{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01804402742692169,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036088054853843375,
      "eval_loss": 2.2970988750457764,
      "eval_runtime": 40.8928,
      "eval_samples_per_second": 28.538,
      "eval_steps_per_second": 14.281,
      "step": 1
    },
    {
      "epoch": 0.001804402742692169,
      "grad_norm": 1.4550670385360718,
      "learning_rate": 5e-05,
      "loss": 2.0658,
      "step": 5
    },
    {
      "epoch": 0.003608805485384338,
      "grad_norm": 1.1833549737930298,
      "learning_rate": 0.0001,
      "loss": 2.0273,
      "step": 10
    },
    {
      "epoch": 0.003608805485384338,
      "eval_loss": 1.8604884147644043,
      "eval_runtime": 40.0345,
      "eval_samples_per_second": 29.15,
      "eval_steps_per_second": 14.587,
      "step": 10
    },
    {
      "epoch": 0.0054132082280765065,
      "grad_norm": 1.5056965351104736,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6813,
      "step": 15
    },
    {
      "epoch": 0.007217610970768676,
      "grad_norm": 1.5909525156021118,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3814,
      "step": 20
    },
    {
      "epoch": 0.007217610970768676,
      "eval_loss": 1.2907471656799316,
      "eval_runtime": 41.2631,
      "eval_samples_per_second": 28.282,
      "eval_steps_per_second": 14.153,
      "step": 20
    },
    {
      "epoch": 0.009022013713460845,
      "grad_norm": 1.2135497331619263,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.226,
      "step": 25
    },
    {
      "epoch": 0.010826416456153013,
      "grad_norm": 1.0557843446731567,
      "learning_rate": 5e-05,
      "loss": 1.1616,
      "step": 30
    },
    {
      "epoch": 0.010826416456153013,
      "eval_loss": 1.1701592206954956,
      "eval_runtime": 43.9546,
      "eval_samples_per_second": 26.55,
      "eval_steps_per_second": 13.286,
      "step": 30
    },
    {
      "epoch": 0.012630819198845183,
      "grad_norm": 0.8924847841262817,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.1289,
      "step": 35
    },
    {
      "epoch": 0.014435221941537351,
      "grad_norm": 0.9489301443099976,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1425,
      "step": 40
    },
    {
      "epoch": 0.014435221941537351,
      "eval_loss": 1.131185531616211,
      "eval_runtime": 43.5392,
      "eval_samples_per_second": 26.803,
      "eval_steps_per_second": 13.413,
      "step": 40
    },
    {
      "epoch": 0.01623962468422952,
      "grad_norm": 1.2116780281066895,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1448,
      "step": 45
    },
    {
      "epoch": 0.01804402742692169,
      "grad_norm": 0.8470674753189087,
      "learning_rate": 0.0,
      "loss": 1.1224,
      "step": 50
    },
    {
      "epoch": 0.01804402742692169,
      "eval_loss": 1.1224923133850098,
      "eval_runtime": 40.4158,
      "eval_samples_per_second": 28.875,
      "eval_steps_per_second": 14.45,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2557919782502400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}