last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9972648155822628,
  "eval_steps": 100,
  "global_step": 188,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05304600082884376,
      "grad_norm": 44.375,
      "learning_rate": 9.998963956030293e-07,
      "loss": 60.1259,
      "step": 10
    },
    {
      "epoch": 0.10609200165768752,
      "grad_norm": 18.46875,
      "learning_rate": 9.997927912060587e-07,
      "loss": 32.1406,
      "step": 20
    },
    {
      "epoch": 0.1591380024865313,
      "grad_norm": 14.609375,
      "learning_rate": 9.99689186809088e-07,
      "loss": 29.5838,
      "step": 30
    },
    {
      "epoch": 0.21218400331537504,
      "grad_norm": 14.71875,
      "learning_rate": 9.995855824121175e-07,
      "loss": 28.0137,
      "step": 40
    },
    {
      "epoch": 0.2652300041442188,
      "grad_norm": 21.984375,
      "learning_rate": 9.994819780151468e-07,
      "loss": 26.8252,
      "step": 50
    },
    {
      "epoch": 0.3182760049730626,
      "grad_norm": 12.4296875,
      "learning_rate": 9.993783736181764e-07,
      "loss": 26.4244,
      "step": 60
    },
    {
      "epoch": 0.37132200580190633,
      "grad_norm": 12.203125,
      "learning_rate": 9.992747692212056e-07,
      "loss": 26.1259,
      "step": 70
    },
    {
      "epoch": 0.4243680066307501,
      "grad_norm": 10.3828125,
      "learning_rate": 9.991711648242352e-07,
      "loss": 25.4777,
      "step": 80
    },
    {
      "epoch": 0.4774140074595939,
      "grad_norm": 14.0546875,
      "learning_rate": 9.990675604272645e-07,
      "loss": 25.3432,
      "step": 90
    },
    {
      "epoch": 0.5304600082884376,
      "grad_norm": 13.203125,
      "learning_rate": 9.98963956030294e-07,
      "loss": 24.9725,
      "step": 100
    },
    {
      "epoch": 0.5304600082884376,
      "eval_loss": 0.3865843713283539,
      "eval_runtime": 12.0567,
      "eval_samples_per_second": 821.122,
      "eval_steps_per_second": 25.712,
      "step": 100
    },
    {
      "epoch": 0.5835060091172813,
      "grad_norm": 13.484375,
      "learning_rate": 9.988603516333233e-07,
      "loss": 24.8423,
      "step": 110
    },
    {
      "epoch": 0.6365520099461252,
      "grad_norm": 12.78125,
      "learning_rate": 9.987567472363527e-07,
      "loss": 24.5701,
      "step": 120
    },
    {
      "epoch": 0.689598010774969,
      "grad_norm": 13.5625,
      "learning_rate": 9.98653142839382e-07,
      "loss": 24.5008,
      "step": 130
    },
    {
      "epoch": 0.7426440116038127,
      "grad_norm": 10.8046875,
      "learning_rate": 9.985495384424114e-07,
      "loss": 24.1657,
      "step": 140
    },
    {
      "epoch": 0.7956900124326565,
      "grad_norm": 15.5078125,
      "learning_rate": 9.984459340454408e-07,
      "loss": 24.2864,
      "step": 150
    },
    {
      "epoch": 0.8487360132615002,
      "grad_norm": 11.609375,
      "learning_rate": 9.983423296484702e-07,
      "loss": 24.0425,
      "step": 160
    },
    {
      "epoch": 0.901782014090344,
      "grad_norm": 11.1171875,
      "learning_rate": 9.982387252514998e-07,
      "loss": 24.1412,
      "step": 170
    },
    {
      "epoch": 0.9548280149191878,
      "grad_norm": 15.390625,
      "learning_rate": 9.98135120854529e-07,
      "loss": 23.766,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1908991489828454e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}