{
  "best_global_step": 300,
  "best_metric": 0.3491288125514984,
  "best_model_checkpoint": "./output_training_h200/checkpoint-300",
  "epoch": 1.6129032258064515,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053763440860215055,
      "grad_norm": 0.05421804264187813,
      "learning_rate": 4.5e-06,
      "loss": 0.5785,
      "step": 10
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 0.06676478683948517,
      "learning_rate": 9.5e-06,
      "loss": 0.6234,
      "step": 20
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 0.062416791915893555,
      "learning_rate": 1.45e-05,
      "loss": 0.6716,
      "step": 30
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 0.05097672715783119,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.6736,
      "step": 40
    },
    {
      "epoch": 0.26881720430107525,
      "grad_norm": 0.03752289339900017,
      "learning_rate": 2.45e-05,
      "loss": 0.6243,
      "step": 50
    },
    {
      "epoch": 0.26881720430107525,
      "eval_loss": 0.5304985642433167,
      "eval_runtime": 1155.6426,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.151,
      "step": 50
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.0321248322725296,
      "learning_rate": 2.95e-05,
      "loss": 0.4349,
      "step": 60
    },
    {
      "epoch": 0.3763440860215054,
      "grad_norm": 0.02994599938392639,
      "learning_rate": 3.45e-05,
      "loss": 0.4682,
      "step": 70
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.03603624552488327,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.4734,
      "step": 80
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.0552607886493206,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.5035,
      "step": 90
    },
    {
      "epoch": 0.5376344086021505,
      "grad_norm": 0.04917095974087715,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.4024,
      "step": 100
    },
    {
      "epoch": 0.5376344086021505,
      "eval_loss": 0.41749581694602966,
      "eval_runtime": 1156.2817,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.151,
      "step": 100
    },
    {
      "epoch": 0.5913978494623656,
      "grad_norm": 0.043786872178316116,
      "learning_rate": 4.998549570601475e-05,
      "loss": 0.3703,
      "step": 110
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.05016686022281647,
      "learning_rate": 4.9935379012568985e-05,
      "loss": 0.4031,
      "step": 120
    },
    {
      "epoch": 0.6989247311827957,
      "grad_norm": 0.056300703436136246,
      "learning_rate": 4.984954262888182e-05,
      "loss": 0.4134,
      "step": 130
    },
    {
      "epoch": 0.7526881720430108,
      "grad_norm": 0.04982742667198181,
      "learning_rate": 4.972810951474605e-05,
      "loss": 0.4282,
      "step": 140
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.042826056480407715,
      "learning_rate": 4.957125362192794e-05,
      "loss": 0.3259,
      "step": 150
    },
    {
      "epoch": 0.8064516129032258,
      "eval_loss": 0.3815489113330841,
      "eval_runtime": 1148.3707,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.152,
      "step": 150
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.0555887334048748,
      "learning_rate": 4.937919964498302e-05,
      "loss": 0.3549,
      "step": 160
    },
    {
      "epoch": 0.9139784946236559,
      "grad_norm": 0.0595487505197525,
      "learning_rate": 4.9152222699383273e-05,
      "loss": 0.3793,
      "step": 170
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.07630524784326553,
      "learning_rate": 4.8890647927416887e-05,
      "loss": 0.3904,
      "step": 180
    },
    {
      "epoch": 1.021505376344086,
      "grad_norm": 0.054408393800258636,
      "learning_rate": 4.859485003242503e-05,
      "loss": 0.3848,
      "step": 190
    },
    {
      "epoch": 1.075268817204301,
      "grad_norm": 0.052903175354003906,
      "learning_rate": 4.8265252742042965e-05,
      "loss": 0.3173,
      "step": 200
    },
    {
      "epoch": 1.075268817204301,
      "eval_loss": 0.3656960725784302,
      "eval_runtime": 1157.3762,
      "eval_samples_per_second": 0.302,
      "eval_steps_per_second": 0.151,
      "step": 200
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 0.06489476561546326,
      "learning_rate": 4.7902328201214256e-05,
      "loss": 0.3467,
      "step": 210
    },
    {
      "epoch": 1.1827956989247312,
      "grad_norm": 0.06930793821811676,
      "learning_rate": 4.7506596295847716e-05,
      "loss": 0.3572,
      "step": 220
    },
    {
      "epoch": 1.2365591397849462,
      "grad_norm": 0.08778736740350723,
      "learning_rate": 4.7078623908085825e-05,
      "loss": 0.3915,
      "step": 230
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.07511554658412933,
      "learning_rate": 4.661902410425155e-05,
      "loss": 0.3341,
      "step": 240
    },
    {
      "epoch": 1.3440860215053765,
      "grad_norm": 0.061772529035806656,
      "learning_rate": 4.6128455256636706e-05,
      "loss": 0.3135,
      "step": 250
    },
    {
      "epoch": 1.3440860215053765,
      "eval_loss": 0.3562982678413391,
      "eval_runtime": 1141.9386,
      "eval_samples_per_second": 0.306,
      "eval_steps_per_second": 0.153,
      "step": 250
    },
    {
      "epoch": 1.3978494623655915,
      "grad_norm": 0.06834172457456589,
      "learning_rate": 4.560762010039001e-05,
      "loss": 0.347,
      "step": 260
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.07726427167654037,
      "learning_rate": 4.5057264726855765e-05,
      "loss": 0.3572,
      "step": 270
    },
    {
      "epoch": 1.5053763440860215,
      "grad_norm": 0.06627994775772095,
      "learning_rate": 4.4478177514805166e-05,
      "loss": 0.3861,
      "step": 280
    },
    {
      "epoch": 1.5591397849462365,
      "grad_norm": 0.06034032255411148,
      "learning_rate": 4.387118800109133e-05,
      "loss": 0.2919,
      "step": 290
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.07344155013561249,
      "learning_rate": 4.323716569234572e-05,
      "loss": 0.3211,
      "step": 300
    },
    {
      "epoch": 1.6129032258064515,
      "eval_loss": 0.3491288125514984,
      "eval_runtime": 1137.4889,
      "eval_samples_per_second": 0.308,
      "eval_steps_per_second": 0.154,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 930,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.695445572198904e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}