{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 3.3398852348327637,
      "learning_rate": 4.999950652140343e-05,
      "loss": 0.288,
      "num_input_tokens_seen": 1192,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.534205436706543,
      "learning_rate": 4.9998026105095405e-05,
      "loss": 0.1627,
      "num_input_tokens_seen": 2208,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.9795141220092773,
      "learning_rate": 4.999555880952023e-05,
      "loss": 0.2259,
      "num_input_tokens_seen": 3320,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.712265729904175,
      "learning_rate": 4.99921047320825e-05,
      "loss": 0.3248,
      "num_input_tokens_seen": 4536,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.0970170497894287,
      "learning_rate": 4.998766400914329e-05,
      "loss": 0.1867,
      "num_input_tokens_seen": 5960,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.16365909576416,
      "learning_rate": 4.998223681601473e-05,
      "loss": 0.1558,
      "num_input_tokens_seen": 7304,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.9363147020339966,
      "learning_rate": 4.9975823366953124e-05,
      "loss": 0.1863,
      "num_input_tokens_seen": 8744,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.874936819076538,
      "learning_rate": 4.996842391515044e-05,
      "loss": 0.1679,
      "num_input_tokens_seen": 10120,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 7.298994541168213,
      "learning_rate": 4.996003875272438e-05,
      "loss": 0.3627,
      "num_input_tokens_seen": 10816,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.7786474227905273,
      "learning_rate": 4.995066821070679e-05,
      "loss": 0.1466,
      "num_input_tokens_seen": 11920,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.9229803085327148,
      "learning_rate": 4.994031265903063e-05,
      "loss": 0.2029,
      "num_input_tokens_seen": 13216,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.230123519897461,
      "learning_rate": 4.992897250651535e-05,
      "loss": 0.1142,
      "num_input_tokens_seen": 14552,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 2.0229177474975586,
      "learning_rate": 4.991664820085074e-05,
      "loss": 0.2142,
      "num_input_tokens_seen": 15600,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.4955450296401978,
      "learning_rate": 4.990334022857932e-05,
      "loss": 0.149,
      "num_input_tokens_seen": 16744,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.070120334625244,
      "learning_rate": 4.9889049115077005e-05,
      "loss": 0.2267,
      "num_input_tokens_seen": 17424,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.16508150100708,
      "learning_rate": 4.987377542453251e-05,
      "loss": 0.1499,
      "num_input_tokens_seen": 18408,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 3.1738064289093018,
      "learning_rate": 4.9857519759924974e-05,
      "loss": 0.4279,
      "num_input_tokens_seen": 19288,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 2.7662558555603027,
      "learning_rate": 4.984028276300021e-05,
      "loss": 0.2957,
      "num_input_tokens_seen": 20336,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.4056564569473267,
      "learning_rate": 4.982206511424534e-05,
      "loss": 0.1899,
      "num_input_tokens_seen": 21528,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.4555004835128784,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.1429,
      "num_input_tokens_seen": 22680,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.6009600162506104,
      "learning_rate": 4.978269077673767e-05,
      "loss": 0.2084,
      "num_input_tokens_seen": 23800,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.1936904191970825,
      "learning_rate": 4.976153564241628e-05,
      "loss": 0.0474,
      "num_input_tokens_seen": 24784,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 2.241938829421997,
      "learning_rate": 4.9739402965066276e-05,
      "loss": 0.1757,
      "num_input_tokens_seen": 25688,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.735016942024231,
      "learning_rate": 4.971629361844785e-05,
      "loss": 0.2083,
      "num_input_tokens_seen": 27016,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.648120403289795,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.1653,
      "num_input_tokens_seen": 28200,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 2.088919162750244,
      "learning_rate": 4.96671486051967e-05,
      "loss": 0.2277,
      "num_input_tokens_seen": 29240,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.9720033407211304,
      "learning_rate": 4.9641114878724956e-05,
      "loss": 0.2262,
      "num_input_tokens_seen": 30264,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.137261390686035,
      "learning_rate": 4.9614108363230135e-05,
      "loss": 0.2119,
      "num_input_tokens_seen": 31376,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.7072184085845947,
      "learning_rate": 4.958613012488324e-05,
      "loss": 0.186,
      "num_input_tokens_seen": 32288,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.6640106439590454,
      "learning_rate": 4.9557181268217227e-05,
      "loss": 0.1381,
      "num_input_tokens_seen": 33336,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.743667721748352,
      "learning_rate": 4.952726293608335e-05,
      "loss": 0.1521,
      "num_input_tokens_seen": 35264,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3096036911010742,
      "learning_rate": 4.949637630960617e-05,
      "loss": 0.2232,
      "num_input_tokens_seen": 36496,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.943765640258789,
      "learning_rate": 4.9464522608136805e-05,
      "loss": 0.0252,
      "num_input_tokens_seen": 37312,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.8293421268463135,
      "learning_rate": 4.943170308920484e-05,
      "loss": 0.264,
      "num_input_tokens_seen": 38376,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 2.6471211910247803,
      "learning_rate": 4.939791904846869e-05,
      "loss": 0.1645,
      "num_input_tokens_seen": 39168,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.6533693075180054,
      "learning_rate": 4.9363171819664434e-05,
      "loss": 0.1802,
      "num_input_tokens_seen": 40440,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.3770309686660767,
      "learning_rate": 4.9327462774553166e-05,
      "loss": 0.2206,
      "num_input_tokens_seen": 41760,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.6882014274597168,
      "learning_rate": 4.929079332286685e-05,
      "loss": 0.2886,
      "num_input_tokens_seen": 42944,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.9799898862838745,
      "learning_rate": 4.925316491225265e-05,
      "loss": 0.1897,
      "num_input_tokens_seen": 44008,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.551802158355713,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 0.1935,
      "num_input_tokens_seen": 45168,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.0445095300674438,
      "learning_rate": 4.917503719406088e-05,
      "loss": 0.1071,
      "num_input_tokens_seen": 46432,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 3.2616090774536133,
      "learning_rate": 4.913454097083185e-05,
      "loss": 0.5737,
      "num_input_tokens_seen": 47360,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.9618259072303772,
      "learning_rate": 4.909309195725025e-05,
      "loss": 0.114,
      "num_input_tokens_seen": 49008,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.5821013450622559,
      "learning_rate": 4.905069178965215e-05,
      "loss": 0.2676,
      "num_input_tokens_seen": 50264,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.1913903951644897,
      "learning_rate": 4.900734214192358e-05,
      "loss": 0.1061,
      "num_input_tokens_seen": 51368,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.8395439386367798,
      "learning_rate": 4.89630447254344e-05,
      "loss": 0.2161,
      "num_input_tokens_seen": 52304,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.736319363117218,
      "learning_rate": 4.891780128897077e-05,
      "loss": 0.1163,
      "num_input_tokens_seen": 53712,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.5373475551605225,
      "learning_rate": 4.887161361866608e-05,
      "loss": 0.1609,
      "num_input_tokens_seen": 54704,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.3580759763717651,
      "learning_rate": 4.882448353793048e-05,
      "loss": 0.1673,
      "num_input_tokens_seen": 55880,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.0536258220672607,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.1955,
      "num_input_tokens_seen": 56784,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 56784,
  "num_train_epochs": 10,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2564102936199168.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}