{
  "best_metric": 0.37613359093666077,
  "best_model_checkpoint": "finetuned_models/qwen-32b-multi-stock-v1_202603051920/checkpoint-27",
  "epoch": 0.5885558583106267,
  "eval_steps": 27,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021798365122615803,
      "grad_norm": 6.165101528167725,
      "learning_rate": 7.142857142857143e-06,
      "loss": 17.3071,
      "step": 1
    },
    {
      "epoch": 0.043596730245231606,
      "grad_norm": 4.365502834320068,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 17.1928,
      "step": 2
    },
    {
      "epoch": 0.0653950953678474,
      "grad_norm": 4.507502555847168,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 17.0196,
      "step": 3
    },
    {
      "epoch": 0.08719346049046321,
      "grad_norm": 4.440822601318359,
      "learning_rate": 2.857142857142857e-05,
      "loss": 16.5418,
      "step": 4
    },
    {
      "epoch": 0.10899182561307902,
      "grad_norm": 5.166988849639893,
      "learning_rate": 3.571428571428572e-05,
      "loss": 16.7408,
      "step": 5
    },
    {
      "epoch": 0.1307901907356948,
      "grad_norm": 7.1465654373168945,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 16.0273,
      "step": 6
    },
    {
      "epoch": 0.15258855585831063,
      "grad_norm": 14.216585159301758,
      "learning_rate": 5e-05,
      "loss": 14.3316,
      "step": 7
    },
    {
      "epoch": 0.17438692098092642,
      "grad_norm": 23.32270050048828,
      "learning_rate": 4.9609375000000005e-05,
      "loss": 11.1795,
      "step": 8
    },
    {
      "epoch": 0.19618528610354224,
      "grad_norm": 18.680166244506836,
      "learning_rate": 4.921875e-05,
      "loss": 7.61,
      "step": 9
    },
    {
      "epoch": 0.21798365122615804,
      "grad_norm": 15.084885597229004,
      "learning_rate": 4.8828125e-05,
      "loss": 4.6502,
      "step": 10
    },
    {
      "epoch": 0.23978201634877383,
      "grad_norm": 17.5118408203125,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 3.3325,
      "step": 11
    },
    {
      "epoch": 0.2615803814713896,
      "grad_norm": 10.667753219604492,
      "learning_rate": 4.8046875e-05,
      "loss": 2.0176,
      "step": 12
    },
    {
      "epoch": 0.28337874659400547,
      "grad_norm": 5.880115032196045,
      "learning_rate": 4.765625e-05,
      "loss": 1.2728,
      "step": 13
    },
    {
      "epoch": 0.30517711171662126,
      "grad_norm": 3.440869092941284,
      "learning_rate": 4.7265625000000005e-05,
      "loss": 0.9443,
      "step": 14
    },
    {
      "epoch": 0.32697547683923706,
      "grad_norm": 2.7611007690429688,
      "learning_rate": 4.6875e-05,
      "loss": 0.6396,
      "step": 15
    },
    {
      "epoch": 0.34877384196185285,
      "grad_norm": 1.4035634994506836,
      "learning_rate": 4.6484375e-05,
      "loss": 0.5446,
      "step": 16
    },
    {
      "epoch": 0.37057220708446864,
      "grad_norm": 0.5275142788887024,
      "learning_rate": 4.609375e-05,
      "loss": 0.4912,
      "step": 17
    },
    {
      "epoch": 0.3923705722070845,
      "grad_norm": 0.4913148283958435,
      "learning_rate": 4.5703125e-05,
      "loss": 0.5211,
      "step": 18
    },
    {
      "epoch": 0.4141689373297003,
      "grad_norm": 0.3805868923664093,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 0.4556,
      "step": 19
    },
    {
      "epoch": 0.4359673024523161,
      "grad_norm": 0.32233572006225586,
      "learning_rate": 4.4921875e-05,
      "loss": 0.4433,
      "step": 20
    },
    {
      "epoch": 0.45776566757493187,
      "grad_norm": 0.27392125129699707,
      "learning_rate": 4.453125e-05,
      "loss": 0.4108,
      "step": 21
    },
    {
      "epoch": 0.47956403269754766,
      "grad_norm": 0.4670204818248749,
      "learning_rate": 4.4140625000000004e-05,
      "loss": 0.4149,
      "step": 22
    },
    {
      "epoch": 0.5013623978201635,
      "grad_norm": 0.2106008529663086,
      "learning_rate": 4.375e-05,
      "loss": 0.3944,
      "step": 23
    },
    {
      "epoch": 0.5231607629427792,
      "grad_norm": 0.2013174593448639,
      "learning_rate": 4.3359375e-05,
      "loss": 0.3953,
      "step": 24
    },
    {
      "epoch": 0.5449591280653951,
      "grad_norm": 0.1582355797290802,
      "learning_rate": 4.2968750000000004e-05,
      "loss": 0.3797,
      "step": 25
    },
    {
      "epoch": 0.5667574931880109,
      "grad_norm": 0.1465764045715332,
      "learning_rate": 4.2578125e-05,
      "loss": 0.3854,
      "step": 26
    },
    {
      "epoch": 0.5885558583106267,
      "grad_norm": 0.12099988013505936,
      "learning_rate": 4.21875e-05,
      "loss": 0.3565,
      "step": 27
    },
    {
      "epoch": 0.5885558583106267,
      "eval_loss": 0.37613359093666077,
      "eval_runtime": 1238.4482,
      "eval_samples_per_second": 0.296,
      "eval_steps_per_second": 0.296,
      "step": 27
    }
  ],
  "logging_steps": 1,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 27,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.5562890400484966e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}