trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 6,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2975,
      "step": 6
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.3016,
      "step": 12
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.32800790667533875,
      "learning_rate": 0.0016329931618554523,
      "loss": 1.4015,
      "step": 18
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.9177753925323486,
      "learning_rate": 0.0011547005383792518,
      "loss": 1.6273,
      "step": 24
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.3837386667728424,
      "learning_rate": 0.0008528028654224417,
      "loss": 1.4308,
      "step": 30
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.3632727861404419,
      "learning_rate": 0.0006859943405700353,
      "loss": 0.9649,
      "step": 36
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.266460120677948,
      "learning_rate": 0.0005897678246195886,
      "loss": 0.9382,
      "step": 42
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.25073757767677307,
      "learning_rate": 0.0005252257314388902,
      "loss": 0.9458,
      "step": 48
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.30845940113067627,
      "learning_rate": 0.00047809144373375746,
      "loss": 0.919,
      "step": 54
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.2834985852241516,
      "learning_rate": 0.00044172610429938616,
      "loss": 0.8865,
      "step": 60
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.24825343489646912,
      "learning_rate": 0.00041256849850351737,
      "loss": 0.9121,
      "step": 66
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.23214682936668396,
      "learning_rate": 0.0003885143449429057,
      "loss": 0.8687,
      "step": 72
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.28830835223197937,
      "learning_rate": 0.00036822984715932937,
      "loss": 0.8698,
      "step": 78
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.2312021106481552,
      "learning_rate": 0.0003508232077228117,
      "loss": 0.8551,
      "step": 84
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.2500722408294678,
      "learning_rate": 0.00033567254331867566,
      "loss": 0.8588,
      "step": 90
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.24223938584327698,
      "learning_rate": 0.00032232918561015214,
      "loss": 0.839,
      "step": 96
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.2925407886505127,
      "learning_rate": 0.0003104602102825331,
      "loss": 0.8785,
      "step": 102
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.24154560267925262,
      "learning_rate": 0.00029981267559834457,
      "loss": 0.8538,
      "step": 108
    },
    {
      "epoch": 1.0,
      "step": 110,
      "total_flos": 1.1172110162041242e+18,
      "train_loss": 1.0328993797302246,
      "train_runtime": 988.656,
      "train_samples_per_second": 14.24,
      "train_steps_per_second": 0.111
    }
  ],
  "logging_steps": 6,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1172110162041242e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}