trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.0336285829544067,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.4909,
      "step": 10
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.3877207636833191,
      "learning_rate": 9.902193239806635e-05,
      "loss": 1.2682,
      "step": 20
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.36371299624443054,
      "learning_rate": 9.432328436130493e-05,
      "loss": 1.1908,
      "step": 30
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.27169424295425415,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.1151,
      "step": 40
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.32646557688713074,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1586,
      "step": 50
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.28673896193504333,
      "learning_rate": 6.191292957115825e-05,
      "loss": 1.1778,
      "step": 60
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 0.36622354388237,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.1185,
      "step": 70
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.6359225511550903,
      "learning_rate": 3.401180377143774e-05,
      "loss": 1.1429,
      "step": 80
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.3551563024520874,
      "learning_rate": 2.141785853707607e-05,
      "loss": 1.0632,
      "step": 90
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.38739389181137085,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.0262,
      "step": 100
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.685509443283081,
      "learning_rate": 3.87400575837657e-06,
      "loss": 1.0784,
      "step": 110
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.3741980791091919,
      "learning_rate": 3.2007361901485455e-07,
      "loss": 1.0823,
      "step": 120
    },
    {
      "epoch": 2.0,
      "step": 124,
      "total_flos": 3.3413325815545856e+16,
      "train_loss": 1.1585943698883057,
      "train_runtime": 205.3538,
      "train_samples_per_second": 9.554,
      "train_steps_per_second": 0.604
    }
  ],
  "logging_steps": 10,
  "max_steps": 124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3413325815545856e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}