trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.28229808807373047,
      "learning_rate": 0.0003304347826086957,
      "loss": 1.0758,
      "step": 20
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.3910837173461914,
      "learning_rate": 0.0003995221430894122,
      "loss": 0.9148,
      "step": 40
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.37663960456848145,
      "learning_rate": 0.00039758476229578745,
      "loss": 0.8888,
      "step": 60
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2441498339176178,
      "learning_rate": 0.0003941724426452488,
      "loss": 0.8392,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.32805338501930237,
      "learning_rate": 0.0003893106565618147,
      "loss": 0.8178,
      "step": 100
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.8086594939231873,
      "eval_runtime": 19.7643,
      "eval_samples_per_second": 25.298,
      "eval_steps_per_second": 3.188,
      "step": 100
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.32320863008499146,
      "learning_rate": 0.0003830356965061241,
      "loss": 0.7901,
      "step": 120
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.35026517510414124,
      "learning_rate": 0.0003753944040579839,
      "loss": 0.7661,
      "step": 140
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3722197115421295,
      "learning_rate": 0.00036644382025141837,
      "loss": 0.7126,
      "step": 160
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4616721570491791,
      "learning_rate": 0.0003562507597724135,
      "loss": 0.6517,
      "step": 180
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.40086525678634644,
      "learning_rate": 0.0003448913121979015,
      "loss": 0.6215,
      "step": 200
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.6392109394073486,
      "eval_runtime": 19.766,
      "eval_samples_per_second": 25.296,
      "eval_steps_per_second": 3.187,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1585933071855616e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}