trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.3843727111816406,
      "learning_rate": 3.461538461538462e-05,
      "loss": 1.2599,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.23424459993839264,
      "learning_rate": 4.96467754629559e-05,
      "loss": 1.027,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.21692222356796265,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.9389,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.21259009838104248,
      "learning_rate": 4.364105412207914e-05,
      "loss": 0.903,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1998746693134308,
      "learning_rate": 3.830080191288342e-05,
      "loss": 0.9148,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.20056922733783722,
      "learning_rate": 3.1920887785621235e-05,
      "loss": 0.9661,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1582198441028595,
      "learning_rate": 2.5e-05,
      "loss": 0.9292,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.16498740017414093,
      "learning_rate": 1.8079112214378768e-05,
      "loss": 0.8617,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.15066607296466827,
      "learning_rate": 1.1699198087116589e-05,
      "loss": 0.855,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.16578565537929535,
      "learning_rate": 6.358945877920861e-06,
      "loss": 0.8816,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.19978666305541992,
      "learning_rate": 2.475778302439524e-06,
      "loss": 0.9036,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2261303812265396,
      "learning_rate": 3.5322453704410286e-07,
      "loss": 0.9332,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 3.087330233647104e+16,
      "train_loss": 0.9428395881652832,
      "train_runtime": 2846.4924,
      "train_samples_per_second": 1.757,
      "train_steps_per_second": 0.044
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "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": 3.087330233647104e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}