{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 7875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9292134831460674,
      "eval_f1_score": 0.9292134831460674,
      "eval_loss": 0.19579175114631653,
      "eval_runtime": 12.5946,
      "eval_samples_per_second": 70.665,
      "eval_steps_per_second": 1.112,
      "step": 315
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.682539682539683e-05,
      "loss": 0.2897,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9235955056179775,
      "eval_f1_score": 0.9235955056179775,
      "eval_loss": 0.2937149703502655,
      "eval_runtime": 12.3147,
      "eval_samples_per_second": 72.272,
      "eval_steps_per_second": 1.137,
      "step": 630
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9348314606741573,
      "eval_f1_score": 0.9348314606741573,
      "eval_loss": 0.34074461460113525,
      "eval_runtime": 12.3763,
      "eval_samples_per_second": 71.912,
      "eval_steps_per_second": 1.131,
      "step": 945
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.3650793650793655e-05,
      "loss": 0.0673,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9337078651685393,
      "eval_f1_score": 0.9337078651685393,
      "eval_loss": 0.36005520820617676,
      "eval_runtime": 12.1209,
      "eval_samples_per_second": 73.427,
      "eval_steps_per_second": 1.155,
      "step": 1260
    },
    {
      "epoch": 4.76,
      "learning_rate": 4.047619047619048e-05,
      "loss": 0.0248,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.3878713548183441,
      "eval_runtime": 12.0275,
      "eval_samples_per_second": 73.997,
      "eval_steps_per_second": 1.164,
      "step": 1575
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9404494382022472,
      "eval_f1_score": 0.9404494382022472,
      "eval_loss": 0.40726980566978455,
      "eval_runtime": 12.3482,
      "eval_samples_per_second": 72.075,
      "eval_steps_per_second": 1.134,
      "step": 1890
    },
    {
      "epoch": 6.35,
      "learning_rate": 3.730158730158731e-05,
      "loss": 0.0192,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9303370786516854,
      "eval_f1_score": 0.9303370786516854,
      "eval_loss": 0.5313782095909119,
      "eval_runtime": 11.9506,
      "eval_samples_per_second": 74.473,
      "eval_steps_per_second": 1.171,
      "step": 2205
    },
    {
      "epoch": 7.94,
      "learning_rate": 3.412698412698413e-05,
      "loss": 0.006,
      "step": 2500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.4414384067058563,
      "eval_runtime": 12.1778,
      "eval_samples_per_second": 73.084,
      "eval_steps_per_second": 1.15,
      "step": 2520
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9393258426966292,
      "eval_f1_score": 0.9393258426966292,
      "eval_loss": 0.4911651909351349,
      "eval_runtime": 12.0271,
      "eval_samples_per_second": 74.0,
      "eval_steps_per_second": 1.164,
      "step": 2835
    },
    {
      "epoch": 9.52,
      "learning_rate": 3.095238095238095e-05,
      "loss": 0.0035,
      "step": 3000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9337078651685393,
      "eval_f1_score": 0.9337078651685393,
      "eval_loss": 0.5025097727775574,
      "eval_runtime": 11.9685,
      "eval_samples_per_second": 74.362,
      "eval_steps_per_second": 1.17,
      "step": 3150
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9438202247191011,
      "eval_f1_score": 0.9438202247191011,
      "eval_loss": 0.5351067185401917,
      "eval_runtime": 12.1005,
      "eval_samples_per_second": 73.551,
      "eval_steps_per_second": 1.157,
      "step": 3465
    },
    {
      "epoch": 11.11,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0022,
      "step": 3500
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9337078651685393,
      "eval_f1_score": 0.9337078651685393,
      "eval_loss": 0.6514860987663269,
      "eval_runtime": 12.042,
      "eval_samples_per_second": 73.908,
      "eval_steps_per_second": 1.163,
      "step": 3780
    },
    {
      "epoch": 12.7,
      "learning_rate": 2.4603174603174602e-05,
      "loss": 0.0089,
      "step": 4000
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9438202247191011,
      "eval_f1_score": 0.9438202247191011,
      "eval_loss": 0.42843857407569885,
      "eval_runtime": 12.3213,
      "eval_samples_per_second": 72.232,
      "eval_steps_per_second": 1.136,
      "step": 4095
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9393258426966292,
      "eval_f1_score": 0.9393258426966292,
      "eval_loss": 0.5087563395500183,
      "eval_runtime": 12.0385,
      "eval_samples_per_second": 73.93,
      "eval_steps_per_second": 1.163,
      "step": 4410
    },
    {
      "epoch": 14.29,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.0125,
      "step": 4500
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9449438202247191,
      "eval_f1_score": 0.9449438202247191,
      "eval_loss": 0.5048856735229492,
      "eval_runtime": 11.9611,
      "eval_samples_per_second": 74.408,
      "eval_steps_per_second": 1.17,
      "step": 4725
    },
    {
      "epoch": 15.87,
      "learning_rate": 1.8253968253968254e-05,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9438202247191011,
      "eval_f1_score": 0.9438202247191011,
      "eval_loss": 0.5166943073272705,
      "eval_runtime": 11.932,
      "eval_samples_per_second": 74.589,
      "eval_steps_per_second": 1.173,
      "step": 5040
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.5239948630332947,
      "eval_runtime": 12.002,
      "eval_samples_per_second": 74.155,
      "eval_steps_per_second": 1.166,
      "step": 5355
    },
    {
      "epoch": 17.46,
      "learning_rate": 1.5079365079365079e-05,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.5701321363449097,
      "eval_runtime": 12.1342,
      "eval_samples_per_second": 73.347,
      "eval_steps_per_second": 1.154,
      "step": 5670
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9382022471910112,
      "eval_f1_score": 0.9382022471910112,
      "eval_loss": 0.5747442245483398,
      "eval_runtime": 12.1144,
      "eval_samples_per_second": 73.466,
      "eval_steps_per_second": 1.156,
      "step": 5985
    },
    {
      "epoch": 19.05,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 0.0024,
      "step": 6000
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9393258426966292,
      "eval_f1_score": 0.9393258426966292,
      "eval_loss": 0.5525947213172913,
      "eval_runtime": 12.0235,
      "eval_samples_per_second": 74.022,
      "eval_steps_per_second": 1.164,
      "step": 6300
    },
    {
      "epoch": 20.63,
      "learning_rate": 8.73015873015873e-06,
      "loss": 0.0013,
      "step": 6500
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.5538011193275452,
      "eval_runtime": 12.0212,
      "eval_samples_per_second": 74.036,
      "eval_steps_per_second": 1.165,
      "step": 6615
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.9426966292134832,
      "eval_f1_score": 0.9426966292134832,
      "eval_loss": 0.5597621202468872,
      "eval_runtime": 12.4264,
      "eval_samples_per_second": 71.622,
      "eval_steps_per_second": 1.127,
      "step": 6930
    },
    {
      "epoch": 22.22,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.9415730337078652,
      "eval_f1_score": 0.9415730337078652,
      "eval_loss": 0.5650064945220947,
      "eval_runtime": 12.6304,
      "eval_samples_per_second": 70.465,
      "eval_steps_per_second": 1.108,
      "step": 7245
    },
    {
      "epoch": 23.81,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.0,
      "step": 7500
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.9415730337078652,
      "eval_f1_score": 0.9415730337078652,
      "eval_loss": 0.5530457496643066,
      "eval_runtime": 15.9462,
      "eval_samples_per_second": 55.813,
      "eval_steps_per_second": 0.878,
      "step": 7560
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.9438202247191011,
      "eval_f1_score": 0.9438202247191011,
      "eval_loss": 0.5528258681297302,
      "eval_runtime": 12.7008,
      "eval_samples_per_second": 70.074,
      "eval_steps_per_second": 1.102,
      "step": 7875
    }
  ],
  "logging_steps": 500,
  "max_steps": 7875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 500,
  "total_flos": 934453337113386.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}