{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.956521739130435,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.020676065236330032,
      "learning_rate": 0.0001996917333733128,
      "loss": 1.4129,
      "num_input_tokens_seen": 16384,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.019586477428674698,
      "learning_rate": 0.00019876883405951377,
      "loss": 1.3486,
      "num_input_tokens_seen": 32768,
      "step": 2
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.01925278641283512,
      "learning_rate": 0.00019723699203976766,
      "loss": 1.394,
      "num_input_tokens_seen": 49152,
      "step": 3
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.018114449456334114,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3051,
      "num_input_tokens_seen": 65536,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.0193056408315897,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.3236,
      "num_input_tokens_seen": 81920,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.021124837920069695,
      "learning_rate": 0.0001891006524188368,
      "loss": 1.4556,
      "num_input_tokens_seen": 98304,
      "step": 6
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.02479449287056923,
      "learning_rate": 0.00018526401643540922,
      "loss": 1.3086,
      "num_input_tokens_seen": 114688,
      "step": 7
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.029818333685398102,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.1029,
      "num_input_tokens_seen": 131072,
      "step": 8
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.02648150734603405,
      "learning_rate": 0.0001760405965600031,
      "loss": 1.2992,
      "num_input_tokens_seen": 147456,
      "step": 9
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.029215380549430847,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.1914,
      "num_input_tokens_seen": 163840,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.028632890433073044,
      "learning_rate": 0.00016494480483301836,
      "loss": 1.2417,
      "num_input_tokens_seen": 180224,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.030310342088341713,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.3909,
      "num_input_tokens_seen": 196608,
      "step": 12
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.031336575746536255,
      "learning_rate": 0.0001522498564715949,
      "loss": 1.1383,
      "num_input_tokens_seen": 212992,
      "step": 13
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.034497059881687164,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.2009,
      "num_input_tokens_seen": 229376,
      "step": 14
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.03379025310277939,
      "learning_rate": 0.000138268343236509,
      "loss": 1.1918,
      "num_input_tokens_seen": 245760,
      "step": 15
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.03916629031300545,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0642,
      "num_input_tokens_seen": 262144,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.042235296219587326,
      "learning_rate": 0.00012334453638559057,
      "loss": 1.2661,
      "num_input_tokens_seen": 278528,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.03873530402779579,
      "learning_rate": 0.0001156434465040231,
      "loss": 1.0416,
      "num_input_tokens_seen": 294912,
      "step": 18
    },
    {
      "epoch": 3.3043478260869565,
      "grad_norm": 0.04076506569981575,
      "learning_rate": 0.0001078459095727845,
      "loss": 1.0564,
      "num_input_tokens_seen": 311296,
      "step": 19
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.03801592066884041,
      "learning_rate": 0.0001,
      "loss": 0.9894,
      "num_input_tokens_seen": 327680,
      "step": 20
    },
    {
      "epoch": 3.6521739130434785,
      "grad_norm": 0.04381837695837021,
      "learning_rate": 9.215409042721552e-05,
      "loss": 1.0994,
      "num_input_tokens_seen": 344064,
      "step": 21
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.0512906014919281,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.3105,
      "num_input_tokens_seen": 360448,
      "step": 22
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04802567511796951,
      "learning_rate": 7.66554636144095e-05,
      "loss": 1.0337,
      "num_input_tokens_seen": 376832,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.04690830409526825,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0329,
      "num_input_tokens_seen": 393216,
      "step": 24
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.042034752666950226,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.9724,
      "num_input_tokens_seen": 409600,
      "step": 25
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.04824018105864525,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 1.1225,
      "num_input_tokens_seen": 425984,
      "step": 26
    },
    {
      "epoch": 4.695652173913043,
      "grad_norm": 0.049554552882909775,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.95,
      "num_input_tokens_seen": 442368,
      "step": 27
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.04718406870961189,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.0672,
      "num_input_tokens_seen": 458752,
      "step": 28
    },
    {
      "epoch": 5.043478260869565,
      "grad_norm": 0.05403953045606613,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.997,
      "num_input_tokens_seen": 475136,
      "step": 29
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.05253535881638527,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.8303,
      "num_input_tokens_seen": 491520,
      "step": 30
    },
    {
      "epoch": 5.391304347826087,
      "grad_norm": 0.0478719137609005,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.8613,
      "num_input_tokens_seen": 507904,
      "step": 31
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.05444710701704025,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.8735,
      "num_input_tokens_seen": 524288,
      "step": 32
    },
    {
      "epoch": 5.739130434782608,
      "grad_norm": 0.050455138087272644,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 1.1102,
      "num_input_tokens_seen": 540672,
      "step": 33
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.056231990456581116,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2143,
      "num_input_tokens_seen": 557056,
      "step": 34
    },
    {
      "epoch": 6.086956521739131,
      "grad_norm": 0.056390367448329926,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.1449,
      "num_input_tokens_seen": 573440,
      "step": 35
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.053139008581638336,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.0676,
      "num_input_tokens_seen": 589824,
      "step": 36
    },
    {
      "epoch": 6.434782608695652,
      "grad_norm": 0.0504545122385025,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.981,
      "num_input_tokens_seen": 606208,
      "step": 37
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.051228489726781845,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.8797,
      "num_input_tokens_seen": 622592,
      "step": 38
    },
    {
      "epoch": 6.782608695652174,
      "grad_norm": 0.05340878665447235,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.8676,
      "num_input_tokens_seen": 638976,
      "step": 39
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.0532316230237484,
      "learning_rate": 0.0,
      "loss": 1.0274,
      "num_input_tokens_seen": 655360,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "num_input_tokens_seen": 655360,
      "step": 40,
      "total_flos": 3.034267760197632e+16,
      "train_loss": 1.1291589722037316,
      "train_runtime": 509.8753,
      "train_samples_per_second": 0.722,
      "train_steps_per_second": 0.078
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 655360,
  "num_train_epochs": 8,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.034267760197632e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}