{
  "best_metric": 2.1281208992004395,
  "best_model_checkpoint": "/content/drive/MyDrive/Hugh Mann/Qwen_SMS_Final/checkpoint-100",
  "epoch": 0.1037344398340249,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01037344398340249,
      "grad_norm": 4.638428688049316,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.6475,
      "step": 10
    },
    {
      "epoch": 0.02074688796680498,
      "grad_norm": 4.252462387084961,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.5383,
      "step": 20
    },
    {
      "epoch": 0.03112033195020747,
      "grad_norm": 3.85965895652771,
      "learning_rate": 2.4e-05,
      "loss": 4.3536,
      "step": 30
    },
    {
      "epoch": 0.04149377593360996,
      "grad_norm": 4.050565719604492,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.9934,
      "step": 40
    },
    {
      "epoch": 0.05186721991701245,
      "grad_norm": 3.7960705757141113,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 3.3933,
      "step": 50
    },
    {
      "epoch": 0.05186721991701245,
      "eval_loss": 3.1315643787384033,
      "eval_runtime": 132.8003,
      "eval_samples_per_second": 25.813,
      "eval_steps_per_second": 12.907,
      "step": 50
    },
    {
      "epoch": 0.06224066390041494,
      "grad_norm": 2.2538864612579346,
      "learning_rate": 4.64e-05,
      "loss": 2.8554,
      "step": 60
    },
    {
      "epoch": 0.07261410788381743,
      "grad_norm": 0.8144139051437378,
      "learning_rate": 5.440000000000001e-05,
      "loss": 2.6473,
      "step": 70
    },
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 1.0595426559448242,
      "learning_rate": 6.240000000000001e-05,
      "loss": 2.5251,
      "step": 80
    },
    {
      "epoch": 0.09336099585062241,
      "grad_norm": 1.4303592443466187,
      "learning_rate": 7.04e-05,
      "loss": 2.2689,
      "step": 90
    },
    {
      "epoch": 0.1037344398340249,
      "grad_norm": 1.6767040491104126,
      "learning_rate": 7.840000000000001e-05,
      "loss": 2.1918,
      "step": 100
    },
    {
      "epoch": 0.1037344398340249,
      "eval_loss": 2.1281208992004395,
      "eval_runtime": 133.7825,
      "eval_samples_per_second": 25.624,
      "eval_steps_per_second": 12.812,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 964,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.7313374756864e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}