{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1763668430335097,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003527336860670194,
      "grad_norm": 0.3190935552120209,
      "learning_rate": 1e-05,
      "loss": 2.057,
      "step": 1
    },
    {
      "epoch": 0.003527336860670194,
      "eval_loss": 2.136761426925659,
      "eval_runtime": 26.774,
      "eval_samples_per_second": 8.927,
      "eval_steps_per_second": 1.12,
      "step": 1
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 0.2545243203639984,
      "learning_rate": 2e-05,
      "loss": 2.0049,
      "step": 2
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 0.31179338693618774,
      "learning_rate": 3e-05,
      "loss": 2.213,
      "step": 3
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 0.2565617859363556,
      "learning_rate": 4e-05,
      "loss": 1.879,
      "step": 4
    },
    {
      "epoch": 0.01763668430335097,
      "grad_norm": 0.2504461705684662,
      "learning_rate": 5e-05,
      "loss": 1.903,
      "step": 5
    },
    {
      "epoch": 0.01763668430335097,
      "eval_loss": 2.126079559326172,
      "eval_runtime": 25.895,
      "eval_samples_per_second": 9.23,
      "eval_steps_per_second": 1.159,
      "step": 5
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 0.2987203598022461,
      "learning_rate": 6e-05,
      "loss": 1.9851,
      "step": 6
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.28110387921333313,
      "learning_rate": 7e-05,
      "loss": 1.9352,
      "step": 7
    },
    {
      "epoch": 0.02821869488536155,
      "grad_norm": 0.3136221170425415,
      "learning_rate": 8e-05,
      "loss": 2.1815,
      "step": 8
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.30229005217552185,
      "learning_rate": 9e-05,
      "loss": 1.8252,
      "step": 9
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": 0.3663163483142853,
      "learning_rate": 0.0001,
      "loss": 2.1421,
      "step": 10
    },
    {
      "epoch": 0.03527336860670194,
      "eval_loss": 2.0246121883392334,
      "eval_runtime": 25.9348,
      "eval_samples_per_second": 9.215,
      "eval_steps_per_second": 1.157,
      "step": 10
    },
    {
      "epoch": 0.03880070546737213,
      "grad_norm": 0.3005220890045166,
      "learning_rate": 9.98458666866564e-05,
      "loss": 2.0235,
      "step": 11
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 0.3517952859401703,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.0433,
      "step": 12
    },
    {
      "epoch": 0.04585537918871252,
      "grad_norm": 0.2727072536945343,
      "learning_rate": 9.861849601988383e-05,
      "loss": 1.8736,
      "step": 13
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.3203047215938568,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8787,
      "step": 14
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 0.24644802510738373,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8361,
      "step": 15
    },
    {
      "epoch": 0.05291005291005291,
      "eval_loss": 1.955213189125061,
      "eval_runtime": 25.9726,
      "eval_samples_per_second": 9.202,
      "eval_steps_per_second": 1.155,
      "step": 15
    },
    {
      "epoch": 0.0564373897707231,
      "grad_norm": 0.34007856249809265,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.9749,
      "step": 16
    },
    {
      "epoch": 0.059964726631393295,
      "grad_norm": 0.3507412075996399,
      "learning_rate": 9.263200821770461e-05,
      "loss": 2.0134,
      "step": 17
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.3449397385120392,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.876,
      "step": 18
    },
    {
      "epoch": 0.06701940035273368,
      "grad_norm": 0.27750808000564575,
      "learning_rate": 8.802029828000156e-05,
      "loss": 1.9032,
      "step": 19
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": 0.3935078978538513,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9907,
      "step": 20
    },
    {
      "epoch": 0.07054673721340388,
      "eval_loss": 1.9234156608581543,
      "eval_runtime": 25.958,
      "eval_samples_per_second": 9.207,
      "eval_steps_per_second": 1.156,
      "step": 20
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.3393554091453552,
      "learning_rate": 8.247240241650918e-05,
      "loss": 2.202,
      "step": 21
    },
    {
      "epoch": 0.07760141093474426,
      "grad_norm": 0.3277629017829895,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.9742,
      "step": 22
    },
    {
      "epoch": 0.08112874779541446,
      "grad_norm": 0.2576124668121338,
      "learning_rate": 7.612492823579745e-05,
      "loss": 1.6614,
      "step": 23
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 0.2996937930583954,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.9815,
      "step": 24
    },
    {
      "epoch": 0.08818342151675485,
      "grad_norm": 0.31329578161239624,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9136,
      "step": 25
    },
    {
      "epoch": 0.08818342151675485,
      "eval_loss": 1.9130897521972656,
      "eval_runtime": 25.9489,
      "eval_samples_per_second": 9.21,
      "eval_steps_per_second": 1.156,
      "step": 25
    },
    {
      "epoch": 0.09171075837742504,
      "grad_norm": 0.30482396483421326,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7513,
      "step": 26
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.30801886320114136,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.8961,
      "step": 27
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.26133787631988525,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.9043,
      "step": 28
    },
    {
      "epoch": 0.10229276895943562,
      "grad_norm": 0.2819058895111084,
      "learning_rate": 5.392295478639225e-05,
      "loss": 1.7855,
      "step": 29
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 0.312527596950531,
      "learning_rate": 5e-05,
      "loss": 1.9985,
      "step": 30
    },
    {
      "epoch": 0.10582010582010581,
      "eval_loss": 1.9047672748565674,
      "eval_runtime": 25.9486,
      "eval_samples_per_second": 9.211,
      "eval_steps_per_second": 1.156,
      "step": 30
    },
    {
      "epoch": 0.10934744268077601,
      "grad_norm": 0.3022180497646332,
      "learning_rate": 4.607704521360776e-05,
      "loss": 1.892,
      "step": 31
    },
    {
      "epoch": 0.1128747795414462,
      "grad_norm": 0.2602643370628357,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.015,
      "step": 32
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 0.29187506437301636,
      "learning_rate": 3.832773180720475e-05,
      "loss": 1.7977,
      "step": 33
    },
    {
      "epoch": 0.11992945326278659,
      "grad_norm": 0.32443922758102417,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0107,
      "step": 34
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.3862663507461548,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9873,
      "step": 35
    },
    {
      "epoch": 0.12345679012345678,
      "eval_loss": 1.9003955125808716,
      "eval_runtime": 25.9507,
      "eval_samples_per_second": 9.21,
      "eval_steps_per_second": 1.156,
      "step": 35
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.2514958381652832,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.8633,
      "step": 36
    },
    {
      "epoch": 0.13051146384479717,
      "grad_norm": 0.3014344274997711,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 1.817,
      "step": 37
    },
    {
      "epoch": 0.13403880070546736,
      "grad_norm": 0.28053081035614014,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8325,
      "step": 38
    },
    {
      "epoch": 0.13756613756613756,
      "grad_norm": 0.25218141078948975,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 1.8678,
      "step": 39
    },
    {
      "epoch": 0.14109347442680775,
      "grad_norm": 0.3820461928844452,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9818,
      "step": 40
    },
    {
      "epoch": 0.14109347442680775,
      "eval_loss": 1.8975144624710083,
      "eval_runtime": 25.9847,
      "eval_samples_per_second": 9.198,
      "eval_steps_per_second": 1.155,
      "step": 40
    },
    {
      "epoch": 0.14462081128747795,
      "grad_norm": 0.29229605197906494,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 1.7644,
      "step": 41
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.2876432538032532,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.0279,
      "step": 42
    },
    {
      "epoch": 0.15167548500881833,
      "grad_norm": 0.3308974802494049,
      "learning_rate": 7.367991782295391e-06,
      "loss": 1.9899,
      "step": 43
    },
    {
      "epoch": 0.15520282186948853,
      "grad_norm": 0.2830653488636017,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.8475,
      "step": 44
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.2673850655555725,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8772,
      "step": 45
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 1.896990180015564,
      "eval_runtime": 25.9369,
      "eval_samples_per_second": 9.215,
      "eval_steps_per_second": 1.157,
      "step": 45
    },
    {
      "epoch": 0.16225749559082892,
      "grad_norm": 0.3193882405757904,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0192,
      "step": 46
    },
    {
      "epoch": 0.1657848324514991,
      "grad_norm": 0.278481662273407,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 1.7562,
      "step": 47
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 0.3137940466403961,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.8002,
      "step": 48
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.2706012725830078,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 1.99,
      "step": 49
    },
    {
      "epoch": 0.1763668430335097,
      "grad_norm": 0.2629629671573639,
      "learning_rate": 0.0,
      "loss": 1.7014,
      "step": 50
    },
    {
      "epoch": 0.1763668430335097,
      "eval_loss": 1.8965520858764648,
      "eval_runtime": 25.9579,
      "eval_samples_per_second": 9.207,
      "eval_steps_per_second": 1.156,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.63500120529961e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}