{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013714285714285714,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022857142857142857,
      "grad_norm": 0.2346513569355011,
      "learning_rate": 9e-06,
      "loss": 3.8879,
      "step": 10
    },
    {
      "epoch": 0.00045714285714285713,
      "grad_norm": 0.22248627245426178,
      "learning_rate": 1.9e-05,
      "loss": 3.9183,
      "step": 20
    },
    {
      "epoch": 0.0006857142857142857,
      "grad_norm": 0.20896980166435242,
      "learning_rate": 2.9e-05,
      "loss": 3.8078,
      "step": 30
    },
    {
      "epoch": 0.0009142857142857143,
      "grad_norm": 0.23850908875465393,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 3.9322,
      "step": 40
    },
    {
      "epoch": 0.001142857142857143,
      "grad_norm": 0.20449857413768768,
      "learning_rate": 4.9e-05,
      "loss": 3.7764,
      "step": 50
    },
    {
      "epoch": 0.0013714285714285714,
      "grad_norm": 0.2402871549129486,
      "learning_rate": 4.9181818181818183e-05,
      "loss": 3.779,
      "step": 60
    },
    {
      "epoch": 0.0016,
      "grad_norm": 0.24396637082099915,
      "learning_rate": 4.827272727272727e-05,
      "loss": 3.778,
      "step": 70
    },
    {
      "epoch": 0.0018285714285714285,
      "grad_norm": 0.218296080827713,
      "learning_rate": 4.736363636363637e-05,
      "loss": 3.6985,
      "step": 80
    },
    {
      "epoch": 0.002057142857142857,
      "grad_norm": 0.2191750556230545,
      "learning_rate": 4.6454545454545456e-05,
      "loss": 3.7632,
      "step": 90
    },
    {
      "epoch": 0.002285714285714286,
      "grad_norm": 0.2369811236858368,
      "learning_rate": 4.5545454545454544e-05,
      "loss": 3.7226,
      "step": 100
    },
    {
      "epoch": 0.002514285714285714,
      "grad_norm": 0.2669982612133026,
      "learning_rate": 4.463636363636364e-05,
      "loss": 3.7047,
      "step": 110
    },
    {
      "epoch": 0.002742857142857143,
      "grad_norm": 0.2281678467988968,
      "learning_rate": 4.372727272727273e-05,
      "loss": 3.6731,
      "step": 120
    },
    {
      "epoch": 0.0029714285714285715,
      "grad_norm": 0.2538886070251465,
      "learning_rate": 4.281818181818182e-05,
      "loss": 3.6279,
      "step": 130
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.2365216612815857,
      "learning_rate": 4.190909090909091e-05,
      "loss": 3.6114,
      "step": 140
    },
    {
      "epoch": 0.0034285714285714284,
      "grad_norm": 0.2829030156135559,
      "learning_rate": 4.1e-05,
      "loss": 3.6339,
      "step": 150
    },
    {
      "epoch": 0.003657142857142857,
      "grad_norm": 0.28002238273620605,
      "learning_rate": 4.009090909090909e-05,
      "loss": 3.6,
      "step": 160
    },
    {
      "epoch": 0.0038857142857142857,
      "grad_norm": 0.28344056010246277,
      "learning_rate": 3.9181818181818184e-05,
      "loss": 3.6351,
      "step": 170
    },
    {
      "epoch": 0.004114285714285714,
      "grad_norm": 0.25062933564186096,
      "learning_rate": 3.827272727272728e-05,
      "loss": 3.6556,
      "step": 180
    },
    {
      "epoch": 0.004342857142857143,
      "grad_norm": 0.2557496130466461,
      "learning_rate": 3.736363636363637e-05,
      "loss": 3.6196,
      "step": 190
    },
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 0.26178061962127686,
      "learning_rate": 3.645454545454546e-05,
      "loss": 3.6541,
      "step": 200
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.24720928072929382,
      "learning_rate": 3.5545454545454545e-05,
      "loss": 3.6015,
      "step": 210
    },
    {
      "epoch": 0.005028571428571428,
      "grad_norm": 0.24621886014938354,
      "learning_rate": 3.463636363636364e-05,
      "loss": 3.5792,
      "step": 220
    },
    {
      "epoch": 0.005257142857142857,
      "grad_norm": 0.2460050880908966,
      "learning_rate": 3.372727272727273e-05,
      "loss": 3.6046,
      "step": 230
    },
    {
      "epoch": 0.005485714285714286,
      "grad_norm": 0.3001673221588135,
      "learning_rate": 3.281818181818182e-05,
      "loss": 3.5625,
      "step": 240
    },
    {
      "epoch": 0.005714285714285714,
      "grad_norm": 0.2713945209980011,
      "learning_rate": 3.190909090909091e-05,
      "loss": 3.6734,
      "step": 250
    },
    {
      "epoch": 0.005942857142857143,
      "grad_norm": 0.30158859491348267,
      "learning_rate": 3.1e-05,
      "loss": 3.6523,
      "step": 260
    },
    {
      "epoch": 0.006171428571428572,
      "grad_norm": 0.25476905703544617,
      "learning_rate": 3.0090909090909093e-05,
      "loss": 3.554,
      "step": 270
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.247573122382164,
      "learning_rate": 2.9181818181818182e-05,
      "loss": 3.6185,
      "step": 280
    },
    {
      "epoch": 0.006628571428571429,
      "grad_norm": 0.28666672110557556,
      "learning_rate": 2.8272727272727274e-05,
      "loss": 3.5647,
      "step": 290
    },
    {
      "epoch": 0.006857142857142857,
      "grad_norm": 0.2672288417816162,
      "learning_rate": 2.7363636363636362e-05,
      "loss": 3.6464,
      "step": 300
    },
    {
      "epoch": 0.0070857142857142855,
      "grad_norm": 0.27534735202789307,
      "learning_rate": 2.6454545454545454e-05,
      "loss": 3.5813,
      "step": 310
    },
    {
      "epoch": 0.007314285714285714,
      "grad_norm": 0.24681590497493744,
      "learning_rate": 2.5545454545454546e-05,
      "loss": 3.6038,
      "step": 320
    },
    {
      "epoch": 0.007542857142857143,
      "grad_norm": 0.2686510682106018,
      "learning_rate": 2.4636363636363638e-05,
      "loss": 3.5755,
      "step": 330
    },
    {
      "epoch": 0.0077714285714285715,
      "grad_norm": 0.27035024762153625,
      "learning_rate": 2.372727272727273e-05,
      "loss": 3.5517,
      "step": 340
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.28498750925064087,
      "learning_rate": 2.281818181818182e-05,
      "loss": 3.6397,
      "step": 350
    },
    {
      "epoch": 0.008228571428571429,
      "grad_norm": 0.2775673568248749,
      "learning_rate": 2.190909090909091e-05,
      "loss": 3.6033,
      "step": 360
    },
    {
      "epoch": 0.008457142857142858,
      "grad_norm": 0.29988932609558105,
      "learning_rate": 2.1e-05,
      "loss": 3.5917,
      "step": 370
    },
    {
      "epoch": 0.008685714285714286,
      "grad_norm": 0.25248634815216064,
      "learning_rate": 2.009090909090909e-05,
      "loss": 3.6374,
      "step": 380
    },
    {
      "epoch": 0.008914285714285715,
      "grad_norm": 0.2702570855617523,
      "learning_rate": 1.9181818181818183e-05,
      "loss": 3.5725,
      "step": 390
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 0.29647764563560486,
      "learning_rate": 1.8272727272727275e-05,
      "loss": 3.5781,
      "step": 400
    },
    {
      "epoch": 0.009371428571428572,
      "grad_norm": 0.2612384259700775,
      "learning_rate": 1.7363636363636366e-05,
      "loss": 3.5935,
      "step": 410
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.24550645053386688,
      "learning_rate": 1.6454545454545455e-05,
      "loss": 3.5511,
      "step": 420
    },
    {
      "epoch": 0.009828571428571428,
      "grad_norm": 0.3067398965358734,
      "learning_rate": 1.5545454545454547e-05,
      "loss": 3.6077,
      "step": 430
    },
    {
      "epoch": 0.010057142857142857,
      "grad_norm": 0.2859310507774353,
      "learning_rate": 1.4636363636363637e-05,
      "loss": 3.5567,
      "step": 440
    },
    {
      "epoch": 0.010285714285714285,
      "grad_norm": 0.34277746081352234,
      "learning_rate": 1.3727272727272727e-05,
      "loss": 3.5546,
      "step": 450
    },
    {
      "epoch": 0.010514285714285714,
      "grad_norm": 0.31543368101119995,
      "learning_rate": 1.2818181818181818e-05,
      "loss": 3.5976,
      "step": 460
    },
    {
      "epoch": 0.010742857142857143,
      "grad_norm": 0.2583160698413849,
      "learning_rate": 1.190909090909091e-05,
      "loss": 3.566,
      "step": 470
    },
    {
      "epoch": 0.010971428571428571,
      "grad_norm": 0.2528459131717682,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 3.667,
      "step": 480
    },
    {
      "epoch": 0.0112,
      "grad_norm": 0.26343825459480286,
      "learning_rate": 1.0090909090909092e-05,
      "loss": 3.5792,
      "step": 490
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 0.26427048444747925,
      "learning_rate": 9.181818181818182e-06,
      "loss": 3.5028,
      "step": 500
    },
    {
      "epoch": 0.011657142857142857,
      "grad_norm": 0.3029393255710602,
      "learning_rate": 8.272727272727274e-06,
      "loss": 3.6024,
      "step": 510
    },
    {
      "epoch": 0.011885714285714286,
      "grad_norm": 0.2847612500190735,
      "learning_rate": 7.363636363636364e-06,
      "loss": 3.5887,
      "step": 520
    },
    {
      "epoch": 0.012114285714285715,
      "grad_norm": 0.2795548439025879,
      "learning_rate": 6.454545454545455e-06,
      "loss": 3.5564,
      "step": 530
    },
    {
      "epoch": 0.012342857142857143,
      "grad_norm": 0.2452515810728073,
      "learning_rate": 5.545454545454546e-06,
      "loss": 3.5679,
      "step": 540
    },
    {
      "epoch": 0.012571428571428572,
      "grad_norm": 0.27698689699172974,
      "learning_rate": 4.636363636363636e-06,
      "loss": 3.6436,
      "step": 550
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.286603718996048,
      "learning_rate": 3.727272727272727e-06,
      "loss": 3.5336,
      "step": 560
    },
    {
      "epoch": 0.01302857142857143,
      "grad_norm": 0.2752152681350708,
      "learning_rate": 2.8181818181818185e-06,
      "loss": 3.5525,
      "step": 570
    },
    {
      "epoch": 0.013257142857142858,
      "grad_norm": 0.28077051043510437,
      "learning_rate": 1.9090909090909095e-06,
      "loss": 3.6844,
      "step": 580
    },
    {
      "epoch": 0.013485714285714285,
      "grad_norm": 0.31142348051071167,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.557,
      "step": 590
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.29399439692497253,
      "learning_rate": 9.090909090909091e-08,
      "loss": 3.5452,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2571449548492800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}