checkpoint-405/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 405,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.24764642119407654,
      "learning_rate": 1.9984268150178167e-06,
      "loss": 0.4454,
      "step": 20
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.16292472183704376,
      "learning_rate": 1.976679926364567e-06,
      "loss": 0.4486,
      "step": 40
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.23981738090515137,
      "learning_rate": 1.9298944480495172e-06,
      "loss": 0.4176,
      "step": 60
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.25884947180747986,
      "learning_rate": 1.8592697928608701e-06,
      "loss": 0.4354,
      "step": 80
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.24895012378692627,
      "learning_rate": 1.7666165250516003e-06,
      "loss": 0.4689,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2755189836025238,
      "learning_rate": 1.6543099439299843e-06,
      "loss": 0.4721,
      "step": 120
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.24769575893878937,
      "learning_rate": 1.5252291896576213e-06,
      "loss": 0.4476,
      "step": 140
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.2432471662759781,
      "learning_rate": 1.3826834323650898e-06,
      "loss": 0.4631,
      "step": 160
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.2844541072845459,
      "learning_rate": 1.2303270368330437e-06,
      "loss": 0.4249,
      "step": 180
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.30305707454681396,
      "learning_rate": 1.0720658776137296e-06,
      "loss": 0.4358,
      "step": 200
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.2243204116821289,
      "learning_rate": 9.119572063390548e-07,
      "loss": 0.4057,
      "step": 220
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.2798885405063629,
      "learning_rate": 7.541056382602656e-07,
      "loss": 0.46,
      "step": 240
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.2705991566181183,
      "learning_rate": 6.025579245533673e-07,
      "loss": 0.4226,
      "step": 260
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.30190983414649963,
      "learning_rate": 4.611992080530396e-07,
      "loss": 0.4285,
      "step": 280
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.3848233222961426,
      "learning_rate": 3.3365342204799606e-07,
      "loss": 0.4546,
      "step": 300
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3378937244415283,
      "learning_rate": 2.231903855574101e-07,
      "loss": 0.4314,
      "step": 320
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.3310483396053314,
      "learning_rate": 1.3264197683414912e-07,
      "loss": 0.4168,
      "step": 340
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3315976560115814,
      "learning_rate": 6.432953410719677e-08,
      "loss": 0.4389,
      "step": 360
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.29953354597091675,
      "learning_rate": 2.0004344749277036e-08,
      "loss": 0.4036,
      "step": 380
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.32311904430389404,
      "learning_rate": 8.027485151603786e-10,
      "loss": 0.4419,
      "step": 400
    }
  ],
  "logging_steps": 20,
  "max_steps": 405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 135,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.753047941650842e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}