{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 1,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 32.508975982666016,
      "learning_rate": 2.5e-05,
      "loss": 1.9242,
      "step": 1
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.845262050628662,
      "eval_runtime": 1.664,
      "eval_samples_per_second": 37.261,
      "eval_steps_per_second": 1.202,
      "step": 1
    },
    {
      "epoch": 0.5,
      "grad_norm": 31.633163452148438,
      "learning_rate": 5e-05,
      "loss": 1.8427,
      "step": 2
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.8311964273452759,
      "eval_runtime": 1.6638,
      "eval_samples_per_second": 37.264,
      "eval_steps_per_second": 1.202,
      "step": 2
    },
    {
      "epoch": 0.75,
      "grad_norm": 32.75844192504883,
      "learning_rate": 4.868421052631579e-05,
      "loss": 1.811,
      "step": 3
    },
    {
      "epoch": 0.75,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.7797694206237793,
      "eval_runtime": 1.6596,
      "eval_samples_per_second": 37.359,
      "eval_steps_per_second": 1.205,
      "step": 3
    },
    {
      "epoch": 1.0,
      "grad_norm": 33.511817932128906,
      "learning_rate": 4.736842105263158e-05,
      "loss": 1.9235,
      "step": 4
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.7310200929641724,
      "eval_runtime": 1.6611,
      "eval_samples_per_second": 37.325,
      "eval_steps_per_second": 1.204,
      "step": 4
    },
    {
      "epoch": 1.25,
      "grad_norm": 30.517168045043945,
      "learning_rate": 4.605263157894737e-05,
      "loss": 1.6903,
      "step": 5
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.6759703159332275,
      "eval_runtime": 1.6597,
      "eval_samples_per_second": 37.357,
      "eval_steps_per_second": 1.205,
      "step": 5
    },
    {
      "epoch": 1.5,
      "grad_norm": 29.271242141723633,
      "learning_rate": 4.473684210526316e-05,
      "loss": 1.6032,
      "step": 6
    },
    {
      "epoch": 1.5,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.620038390159607,
      "eval_runtime": 1.6099,
      "eval_samples_per_second": 38.511,
      "eval_steps_per_second": 1.242,
      "step": 6
    },
    {
      "epoch": 1.75,
      "grad_norm": 31.15843963623047,
      "learning_rate": 4.342105263157895e-05,
      "loss": 1.7522,
      "step": 7
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.5599325895309448,
      "eval_runtime": 1.6096,
      "eval_samples_per_second": 38.518,
      "eval_steps_per_second": 1.243,
      "step": 7
    },
    {
      "epoch": 2.0,
      "grad_norm": 32.795101165771484,
      "learning_rate": 4.210526315789474e-05,
      "loss": 1.665,
      "step": 8
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.5007245540618896,
      "eval_runtime": 1.6593,
      "eval_samples_per_second": 37.365,
      "eval_steps_per_second": 1.205,
      "step": 8
    },
    {
      "epoch": 2.25,
      "grad_norm": 24.919414520263672,
      "learning_rate": 4.078947368421053e-05,
      "loss": 1.4334,
      "step": 9
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.4376260042190552,
      "eval_runtime": 1.6592,
      "eval_samples_per_second": 37.367,
      "eval_steps_per_second": 1.205,
      "step": 9
    },
    {
      "epoch": 2.5,
      "grad_norm": 26.314369201660156,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 1.4499,
      "step": 10
    },
    {
      "epoch": 2.5,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.3746062517166138,
      "eval_runtime": 1.659,
      "eval_samples_per_second": 37.372,
      "eval_steps_per_second": 1.206,
      "step": 10
    },
    {
      "epoch": 2.75,
      "grad_norm": 29.581968307495117,
      "learning_rate": 3.815789473684211e-05,
      "loss": 1.4751,
      "step": 11
    },
    {
      "epoch": 2.75,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.3099955320358276,
      "eval_runtime": 1.6591,
      "eval_samples_per_second": 37.37,
      "eval_steps_per_second": 1.205,
      "step": 11
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.594392776489258,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 1.2184,
      "step": 12
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.2490864992141724,
      "eval_runtime": 1.6592,
      "eval_samples_per_second": 37.368,
      "eval_steps_per_second": 1.205,
      "step": 12
    },
    {
      "epoch": 3.25,
      "grad_norm": 21.464380264282227,
      "learning_rate": 3.5526315789473684e-05,
      "loss": 1.1918,
      "step": 13
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.1868385076522827,
      "eval_runtime": 1.6597,
      "eval_samples_per_second": 37.355,
      "eval_steps_per_second": 1.205,
      "step": 13
    },
    {
      "epoch": 3.5,
      "grad_norm": 23.22657585144043,
      "learning_rate": 3.421052631578947e-05,
      "loss": 1.2961,
      "step": 14
    },
    {
      "epoch": 3.5,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.1285125017166138,
      "eval_runtime": 1.6596,
      "eval_samples_per_second": 37.359,
      "eval_steps_per_second": 1.205,
      "step": 14
    },
    {
      "epoch": 3.75,
      "grad_norm": 20.130626678466797,
      "learning_rate": 3.289473684210527e-05,
      "loss": 1.058,
      "step": 15
    },
    {
      "epoch": 3.75,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.0760616064071655,
      "eval_runtime": 1.6629,
      "eval_samples_per_second": 37.284,
      "eval_steps_per_second": 1.203,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.751522064208984,
      "learning_rate": 3.157894736842105e-05,
      "loss": 1.0431,
      "step": 16
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 1.027753233909607,
      "eval_runtime": 1.6593,
      "eval_samples_per_second": 37.365,
      "eval_steps_per_second": 1.205,
      "step": 16
    },
    {
      "epoch": 4.25,
      "grad_norm": 21.63219451904297,
      "learning_rate": 3.0263157894736844e-05,
      "loss": 1.1025,
      "step": 17
    },
    {
      "epoch": 4.25,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 0.9908801913261414,
      "eval_runtime": 1.6593,
      "eval_samples_per_second": 37.364,
      "eval_steps_per_second": 1.205,
      "step": 17
    },
    {
      "epoch": 4.5,
      "grad_norm": 10.896172523498535,
      "learning_rate": 2.8947368421052634e-05,
      "loss": 1.027,
      "step": 18
    },
    {
      "epoch": 4.5,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.25513196480938416,
      "eval_loss": 0.9616305232048035,
      "eval_runtime": 1.6609,
      "eval_samples_per_second": 37.328,
      "eval_steps_per_second": 1.204,
      "step": 18
    },
    {
      "epoch": 4.75,
      "grad_norm": 10.560508728027344,
      "learning_rate": 2.7631578947368426e-05,
      "loss": 0.9494,
      "step": 19
    },
    {
      "epoch": 4.75,
      "eval_accuracy": 0.4838709677419355,
      "eval_f1": 0.26990838618745594,
      "eval_loss": 0.9417527914047241,
      "eval_runtime": 1.6591,
      "eval_samples_per_second": 37.369,
      "eval_steps_per_second": 1.205,
      "step": 19
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.201696395874023,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.8845,
      "step": 20
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.532258064516129,
      "eval_f1": 0.32762030323005936,
      "eval_loss": 0.9292937517166138,
      "eval_runtime": 1.6591,
      "eval_samples_per_second": 37.371,
      "eval_steps_per_second": 1.206,
      "step": 20
    },
    {
      "epoch": 5.25,
      "grad_norm": 3.4469192028045654,
      "learning_rate": 2.5e-05,
      "loss": 1.0096,
      "step": 21
    },
    {
      "epoch": 5.25,
      "eval_accuracy": 0.5967741935483871,
      "eval_f1": 0.4066193853427896,
      "eval_loss": 0.9209141731262207,
      "eval_runtime": 1.6594,
      "eval_samples_per_second": 37.363,
      "eval_steps_per_second": 1.205,
      "step": 21
    },
    {
      "epoch": 5.5,
      "grad_norm": 5.117708683013916,
      "learning_rate": 2.368421052631579e-05,
      "loss": 0.8488,
      "step": 22
    },
    {
      "epoch": 5.5,
      "eval_accuracy": 0.6290322580645161,
      "eval_f1": 0.434640522875817,
      "eval_loss": 0.9170079231262207,
      "eval_runtime": 1.6597,
      "eval_samples_per_second": 37.356,
      "eval_steps_per_second": 1.205,
      "step": 22
    },
    {
      "epoch": 5.75,
      "grad_norm": 4.267374515533447,
      "learning_rate": 2.236842105263158e-05,
      "loss": 0.847,
      "step": 23
    },
    {
      "epoch": 5.75,
      "eval_accuracy": 0.6129032258064516,
      "eval_f1": 0.41979655712050085,
      "eval_loss": 0.9126449227333069,
      "eval_runtime": 1.6593,
      "eval_samples_per_second": 37.364,
      "eval_steps_per_second": 1.205,
      "step": 23
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.23488712310791,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.8127,
      "step": 24
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3648484848484848,
      "eval_loss": 0.9107705354690552,
      "eval_runtime": 1.6606,
      "eval_samples_per_second": 37.337,
      "eval_steps_per_second": 1.204,
      "step": 24
    },
    {
      "epoch": 6.25,
      "grad_norm": 6.90617561340332,
      "learning_rate": 1.9736842105263158e-05,
      "loss": 0.8793,
      "step": 25
    },
    {
      "epoch": 6.25,
      "eval_accuracy": 0.5161290322580645,
      "eval_f1": 0.34080808080808084,
      "eval_loss": 0.9092269539833069,
      "eval_runtime": 1.6621,
      "eval_samples_per_second": 37.302,
      "eval_steps_per_second": 1.203,
      "step": 25
    },
    {
      "epoch": 6.5,
      "grad_norm": 3.975435733795166,
      "learning_rate": 1.8421052631578947e-05,
      "loss": 0.8219,
      "step": 26
    },
    {
      "epoch": 6.5,
      "eval_accuracy": 0.532258064516129,
      "eval_f1": 0.35006119951040393,
      "eval_loss": 0.9109280705451965,
      "eval_runtime": 1.6614,
      "eval_samples_per_second": 37.318,
      "eval_steps_per_second": 1.204,
      "step": 26
    },
    {
      "epoch": 6.75,
      "grad_norm": 4.9610748291015625,
      "learning_rate": 1.7105263157894737e-05,
      "loss": 0.8406,
      "step": 27
    },
    {
      "epoch": 6.75,
      "eval_accuracy": 0.5161290322580645,
      "eval_f1": 0.34080808080808084,
      "eval_loss": 0.9092269539833069,
      "eval_runtime": 1.6609,
      "eval_samples_per_second": 37.33,
      "eval_steps_per_second": 1.204,
      "step": 27
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.729252815246582,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 0.9318,
      "step": 28
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.532258064516129,
      "eval_f1": 0.3553553553553554,
      "eval_loss": 0.9079668521881104,
      "eval_runtime": 1.6613,
      "eval_samples_per_second": 37.321,
      "eval_steps_per_second": 1.204,
      "step": 28
    },
    {
      "epoch": 7.25,
      "grad_norm": 5.042109489440918,
      "learning_rate": 1.4473684210526317e-05,
      "loss": 0.9478,
      "step": 29
    },
    {
      "epoch": 7.25,
      "eval_accuracy": 0.532258064516129,
      "eval_f1": 0.3553553553553554,
      "eval_loss": 0.9087701439857483,
      "eval_runtime": 1.661,
      "eval_samples_per_second": 37.327,
      "eval_steps_per_second": 1.204,
      "step": 29
    },
    {
      "epoch": 7.5,
      "grad_norm": 4.453703880310059,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.8433,
      "step": 30
    },
    {
      "epoch": 7.5,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.36946595195552906,
      "eval_loss": 0.9084787964820862,
      "eval_runtime": 1.6611,
      "eval_samples_per_second": 37.325,
      "eval_steps_per_second": 1.204,
      "step": 30
    },
    {
      "epoch": 7.75,
      "grad_norm": 3.1456220149993896,
      "learning_rate": 1.1842105263157895e-05,
      "loss": 0.794,
      "step": 31
    },
    {
      "epoch": 7.75,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.36946595195552906,
      "eval_loss": 0.9089512825012207,
      "eval_runtime": 1.6607,
      "eval_samples_per_second": 37.334,
      "eval_steps_per_second": 1.204,
      "step": 31
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.549348831176758,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.9746,
      "step": 32
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.36946595195552906,
      "eval_loss": 0.9065335392951965,
      "eval_runtime": 1.6609,
      "eval_samples_per_second": 37.329,
      "eval_steps_per_second": 1.204,
      "step": 32
    },
    {
      "epoch": 8.25,
      "grad_norm": 4.388298511505127,
      "learning_rate": 9.210526315789474e-06,
      "loss": 0.9246,
      "step": 33
    },
    {
      "epoch": 8.25,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.36946595195552906,
      "eval_loss": 0.9052813053131104,
      "eval_runtime": 1.661,
      "eval_samples_per_second": 37.326,
      "eval_steps_per_second": 1.204,
      "step": 33
    },
    {
      "epoch": 8.5,
      "grad_norm": 2.7072877883911133,
      "learning_rate": 7.894736842105263e-06,
      "loss": 0.7426,
      "step": 34
    },
    {
      "epoch": 8.5,
      "eval_accuracy": 0.5645161290322581,
      "eval_f1": 0.3831757289204098,
      "eval_loss": 0.9058404564857483,
      "eval_runtime": 1.661,
      "eval_samples_per_second": 37.328,
      "eval_steps_per_second": 1.204,
      "step": 34
    },
    {
      "epoch": 8.75,
      "grad_norm": 12.431721687316895,
      "learning_rate": 6.578947368421053e-06,
      "loss": 0.8438,
      "step": 35
    },
    {
      "epoch": 8.75,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9043520092964172,
      "eval_runtime": 1.6608,
      "eval_samples_per_second": 37.332,
      "eval_steps_per_second": 1.204,
      "step": 35
    },
    {
      "epoch": 9.0,
      "grad_norm": 4.142194747924805,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.8591,
      "step": 36
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9042260050773621,
      "eval_runtime": 1.6606,
      "eval_samples_per_second": 37.336,
      "eval_steps_per_second": 1.204,
      "step": 36
    },
    {
      "epoch": 9.25,
      "grad_norm": 2.2469961643218994,
      "learning_rate": 3.9473684210526315e-06,
      "loss": 0.8005,
      "step": 37
    },
    {
      "epoch": 9.25,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9043677449226379,
      "eval_runtime": 1.6601,
      "eval_samples_per_second": 37.347,
      "eval_steps_per_second": 1.205,
      "step": 37
    },
    {
      "epoch": 9.5,
      "grad_norm": 2.831308126449585,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.8354,
      "step": 38
    },
    {
      "epoch": 9.5,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9049898982048035,
      "eval_runtime": 1.6604,
      "eval_samples_per_second": 37.341,
      "eval_steps_per_second": 1.205,
      "step": 38
    },
    {
      "epoch": 9.75,
      "grad_norm": 4.90074348449707,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 0.8728,
      "step": 39
    },
    {
      "epoch": 9.75,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9037298560142517,
      "eval_runtime": 1.6599,
      "eval_samples_per_second": 37.352,
      "eval_steps_per_second": 1.205,
      "step": 39
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.8960094451904297,
      "learning_rate": 0.0,
      "loss": 0.8464,
      "step": 40
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5483870967741935,
      "eval_f1": 0.3732394366197183,
      "eval_loss": 0.9036431908607483,
      "eval_runtime": 1.6603,
      "eval_samples_per_second": 37.343,
      "eval_steps_per_second": 1.205,
      "step": 40
    },
    {
      "epoch": 10.0,
      "step": 40,
      "total_flos": 50446463926272.0,
      "train_loss": 1.1404520988464355,
      "train_runtime": 238.9505,
      "train_samples_per_second": 10.211,
      "train_steps_per_second": 0.167
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 50446463926272.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}