{
  "best_global_step": 700,
  "best_metric": 0.5273797512054443,
  "best_model_checkpoint": "/dgx2/pawangcs/Trained_Models/Phi4-3shot/checkpoint-700",
  "epoch": 3.288065843621399,
  "eval_steps": 100,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 0.6248233914375305,
      "learning_rate": 0.0002179699417406859,
      "loss": 0.832540283203125,
      "step": 100
    },
    {
      "epoch": 0.27434842249657065,
      "eval_loss": 0.6426836252212524,
      "eval_runtime": 1160.1148,
      "eval_samples_per_second": 2.515,
      "eval_steps_per_second": 0.629,
      "step": 100
    },
    {
      "epoch": 0.5486968449931413,
      "grad_norm": 0.6830066442489624,
      "learning_rate": 0.0002157366837530479,
      "loss": 0.6157448196411133,
      "step": 200
    },
    {
      "epoch": 0.5486968449931413,
      "eval_loss": 0.6033561825752258,
      "eval_runtime": 405.4127,
      "eval_samples_per_second": 7.198,
      "eval_steps_per_second": 1.801,
      "step": 200
    },
    {
      "epoch": 0.823045267489712,
      "grad_norm": 0.6402314901351929,
      "learning_rate": 0.00021002940172700765,
      "loss": 0.5921715927124024,
      "step": 300
    },
    {
      "epoch": 0.823045267489712,
      "eval_loss": 0.5785361528396606,
      "eval_runtime": 405.9414,
      "eval_samples_per_second": 7.188,
      "eval_steps_per_second": 1.798,
      "step": 300
    },
    {
      "epoch": 1.0960219478737998,
      "grad_norm": 0.8042563796043396,
      "learning_rate": 0.00020103385405654221,
      "loss": 0.5310408401489258,
      "step": 400
    },
    {
      "epoch": 1.0960219478737998,
      "eval_loss": 0.5722617506980896,
      "eval_runtime": 406.5022,
      "eval_samples_per_second": 7.178,
      "eval_steps_per_second": 1.796,
      "step": 400
    },
    {
      "epoch": 1.3703703703703702,
      "grad_norm": 0.6911748051643372,
      "learning_rate": 0.0001890428243259542,
      "loss": 0.45402183532714846,
      "step": 500
    },
    {
      "epoch": 1.3703703703703702,
      "eval_loss": 0.5583283305168152,
      "eval_runtime": 404.6307,
      "eval_samples_per_second": 7.212,
      "eval_steps_per_second": 1.804,
      "step": 500
    },
    {
      "epoch": 1.6447187928669411,
      "grad_norm": 0.6612902283668518,
      "learning_rate": 0.00017444659190372805,
      "loss": 0.4490911865234375,
      "step": 600
    },
    {
      "epoch": 1.6447187928669411,
      "eval_loss": 0.5405105948448181,
      "eval_runtime": 464.3862,
      "eval_samples_per_second": 6.284,
      "eval_steps_per_second": 1.572,
      "step": 600
    },
    {
      "epoch": 1.9190672153635115,
      "grad_norm": 0.6907134652137756,
      "learning_rate": 0.00015772022928155024,
      "loss": 0.446926155090332,
      "step": 700
    },
    {
      "epoch": 1.9190672153635115,
      "eval_loss": 0.5273797512054443,
      "eval_runtime": 407.3892,
      "eval_samples_per_second": 7.163,
      "eval_steps_per_second": 1.792,
      "step": 700
    },
    {
      "epoch": 2.1920438957475996,
      "grad_norm": 0.8313947319984436,
      "learning_rate": 0.00013940813959975931,
      "loss": 0.3268693161010742,
      "step": 800
    },
    {
      "epoch": 2.1920438957475996,
      "eval_loss": 0.5782487392425537,
      "eval_runtime": 408.7224,
      "eval_samples_per_second": 7.139,
      "eval_steps_per_second": 1.786,
      "step": 800
    },
    {
      "epoch": 2.46639231824417,
      "grad_norm": 0.8360450267791748,
      "learning_rate": 0.0001201063376258284,
      "loss": 0.2783058738708496,
      "step": 900
    },
    {
      "epoch": 2.46639231824417,
      "eval_loss": 0.5717503428459167,
      "eval_runtime": 411.446,
      "eval_samples_per_second": 7.092,
      "eval_steps_per_second": 1.774,
      "step": 900
    },
    {
      "epoch": 2.7407407407407405,
      "grad_norm": 0.8385628461837769,
      "learning_rate": 0.00010044305089769608,
      "loss": 0.27848129272460936,
      "step": 1000
    },
    {
      "epoch": 2.7407407407407405,
      "eval_loss": 0.5624513626098633,
      "eval_runtime": 418.3409,
      "eval_samples_per_second": 6.975,
      "eval_steps_per_second": 1.745,
      "step": 1000
    },
    {
      "epoch": 3.0137174211248285,
      "grad_norm": 0.6840721368789673,
      "learning_rate": 8.10582724183826e-05,
      "loss": 0.2649513816833496,
      "step": 1100
    },
    {
      "epoch": 3.0137174211248285,
      "eval_loss": 0.6641095280647278,
      "eval_runtime": 422.9219,
      "eval_samples_per_second": 6.9,
      "eval_steps_per_second": 1.726,
      "step": 1100
    },
    {
      "epoch": 3.288065843621399,
      "grad_norm": 0.784125030040741,
      "learning_rate": 6.258293041282737e-05,
      "loss": 0.11603937149047852,
      "step": 1200
    },
    {
      "epoch": 3.288065843621399,
      "eval_loss": 0.6770608425140381,
      "eval_runtime": 415.4832,
      "eval_samples_per_second": 7.023,
      "eval_steps_per_second": 1.757,
      "step": 1200
    },
    {
      "epoch": 3.288065843621399,
      "step": 1200,
      "total_flos": 1.4071460444506644e+19,
      "train_loss": 0.43218199570973714,
      "train_runtime": 38768.0459,
      "train_samples_per_second": 3.007,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 100,
  "max_steps": 1825,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4071460444506644e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}