last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08525149190110827,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034100596760443308,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0068201193520886615,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.010230179028132993,
      "grad_norm": NaN,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.013640238704177323,
      "grad_norm": NaN,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.017050298380221655,
      "grad_norm": NaN,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": NaN,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.023870417732310314,
      "grad_norm": NaN,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.027280477408354646,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": NaN,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.03410059676044331,
      "grad_norm": NaN,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.03751065643648764,
      "grad_norm": NaN,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": NaN,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0443307757885763,
      "grad_norm": NaN,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.04774083546462063,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": NaN,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.05456095481670929,
      "grad_norm": NaN,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": NaN,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.06479113384484228,
      "grad_norm": NaN,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.06820119352088662,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.07161125319693094,
      "grad_norm": NaN,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07502131287297528,
      "grad_norm": NaN,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": NaN,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.08184143222506395,
      "grad_norm": NaN,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.08525149190110827,
      "grad_norm": NaN,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5146843860172800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}