{
  "best_metric": 1.016390323638916,
  "best_model_checkpoint": "/home/ankur/projects/llm_test/Akshay_Work/mistral_12B_snippets_v1/checkpoint-5149",
  "epoch": 6.998640512720916,
  "eval_steps": 3000,
  "global_step": 12012,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9998057875315596,
      "eval_loss": 1.1702903509140015,
      "eval_runtime": 1084.2637,
      "eval_samples_per_second": 2.364,
      "eval_steps_per_second": 2.364,
      "step": 1716
    },
    {
      "epoch": 1.747912215964265,
      "grad_norm": 0.8725250363349915,
      "learning_rate": 0.00015795285251073526,
      "loss": 1.1644,
      "step": 3000
    },
    {
      "epoch": 1.9996115750631192,
      "eval_loss": 1.0563772916793823,
      "eval_runtime": 1084.6886,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 2.363,
      "step": 3432
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.016390323638916,
      "eval_runtime": 1085.9027,
      "eval_samples_per_second": 2.36,
      "eval_steps_per_second": 2.36,
      "step": 5149
    },
    {
      "epoch": 3.4958244319285297,
      "grad_norm": 0.9269574880599976,
      "learning_rate": 0.00010540706335991588,
      "loss": 0.6414,
      "step": 6000
    },
    {
      "epoch": 3.9998057875315594,
      "eval_loss": 1.0506994724273682,
      "eval_runtime": 1098.0815,
      "eval_samples_per_second": 2.334,
      "eval_steps_per_second": 2.334,
      "step": 6865
    },
    {
      "epoch": 4.999611575063119,
      "eval_loss": 1.1407289505004883,
      "eval_runtime": 1094.1268,
      "eval_samples_per_second": 2.343,
      "eval_steps_per_second": 2.343,
      "step": 8581
    },
    {
      "epoch": 5.243736647892795,
      "grad_norm": 1.0000396966934204,
      "learning_rate": 5.2843747261414424e-05,
      "loss": 0.3137,
      "step": 9000
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.2437316179275513,
      "eval_runtime": 1079.3569,
      "eval_samples_per_second": 2.375,
      "eval_steps_per_second": 2.375,
      "step": 10298
    },
    {
      "epoch": 6.991648863857059,
      "grad_norm": 0.6523720026016235,
      "learning_rate": 2.804311629129787e-07,
      "loss": 0.1744,
      "step": 12000
    },
    {
      "epoch": 6.998640512720916,
      "eval_loss": 1.377004623413086,
      "eval_runtime": 1079.4922,
      "eval_samples_per_second": 2.374,
      "eval_steps_per_second": 2.374,
      "step": 12012
    }
  ],
  "logging_steps": 3000,
  "max_steps": 12012,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.4877646120458547e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}