trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4851657940663174,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17452006980802792,
      "grad_norm": 0.4577705864316013,
      "learning_rate": 1.9650349650349652e-05,
      "loss": 0.4726,
      "step": 50
    },
    {
      "epoch": 0.34904013961605584,
      "grad_norm": 0.4405072488355611,
      "learning_rate": 1.9300699300699302e-05,
      "loss": 0.2237,
      "step": 100
    },
    {
      "epoch": 0.5235602094240838,
      "grad_norm": 0.3150438885523821,
      "learning_rate": 1.8951048951048952e-05,
      "loss": 0.2138,
      "step": 150
    },
    {
      "epoch": 0.6980802792321117,
      "grad_norm": 0.30186315289278887,
      "learning_rate": 1.8601398601398602e-05,
      "loss": 0.2093,
      "step": 200
    },
    {
      "epoch": 0.8726003490401396,
      "grad_norm": 0.30327449540529644,
      "learning_rate": 1.8251748251748253e-05,
      "loss": 0.2076,
      "step": 250
    },
    {
      "epoch": 1.0453752181500873,
      "grad_norm": 0.2984776116660214,
      "learning_rate": 1.7902097902097903e-05,
      "loss": 0.2021,
      "step": 300
    },
    {
      "epoch": 1.2198952879581153,
      "grad_norm": 0.25202994798548517,
      "learning_rate": 1.7552447552447553e-05,
      "loss": 0.1991,
      "step": 350
    },
    {
      "epoch": 1.3944153577661431,
      "grad_norm": 0.2723524084295508,
      "learning_rate": 1.7202797202797203e-05,
      "loss": 0.1989,
      "step": 400
    },
    {
      "epoch": 1.568935427574171,
      "grad_norm": 0.27348456375148283,
      "learning_rate": 1.6853146853146857e-05,
      "loss": 0.1987,
      "step": 450
    },
    {
      "epoch": 1.743455497382199,
      "grad_norm": 0.22659681162037162,
      "learning_rate": 1.6503496503496507e-05,
      "loss": 0.1984,
      "step": 500
    },
    {
      "epoch": 1.917975567190227,
      "grad_norm": 0.23193311758269958,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.1975,
      "step": 550
    },
    {
      "epoch": 2.0907504363001745,
      "grad_norm": 0.22310700413525822,
      "learning_rate": 1.5804195804195804e-05,
      "loss": 0.1908,
      "step": 600
    },
    {
      "epoch": 2.2652705061082026,
      "grad_norm": 0.24057729691103882,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.1888,
      "step": 650
    },
    {
      "epoch": 2.4397905759162306,
      "grad_norm": 0.21421296242562723,
      "learning_rate": 1.5104895104895105e-05,
      "loss": 0.1894,
      "step": 700
    },
    {
      "epoch": 2.614310645724258,
      "grad_norm": 0.22889632275029062,
      "learning_rate": 1.4755244755244758e-05,
      "loss": 0.1895,
      "step": 750
    },
    {
      "epoch": 2.7888307155322862,
      "grad_norm": 0.2847441489645133,
      "learning_rate": 1.4405594405594407e-05,
      "loss": 0.1893,
      "step": 800
    },
    {
      "epoch": 2.9633507853403143,
      "grad_norm": 0.2116124290570679,
      "learning_rate": 1.4055944055944057e-05,
      "loss": 0.1898,
      "step": 850
    },
    {
      "epoch": 3.136125654450262,
      "grad_norm": 0.23865228919415055,
      "learning_rate": 1.3706293706293707e-05,
      "loss": 0.1772,
      "step": 900
    },
    {
      "epoch": 3.31064572425829,
      "grad_norm": 0.23183673252551631,
      "learning_rate": 1.3356643356643357e-05,
      "loss": 0.1772,
      "step": 950
    },
    {
      "epoch": 3.4851657940663174,
      "grad_norm": 0.21432522974003418,
      "learning_rate": 1.3006993006993008e-05,
      "loss": 0.1778,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 2860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5694335991414784.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}