{
  "best_metric": 7.5260701179504395,
  "best_model_checkpoint": "/home/datta0/models/lora_final/Mistral-7B-v0.3_pct_reverse/checkpoint-48",
  "epoch": 0.18568665377176016,
  "eval_steps": 8,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025789813023855577,
      "grad_norm": 17.363887786865234,
      "learning_rate": 3.75e-05,
      "loss": 2.1239,
      "step": 1
    },
    {
      "epoch": 0.010315925209542231,
      "grad_norm": 14.140544891357422,
      "learning_rate": 0.00015,
      "loss": 2.053,
      "step": 4
    },
    {
      "epoch": 0.020631850419084462,
      "grad_norm": 471.962158203125,
      "learning_rate": 0.0003,
      "loss": 2.1192,
      "step": 8
    },
    {
      "epoch": 0.020631850419084462,
      "eval_loss": 11.598015785217285,
      "eval_runtime": 10.9566,
      "eval_samples_per_second": 22.361,
      "eval_steps_per_second": 2.829,
      "step": 8
    },
    {
      "epoch": 0.030947775628626693,
      "grad_norm": 4009.223388671875,
      "learning_rate": 0.00029991755529206284,
      "loss": 10.6315,
      "step": 12
    },
    {
      "epoch": 0.041263700838168924,
      "grad_norm": 42.12191390991211,
      "learning_rate": 0.0002996703117966496,
      "loss": 9.6637,
      "step": 16
    },
    {
      "epoch": 0.041263700838168924,
      "eval_loss": 8.410330772399902,
      "eval_runtime": 10.7056,
      "eval_samples_per_second": 22.885,
      "eval_steps_per_second": 2.896,
      "step": 16
    },
    {
      "epoch": 0.05157962604771115,
      "grad_norm": 24.113929748535156,
      "learning_rate": 0.00029925854129933066,
      "loss": 8.3281,
      "step": 20
    },
    {
      "epoch": 0.061895551257253385,
      "grad_norm": 6.116011619567871,
      "learning_rate": 0.0002986826964440844,
      "loss": 7.8718,
      "step": 24
    },
    {
      "epoch": 0.061895551257253385,
      "eval_loss": 8.008735656738281,
      "eval_runtime": 10.6891,
      "eval_samples_per_second": 22.921,
      "eval_steps_per_second": 2.9,
      "step": 24
    },
    {
      "epoch": 0.07221147646679561,
      "grad_norm": 11.01762580871582,
      "learning_rate": 0.00029794341023572295,
      "loss": 7.8313,
      "step": 28
    },
    {
      "epoch": 0.08252740167633785,
      "grad_norm": 3.9344899654388428,
      "learning_rate": 0.0002970414953440533,
      "loss": 7.6741,
      "step": 32
    },
    {
      "epoch": 0.08252740167633785,
      "eval_loss": 7.719517230987549,
      "eval_runtime": 10.5778,
      "eval_samples_per_second": 23.162,
      "eval_steps_per_second": 2.931,
      "step": 32
    },
    {
      "epoch": 0.09284332688588008,
      "grad_norm": 4.952977180480957,
      "learning_rate": 0.00029597794321054006,
      "loss": 7.6388,
      "step": 36
    },
    {
      "epoch": 0.1031592520954223,
      "grad_norm": 3.788853406906128,
      "learning_rate": 0.00029475392295845,
      "loss": 7.6499,
      "step": 40
    },
    {
      "epoch": 0.1031592520954223,
      "eval_loss": 7.619475364685059,
      "eval_runtime": 10.6008,
      "eval_samples_per_second": 23.111,
      "eval_steps_per_second": 2.924,
      "step": 40
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 5.81605863571167,
      "learning_rate": 0.0002933707801076791,
      "loss": 7.6638,
      "step": 44
    },
    {
      "epoch": 0.12379110251450677,
      "grad_norm": 2.517054319381714,
      "learning_rate": 0.00029183003509567217,
      "loss": 7.6391,
      "step": 48
    },
    {
      "epoch": 0.12379110251450677,
      "eval_loss": 7.5260701179504395,
      "eval_runtime": 10.5993,
      "eval_samples_per_second": 23.115,
      "eval_steps_per_second": 2.925,
      "step": 48
    },
    {
      "epoch": 0.134107027724049,
      "grad_norm": 3.91676926612854,
      "learning_rate": 0.000290133381606063,
      "loss": 7.6305,
      "step": 52
    },
    {
      "epoch": 0.14442295293359123,
      "grad_norm": 9.17829418182373,
      "learning_rate": 0.0002882826847068703,
      "loss": 7.5835,
      "step": 56
    },
    {
      "epoch": 0.14442295293359123,
      "eval_loss": 7.5467963218688965,
      "eval_runtime": 10.628,
      "eval_samples_per_second": 23.052,
      "eval_steps_per_second": 2.917,
      "step": 56
    },
    {
      "epoch": 0.15473887814313347,
      "grad_norm": 12.215532302856445,
      "learning_rate": 0.00028627997880029875,
      "loss": 7.563,
      "step": 60
    },
    {
      "epoch": 0.1650548033526757,
      "grad_norm": 11.112576484680176,
      "learning_rate": 0.0002841274653863955,
      "loss": 7.5515,
      "step": 64
    },
    {
      "epoch": 0.1650548033526757,
      "eval_loss": 7.549396514892578,
      "eval_runtime": 10.6501,
      "eval_samples_per_second": 23.005,
      "eval_steps_per_second": 2.911,
      "step": 64
    },
    {
      "epoch": 0.17537072856221791,
      "grad_norm": 13.383460998535156,
      "learning_rate": 0.00028182751064302397,
      "loss": 7.5315,
      "step": 68
    },
    {
      "epoch": 0.18568665377176016,
      "grad_norm": 11.468887329101562,
      "learning_rate": 0.0002793826428248118,
      "loss": 7.6827,
      "step": 72
    },
    {
      "epoch": 0.18568665377176016,
      "eval_loss": 7.556999206542969,
      "eval_runtime": 10.7096,
      "eval_samples_per_second": 22.877,
      "eval_steps_per_second": 2.895,
      "step": 72
    }
  ],
  "logging_steps": 4,
  "max_steps": 387,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6852503905540506e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}