": 4.950991058546893e-05,
      "loss": 3.1079,
      "num_input_tokens_seen": 512160,
      "step": 50
    },
    {
      "epoch": 0.41470311027332707,
      "grad_norm": 2.181554079055786,
      "learning_rate": 4.940740017799833e-05,
      "loss": 2.9883,
      "num_input_tokens_seen": 562928,
      "step": 55
    },
    {
      "epoch": 0.4524033930254477,
      "grad_norm": 2.0724411010742188,
      "learning_rate": 4.929528920808854e-05,
      "loss": 2.969,
      "num_input_tokens_seen": 613072,
      "step": 60
    },
    {
      "epoch": 0.49010367577756836,
      "grad_norm": 2.5529158115386963,
      "learning_rate": 4.917362177418342e-05,
      "loss": 3.0019,
      "num_input_tokens_seen": 664640,
      "step": 65
    },
    {
      "epoch": 0.527803958529689,
      "grad_norm": 2.3983142375946045,
      "learning_rate": 4.904244573372733e-05,
      "loss": 2.9984,
      "num_input_tokens_seen": 716800,
      "step": 70
    },
    {
      "epoch": 0.5655042412818096,
      "grad_norm": 2.206209182739258,
      "learning_rate": 4.8901812684340564e-05,
      "loss": 2.9848,
      "num_input_tokens_seen": 766528,
      "step": 75
    },
    {
      "epoch": 0.6032045240339302,
      "grad_norm": 2.22698974609375,
      "learning_rate": 4.8751777943523634e-05,
      "loss": 2.9169,
      "num_input_tokens_seen": 817376,
      "step": 80
    },
    {
      "epoch": 0.6409048067860509,
      "grad_norm": 2.4569709300994873,
      "learning_rate": 4.8592400526898314e-05,
      "loss": 2.8844,
      "num_input_tokens_seen": 864688,
      "step": 85
    },
    {
      "epoch": 0.6786050895381716,
      "grad_norm": 2.195237636566162,
      "learning_rate": 4.842374312499405e-05,
      "loss": 2.9422,
      "num_input_tokens_seen": 913216,
      "step": 90
    },
    {
      "epoch": 0.7163053722902922,
      "grad_norm": 2.54585599899292,
      "learning_rate": 4.824587207858888e-05,
      "loss": 2.8431,
      "num_input_tokens_seen": 964144,
      "step": 95
    },
    {
      "epoch": 0.7540056550424128,
      "grad_norm": 2.3841867446899414,
      "learning_rate": 4.805885735261454e-05,
      "loss": 2.8377,
      "num_input_tokens_seen": 1018768,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 792,
  "num_input_tokens_seen": 1018768,
  "num_train_epochs": 6,
  "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": 1.243855378710528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}