{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 2.9437830448150635,
      "learning_rate": 9.818181818181818e-05,
      "loss": 0.2953,
      "step": 10
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 5.8472676277160645,
      "learning_rate": 9.636363636363637e-05,
      "loss": 0.349,
      "step": 20
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 2.7091057300567627,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.2583,
      "step": 30
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 3.0798821449279785,
      "learning_rate": 9.272727272727273e-05,
      "loss": 0.2806,
      "step": 40
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.9187162518501282,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.3229,
      "step": 50
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.0290968418121338,
      "learning_rate": 8.90909090909091e-05,
      "loss": 0.271,
      "step": 60
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.4106591939926147,
      "learning_rate": 8.727272727272727e-05,
      "loss": 0.3005,
      "step": 70
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.5027103424072266,
      "learning_rate": 8.545454545454545e-05,
      "loss": 0.3279,
      "step": 80
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.4250562191009521,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.261,
      "step": 90
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.6990318298339844,
      "learning_rate": 8.181818181818183e-05,
      "loss": 0.3056,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4321504831314087,
      "learning_rate": 8e-05,
      "loss": 0.3135,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.26422303915023804,
      "eval_mse": 0.26422300934791565,
      "eval_runtime": 146.8663,
      "eval_samples_per_second": 5.992,
      "eval_steps_per_second": 0.191,
      "step": 110
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.3414746522903442,
      "learning_rate": 7.818181818181818e-05,
      "loss": 0.2876,
      "step": 120
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 2.420074939727783,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.2263,
      "step": 130
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.7859795093536377,
      "learning_rate": 7.454545454545455e-05,
      "loss": 0.2656,
      "step": 140
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.711840033531189,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.3181,
      "step": 150
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.9030543565750122,
      "learning_rate": 7.090909090909092e-05,
      "loss": 0.2948,
      "step": 160
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 4.079201698303223,
      "learning_rate": 6.90909090909091e-05,
      "loss": 0.3092,
      "step": 170
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.5639630556106567,
      "learning_rate": 6.727272727272727e-05,
      "loss": 0.3237,
      "step": 180
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 1.0921226739883423,
      "learning_rate": 6.545454545454546e-05,
      "loss": 0.2761,
      "step": 190
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.2289607524871826,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.2839,
      "step": 200
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 7.732837677001953,
      "learning_rate": 6.181818181818182e-05,
      "loss": 0.3596,
      "step": 210
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0822261571884155,
      "learning_rate": 6e-05,
      "loss": 0.2541,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2631426453590393,
      "eval_mse": 0.2631426453590393,
      "eval_runtime": 144.7981,
      "eval_samples_per_second": 6.077,
      "eval_steps_per_second": 0.193,
      "step": 220
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 7.311972618103027,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.2924,
      "step": 230
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 2.816499948501587,
      "learning_rate": 5.636363636363636e-05,
      "loss": 0.2654,
      "step": 240
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 2.1038618087768555,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.3056,
      "step": 250
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 2.7272915840148926,
      "learning_rate": 5.272727272727272e-05,
      "loss": 0.2994,
      "step": 260
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 1.5483731031417847,
      "learning_rate": 5.090909090909091e-05,
      "loss": 0.2938,
      "step": 270
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.6636422872543335,
      "learning_rate": 4.909090909090909e-05,
      "loss": 0.2762,
      "step": 280
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 2.477865219116211,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 0.3129,
      "step": 290
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 2.1476693153381348,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.2656,
      "step": 300
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 1.3794795274734497,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.2629,
      "step": 310
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.8552964925765991,
      "learning_rate": 4.181818181818182e-05,
      "loss": 0.2593,
      "step": 320
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4841196537017822,
      "learning_rate": 4e-05,
      "loss": 0.2589,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2576321065425873,
      "eval_mse": 0.2576321065425873,
      "eval_runtime": 145.7562,
      "eval_samples_per_second": 6.037,
      "eval_steps_per_second": 0.192,
      "step": 330
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 3.3481814861297607,
      "learning_rate": 3.818181818181819e-05,
      "loss": 0.267,
      "step": 340
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 1.704964280128479,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.2177,
      "step": 350
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 1.3325728178024292,
      "learning_rate": 3.454545454545455e-05,
      "loss": 0.2815,
      "step": 360
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 2.831594705581665,
      "learning_rate": 3.272727272727273e-05,
      "loss": 0.2813,
      "step": 370
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 1.7833585739135742,
      "learning_rate": 3.090909090909091e-05,
      "loss": 0.2745,
      "step": 380
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 2.4361367225646973,
      "learning_rate": 2.909090909090909e-05,
      "loss": 0.3067,
      "step": 390
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 1.7597070932388306,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.2706,
      "step": 400
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 2.5651698112487793,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.2742,
      "step": 410
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 1.827591896057129,
      "learning_rate": 2.3636363636363637e-05,
      "loss": 0.2732,
      "step": 420
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 3.2626404762268066,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.2653,
      "step": 430
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.742932081222534,
      "learning_rate": 2e-05,
      "loss": 0.3396,
      "step": 440
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2595486342906952,
      "eval_mse": 0.2595486640930176,
      "eval_runtime": 142.819,
      "eval_samples_per_second": 6.162,
      "eval_steps_per_second": 0.196,
      "step": 440
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 1.4092158079147339,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.2322,
      "step": 450
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 4.581083297729492,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.3015,
      "step": 460
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 1.8915051221847534,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 0.2979,
      "step": 470
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 2.127157688140869,
      "learning_rate": 1.2727272727272727e-05,
      "loss": 0.2525,
      "step": 480
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 3.3702645301818848,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.2603,
      "step": 490
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 2.1041481494903564,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.2564,
      "step": 500
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 2.5933034420013428,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.2677,
      "step": 510
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 2.349623918533325,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.2752,
      "step": 520
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 5.803585529327393,
      "learning_rate": 3.636363636363636e-06,
      "loss": 0.2943,
      "step": 530
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 1.2074114084243774,
      "learning_rate": 1.818181818181818e-06,
      "loss": 0.2917,
      "step": 540
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.9745060801506042,
      "learning_rate": 0.0,
      "loss": 0.2587,
      "step": 550
    }
  ],
  "logging_steps": 10,
  "max_steps": 550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}