{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22876751501286818,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001143837575064341,
      "eval_loss": 0.9352622032165527,
      "eval_runtime": 19.8223,
      "eval_samples_per_second": 18.615,
      "eval_steps_per_second": 9.333,
      "step": 1
    },
    {
      "epoch": 0.01143837575064341,
      "grad_norm": 1.0111253261566162,
      "learning_rate": 0.0002,
      "loss": 3.4475,
      "step": 10
    },
    {
      "epoch": 0.02287675150128682,
      "grad_norm": 1.0076441764831543,
      "learning_rate": 0.0002,
      "loss": 3.1352,
      "step": 20
    },
    {
      "epoch": 0.03431512725193023,
      "grad_norm": 1.113232135772705,
      "learning_rate": 0.0002,
      "loss": 2.8919,
      "step": 30
    },
    {
      "epoch": 0.04575350300257364,
      "grad_norm": 1.1204644441604614,
      "learning_rate": 0.0002,
      "loss": 2.9899,
      "step": 40
    },
    {
      "epoch": 0.057191878753217046,
      "grad_norm": 0.9739717841148376,
      "learning_rate": 0.0002,
      "loss": 2.9405,
      "step": 50
    },
    {
      "epoch": 0.057191878753217046,
      "eval_loss": 0.7362952828407288,
      "eval_runtime": 19.921,
      "eval_samples_per_second": 18.523,
      "eval_steps_per_second": 9.287,
      "step": 50
    },
    {
      "epoch": 0.06863025450386046,
      "grad_norm": 0.8366644978523254,
      "learning_rate": 0.0002,
      "loss": 2.9592,
      "step": 60
    },
    {
      "epoch": 0.08006863025450386,
      "grad_norm": 0.8385974764823914,
      "learning_rate": 0.0002,
      "loss": 2.9791,
      "step": 70
    },
    {
      "epoch": 0.09150700600514727,
      "grad_norm": 0.8647813200950623,
      "learning_rate": 0.0002,
      "loss": 2.8695,
      "step": 80
    },
    {
      "epoch": 0.10294538175579068,
      "grad_norm": 0.7855409383773804,
      "learning_rate": 0.0002,
      "loss": 3.2081,
      "step": 90
    },
    {
      "epoch": 0.11438375750643409,
      "grad_norm": 2.0227108001708984,
      "learning_rate": 0.0002,
      "loss": 2.9471,
      "step": 100
    },
    {
      "epoch": 0.11438375750643409,
      "eval_loss": 0.7189851999282837,
      "eval_runtime": 19.8343,
      "eval_samples_per_second": 18.604,
      "eval_steps_per_second": 9.327,
      "step": 100
    },
    {
      "epoch": 0.1258221332570775,
      "grad_norm": 0.8634002208709717,
      "learning_rate": 0.0002,
      "loss": 2.9229,
      "step": 110
    },
    {
      "epoch": 0.1372605090077209,
      "grad_norm": 0.8289279937744141,
      "learning_rate": 0.0002,
      "loss": 2.7623,
      "step": 120
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 0.8797029852867126,
      "learning_rate": 0.0002,
      "loss": 2.9304,
      "step": 130
    },
    {
      "epoch": 0.16013726050900773,
      "grad_norm": 1.5126310586929321,
      "learning_rate": 0.0002,
      "loss": 2.7309,
      "step": 140
    },
    {
      "epoch": 0.17157563625965114,
      "grad_norm": 0.9973982572555542,
      "learning_rate": 0.0002,
      "loss": 2.8402,
      "step": 150
    },
    {
      "epoch": 0.17157563625965114,
      "eval_loss": 0.7114607095718384,
      "eval_runtime": 19.8671,
      "eval_samples_per_second": 18.573,
      "eval_steps_per_second": 9.312,
      "step": 150
    },
    {
      "epoch": 0.18301401201029455,
      "grad_norm": 1.0085833072662354,
      "learning_rate": 0.0002,
      "loss": 2.9839,
      "step": 160
    },
    {
      "epoch": 0.19445238776093796,
      "grad_norm": 0.9592446088790894,
      "learning_rate": 0.0002,
      "loss": 2.7984,
      "step": 170
    },
    {
      "epoch": 0.20589076351158137,
      "grad_norm": 1.625331163406372,
      "learning_rate": 0.0002,
      "loss": 2.7971,
      "step": 180
    },
    {
      "epoch": 0.21732913926222477,
      "grad_norm": 1.4084880352020264,
      "learning_rate": 0.0002,
      "loss": 2.6103,
      "step": 190
    },
    {
      "epoch": 0.22876751501286818,
      "grad_norm": 0.64777672290802,
      "learning_rate": 0.0002,
      "loss": 3.0829,
      "step": 200
    },
    {
      "epoch": 0.22876751501286818,
      "eval_loss": 0.7066531181335449,
      "eval_runtime": 19.8714,
      "eval_samples_per_second": 18.569,
      "eval_steps_per_second": 9.31,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.605261891036774e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}