trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.1953125,
      "learning_rate": 2e-06,
      "loss": 0.18965322971343995,
      "step": 5
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.3046875,
      "learning_rate": 2e-06,
      "loss": 0.1927375912666321,
      "step": 10
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 1.1484375,
      "learning_rate": 2e-06,
      "loss": 0.1468045711517334,
      "step": 15
    },
    {
      "epoch": 1.5490196078431373,
      "grad_norm": 1.2265625,
      "learning_rate": 2e-06,
      "loss": 0.2005448818206787,
      "step": 20
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 2.75,
      "learning_rate": 2e-06,
      "loss": 0.1401282548904419,
      "step": 25
    },
    {
      "epoch": 2.313725490196078,
      "grad_norm": 1.1484375,
      "learning_rate": 2e-06,
      "loss": 0.13891748189926148,
      "step": 30
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 1.1796875,
      "learning_rate": 2e-06,
      "loss": 0.14018045663833617,
      "step": 35
    },
    {
      "epoch": 3.0784313725490198,
      "grad_norm": 1.1640625,
      "learning_rate": 2e-06,
      "loss": 0.17441172599792482,
      "step": 40
    },
    {
      "epoch": 3.4705882352941178,
      "grad_norm": 1.21875,
      "learning_rate": 2e-06,
      "loss": 0.17294782400131226,
      "step": 45
    },
    {
      "epoch": 3.8627450980392157,
      "grad_norm": 1.171875,
      "learning_rate": 2e-06,
      "loss": 0.19985162019729613,
      "step": 50
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.1640625,
      "learning_rate": 2e-06,
      "loss": 0.12109531164169311,
      "step": 55
    },
    {
      "epoch": 4.627450980392156,
      "grad_norm": 1.203125,
      "learning_rate": 2e-06,
      "loss": 0.1416569709777832,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.4609375,
      "learning_rate": 2e-06,
      "loss": 0.23194122314453125,
      "step": 65
    },
    {
      "epoch": 5.392156862745098,
      "grad_norm": 1.2734375,
      "learning_rate": 2e-06,
      "loss": 0.16368225812911988,
      "step": 70
    },
    {
      "epoch": 5.784313725490196,
      "grad_norm": 1.203125,
      "learning_rate": 2e-06,
      "loss": 0.16195108890533447,
      "step": 75
    },
    {
      "epoch": 6.1568627450980395,
      "grad_norm": 1.265625,
      "learning_rate": 2e-06,
      "loss": 0.14371482133865357,
      "step": 80
    },
    {
      "epoch": 6.549019607843137,
      "grad_norm": 1.2109375,
      "learning_rate": 2e-06,
      "loss": 0.1427313804626465,
      "step": 85
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.1953125,
      "learning_rate": 2e-06,
      "loss": 0.1870591640472412,
      "step": 90
    },
    {
      "epoch": 7.313725490196078,
      "grad_norm": 1.2578125,
      "learning_rate": 2e-06,
      "loss": 0.12720810174942015,
      "step": 95
    },
    {
      "epoch": 7.705882352941177,
      "grad_norm": 1.2265625,
      "learning_rate": 2e-06,
      "loss": 0.13424586057662963,
      "step": 100
    },
    {
      "epoch": 8.07843137254902,
      "grad_norm": 1.3125,
      "learning_rate": 2e-06,
      "loss": 0.1764780640602112,
      "step": 105
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.2109375,
      "learning_rate": 2e-06,
      "loss": 0.18374539613723756,
      "step": 110
    },
    {
      "epoch": 8.862745098039216,
      "grad_norm": 1.203125,
      "learning_rate": 2e-06,
      "loss": 0.08234047889709473,
      "step": 115
    },
    {
      "epoch": 9.235294117647058,
      "grad_norm": 1.2734375,
      "learning_rate": 2e-06,
      "loss": 0.12020751237869262,
      "step": 120
    },
    {
      "epoch": 9.627450980392156,
      "grad_norm": 1.2890625,
      "learning_rate": 2e-06,
      "loss": 0.14963157176971437,
      "step": 125
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.484375,
      "learning_rate": 2e-06,
      "loss": 0.1688634991645813,
      "step": 130
    },
    {
      "epoch": 10.0,
      "step": 130,
      "total_flos": 0.0,
      "train_loss": 0.1589511669599093,
      "train_runtime": 1185.4484,
      "train_samples_per_second": 3.433,
      "train_steps_per_second": 0.11
    }
  ],
  "logging_steps": 5,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}