checkpoint-1407/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998401704848162,
  "eval_steps": 500,
  "global_step": 1407,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21310602024507191,
      "grad_norm": 3.0930368900299072,
      "learning_rate": 7.092198581560284e-05,
      "loss": 2.0066,
      "step": 100
    },
    {
      "epoch": 0.42621204049014383,
      "grad_norm": 1.5248420238494873,
      "learning_rate": 9.533965244865718e-05,
      "loss": 1.2202,
      "step": 200
    },
    {
      "epoch": 0.6393180607352158,
      "grad_norm": 1.2673641443252563,
      "learning_rate": 8.744075829383887e-05,
      "loss": 1.1874,
      "step": 300
    },
    {
      "epoch": 0.8524240809802877,
      "grad_norm": 1.1734017133712769,
      "learning_rate": 7.954186413902054e-05,
      "loss": 1.1678,
      "step": 400
    },
    {
      "epoch": 1.0655301012253595,
      "grad_norm": 1.4848545789718628,
      "learning_rate": 7.164296998420222e-05,
      "loss": 1.0412,
      "step": 500
    },
    {
      "epoch": 1.2786361214704316,
      "grad_norm": 1.3286683559417725,
      "learning_rate": 6.374407582938389e-05,
      "loss": 0.8314,
      "step": 600
    },
    {
      "epoch": 1.4917421417155035,
      "grad_norm": 1.1215488910675049,
      "learning_rate": 5.584518167456556e-05,
      "loss": 0.8177,
      "step": 700
    },
    {
      "epoch": 1.7048481619605753,
      "grad_norm": 1.2876837253570557,
      "learning_rate": 4.794628751974723e-05,
      "loss": 0.8189,
      "step": 800
    },
    {
      "epoch": 1.9179541822056474,
      "grad_norm": 1.2666414976119995,
      "learning_rate": 4.004739336492891e-05,
      "loss": 0.8247,
      "step": 900
    },
    {
      "epoch": 2.131060202450719,
      "grad_norm": 1.3837511539459229,
      "learning_rate": 3.214849921011059e-05,
      "loss": 0.6754,
      "step": 1000
    },
    {
      "epoch": 2.344166222695791,
      "grad_norm": 1.3017562627792358,
      "learning_rate": 2.424960505529226e-05,
      "loss": 0.5903,
      "step": 1100
    },
    {
      "epoch": 2.557272242940863,
      "grad_norm": 1.1946550607681274,
      "learning_rate": 1.6350710900473933e-05,
      "loss": 0.5916,
      "step": 1200
    },
    {
      "epoch": 2.7703782631859353,
      "grad_norm": 1.2071906328201294,
      "learning_rate": 8.451816745655609e-06,
      "loss": 0.5928,
      "step": 1300
    },
    {
      "epoch": 2.983484283431007,
      "grad_norm": 1.1832154989242554,
      "learning_rate": 5.529225908372828e-07,
      "loss": 0.5906,
      "step": 1400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1407,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.848088742642156e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}