{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.39586764574050903,
      "learning_rate": 0.0,
      "loss": 1.4697265625,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.41085371375083923,
      "learning_rate": 6e-06,
      "loss": 1.4453125,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.41122275590896606,
      "learning_rate": 1.2e-05,
      "loss": 1.48046875,
      "step": 3
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.39023348689079285,
      "learning_rate": 1.8e-05,
      "loss": 1.416015625,
      "step": 4
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.40161392092704773,
      "learning_rate": 2.4e-05,
      "loss": 1.4052734375,
      "step": 5
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.44750726222991943,
      "learning_rate": 3e-05,
      "loss": 1.5869140625,
      "step": 6
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.4769833981990814,
      "learning_rate": 2.996711467850763e-05,
      "loss": 1.7705078125,
      "step": 7
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4416337013244629,
      "learning_rate": 2.98686189280112e-05,
      "loss": 1.5791015625,
      "step": 8
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.4315391182899475,
      "learning_rate": 2.9704992609906378e-05,
      "loss": 1.490234375,
      "step": 9
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.40553179383277893,
      "learning_rate": 2.9477032895167306e-05,
      "loss": 1.3798828125,
      "step": 10
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.625,
      "eval_runtime": 10.0659,
      "eval_samples_per_second": 0.099,
      "eval_steps_per_second": 0.099,
      "step": 10
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4546821117401123,
      "learning_rate": 2.9185850380609763e-05,
      "loss": 1.6181640625,
      "step": 11
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.41665247082710266,
      "learning_rate": 2.883286367817511e-05,
      "loss": 1.3193359375,
      "step": 12
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4286373555660248,
      "learning_rate": 2.8419792503595517e-05,
      "loss": 1.4228515625,
      "step": 13
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.4111352562904358,
      "learning_rate": 2.794864929811175e-05,
      "loss": 1.3525390625,
      "step": 14
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4331604540348053,
      "learning_rate": 2.742172942406179e-05,
      "loss": 1.40234375,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4435633420944214,
      "learning_rate": 2.6841599982106203e-05,
      "loss": 1.5166015625,
      "step": 16
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.43271249532699585,
      "learning_rate": 2.621108730457179e-05,
      "loss": 1.40625,
      "step": 17
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4287485182285309,
      "learning_rate": 2.553326318584459e-05,
      "loss": 1.4033203125,
      "step": 18
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.460796594619751,
      "learning_rate": 2.4811429916896384e-05,
      "loss": 1.517578125,
      "step": 19
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.40780723094940186,
      "learning_rate": 2.404910419685508e-05,
      "loss": 1.23046875,
      "step": 20
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.515625,
      "eval_runtime": 0.6871,
      "eval_samples_per_second": 1.455,
      "eval_steps_per_second": 1.455,
      "step": 20
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.4383203089237213,
      "learning_rate": 2.3250000000000003e-05,
      "loss": 1.3798828125,
      "step": 21
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4807707965373993,
      "learning_rate": 2.2418010481652545e-05,
      "loss": 1.6611328125,
      "step": 22
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4212561249732971,
      "learning_rate": 2.1557189011114815e-05,
      "loss": 1.2587890625,
      "step": 23
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.41202232241630554,
      "learning_rate": 2.067172942406179e-05,
      "loss": 1.23828125,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4602486491203308,
      "learning_rate": 1.9765945590595514e-05,
      "loss": 1.5322265625,
      "step": 25
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.4189227521419525,
      "learning_rate": 1.8844250398503562e-05,
      "loss": 1.2890625,
      "step": 26
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.4298189580440521,
      "learning_rate": 1.791113425411332e-05,
      "loss": 1.248046875,
      "step": 27
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.42624717950820923,
      "learning_rate": 1.6971143205483768e-05,
      "loss": 1.27734375,
      "step": 28
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.4126755893230438,
      "learning_rate": 1.6028856794516242e-05,
      "loss": 1.216796875,
      "step": 29
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.41026341915130615,
      "learning_rate": 1.5088865745886681e-05,
      "loss": 1.2021484375,
      "step": 30
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.4375,
      "eval_runtime": 0.6837,
      "eval_samples_per_second": 1.463,
      "eval_steps_per_second": 1.463,
      "step": 30
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.43846380710601807,
      "learning_rate": 1.4155749601496442e-05,
      "loss": 1.3662109375,
      "step": 31
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.4687407314777374,
      "learning_rate": 1.3234054409404486e-05,
      "loss": 1.5498046875,
      "step": 32
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.4420587122440338,
      "learning_rate": 1.2328270575938213e-05,
      "loss": 1.3623046875,
      "step": 33
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.4126286506652832,
      "learning_rate": 1.1442810988885186e-05,
      "loss": 1.2822265625,
      "step": 34
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.41790735721588135,
      "learning_rate": 1.0581989518347455e-05,
      "loss": 1.19140625,
      "step": 35
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.4591391980648041,
      "learning_rate": 9.750000000000003e-06,
      "loss": 1.41796875,
      "step": 36
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.4123469293117523,
      "learning_rate": 8.95089580314492e-06,
      "loss": 1.1376953125,
      "step": 37
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.41412708163261414,
      "learning_rate": 8.188570083103615e-06,
      "loss": 1.2451171875,
      "step": 38
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.40221884846687317,
      "learning_rate": 7.466736814155419e-06,
      "loss": 1.1884765625,
      "step": 39
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.42751839756965637,
      "learning_rate": 6.788912695428213e-06,
      "loss": 1.234375,
      "step": 40
    },
    {
      "epoch": 1.6,
      "eval_loss": 1.3984375,
      "eval_runtime": 0.6838,
      "eval_samples_per_second": 1.462,
      "eval_steps_per_second": 1.462,
      "step": 40
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.42698732018470764,
      "learning_rate": 6.158400017893799e-06,
      "loss": 1.353515625,
      "step": 41
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.4182870388031006,
      "learning_rate": 5.578270575938212e-06,
      "loss": 1.2548828125,
      "step": 42
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.4187270402908325,
      "learning_rate": 5.05135070188825e-06,
      "loss": 1.2587890625,
      "step": 43
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.45896491408348083,
      "learning_rate": 4.580207496404486e-06,
      "loss": 1.373046875,
      "step": 44
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.40531447529792786,
      "learning_rate": 4.1671363218248875e-06,
      "loss": 1.1064453125,
      "step": 45
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.42398521304130554,
      "learning_rate": 3.814149619390238e-06,
      "loss": 1.2578125,
      "step": 46
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.4653177261352539,
      "learning_rate": 3.522967104832695e-06,
      "loss": 1.5419921875,
      "step": 47
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.41158297657966614,
      "learning_rate": 3.2950073900936235e-06,
      "loss": 1.146484375,
      "step": 48
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.4061604142189026,
      "learning_rate": 3.1313810719888003e-06,
      "loss": 1.1357421875,
      "step": 49
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.45487138628959656,
      "learning_rate": 3.0328853214923737e-06,
      "loss": 1.431640625,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.390625,
      "eval_runtime": 0.6834,
      "eval_samples_per_second": 1.463,
      "eval_steps_per_second": 1.463,
      "step": 50
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6793003070914560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}