{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 3.0887749195098877,
      "learning_rate": 2.384538152610442e-06,
      "loss": 0.7185,
      "step": 25
    },
    {
      "epoch": 0.005,
      "grad_norm": 3.3972108364105225,
      "learning_rate": 2.2590361445783136e-06,
      "loss": 0.7207,
      "step": 50
    },
    {
      "epoch": 0.0075,
      "grad_norm": 2.799666166305542,
      "learning_rate": 2.1335341365461848e-06,
      "loss": 0.6349,
      "step": 75
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.892286539077759,
      "learning_rate": 2.0080321285140564e-06,
      "loss": 0.609,
      "step": 100
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.9785426259040833,
      "eval_runtime": 50.0276,
      "eval_samples_per_second": 0.999,
      "eval_steps_per_second": 0.14,
      "step": 100
    },
    {
      "epoch": 0.0125,
      "grad_norm": 2.4466898441314697,
      "learning_rate": 1.882530120481928e-06,
      "loss": 0.6208,
      "step": 125
    },
    {
      "epoch": 0.015,
      "grad_norm": 2.5951688289642334,
      "learning_rate": 1.7570281124497993e-06,
      "loss": 0.6043,
      "step": 150
    },
    {
      "epoch": 0.0175,
      "grad_norm": 2.5070278644561768,
      "learning_rate": 1.6315261044176709e-06,
      "loss": 0.6723,
      "step": 175
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.5609757900238037,
      "learning_rate": 1.5060240963855425e-06,
      "loss": 0.5984,
      "step": 200
    },
    {
      "epoch": 0.02,
      "eval_loss": 0.985219419002533,
      "eval_runtime": 49.8634,
      "eval_samples_per_second": 1.003,
      "eval_steps_per_second": 0.14,
      "step": 200
    },
    {
      "epoch": 0.0225,
      "grad_norm": 3.5456857681274414,
      "learning_rate": 1.3805220883534137e-06,
      "loss": 0.5879,
      "step": 225
    },
    {
      "epoch": 0.025,
      "grad_norm": 3.7330322265625,
      "learning_rate": 1.2550200803212854e-06,
      "loss": 0.604,
      "step": 250
    },
    {
      "epoch": 0.0275,
      "grad_norm": 2.9475417137145996,
      "learning_rate": 1.1295180722891568e-06,
      "loss": 0.545,
      "step": 275
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.689638137817383,
      "learning_rate": 1.0040160642570282e-06,
      "loss": 0.5419,
      "step": 300
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.9883354306221008,
      "eval_runtime": 49.9109,
      "eval_samples_per_second": 1.002,
      "eval_steps_per_second": 0.14,
      "step": 300
    },
    {
      "epoch": 0.0325,
      "grad_norm": 4.0419721603393555,
      "learning_rate": 8.785140562248996e-07,
      "loss": 0.52,
      "step": 325
    },
    {
      "epoch": 0.035,
      "grad_norm": 4.243961811065674,
      "learning_rate": 7.530120481927713e-07,
      "loss": 0.6001,
      "step": 350
    },
    {
      "epoch": 0.0375,
      "grad_norm": 3.7675397396087646,
      "learning_rate": 6.275100401606427e-07,
      "loss": 0.5309,
      "step": 375
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.4450817108154297,
      "learning_rate": 5.020080321285141e-07,
      "loss": 0.5738,
      "step": 400
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.9952414035797119,
      "eval_runtime": 50.0075,
      "eval_samples_per_second": 1.0,
      "eval_steps_per_second": 0.14,
      "step": 400
    },
    {
      "epoch": 0.0425,
      "grad_norm": 3.5277650356292725,
      "learning_rate": 3.7650602409638563e-07,
      "loss": 0.6085,
      "step": 425
    },
    {
      "epoch": 0.045,
      "grad_norm": 4.167781829833984,
      "learning_rate": 2.5100401606425705e-07,
      "loss": 0.6188,
      "step": 450
    },
    {
      "epoch": 0.0475,
      "grad_norm": 3.9890384674072266,
      "learning_rate": 1.2550200803212853e-07,
      "loss": 0.5281,
      "step": 475
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.777990341186523,
      "learning_rate": 0.0,
      "loss": 0.6808,
      "step": 500
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9945573210716248,
      "eval_runtime": 50.1662,
      "eval_samples_per_second": 0.997,
      "eval_steps_per_second": 0.14,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1052597116928e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}