trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0748502994011976,
      "grad_norm": 0.16372738778591156,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4252,
      "step": 100
    },
    {
      "epoch": 0.1497005988023952,
      "grad_norm": 0.27203845977783203,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4077,
      "step": 200
    },
    {
      "epoch": 0.2245508982035928,
      "grad_norm": 0.27170997858047485,
      "learning_rate": 6e-06,
      "loss": 2.3881,
      "step": 300
    },
    {
      "epoch": 0.2994011976047904,
      "grad_norm": 0.383687824010849,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.3753,
      "step": 400
    },
    {
      "epoch": 0.37425149700598803,
      "grad_norm": 0.4785425662994385,
      "learning_rate": 1e-05,
      "loss": 2.2923,
      "step": 500
    },
    {
      "epoch": 0.4491017964071856,
      "grad_norm": 0.5393449664115906,
      "learning_rate": 1.2e-05,
      "loss": 2.2659,
      "step": 600
    },
    {
      "epoch": 0.5239520958083832,
      "grad_norm": 0.538110077381134,
      "learning_rate": 1.4e-05,
      "loss": 2.2294,
      "step": 700
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 0.7190410494804382,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.1935,
      "step": 800
    },
    {
      "epoch": 0.6736526946107785,
      "grad_norm": 0.8610377311706543,
      "learning_rate": 1.8e-05,
      "loss": 2.1684,
      "step": 900
    },
    {
      "epoch": 0.7485029940119761,
      "grad_norm": 1.113236665725708,
      "learning_rate": 2e-05,
      "loss": 2.178,
      "step": 1000
    },
    {
      "epoch": 0.8233532934131736,
      "grad_norm": 0.762846827507019,
      "learning_rate": 1.5938201855735017e-05,
      "loss": 2.1273,
      "step": 1100
    },
    {
      "epoch": 0.8982035928143712,
      "grad_norm": 0.8103228211402893,
      "learning_rate": 7.052448255890958e-06,
      "loss": 2.148,
      "step": 1200
    },
    {
      "epoch": 0.9730538922155688,
      "grad_norm": 0.8717363476753235,
      "learning_rate": 5.611666969163243e-07,
      "loss": 2.0705,
      "step": 1300
    },
    {
      "epoch": 1.0,
      "step": 1336,
      "total_flos": 2.4464433119232e+16,
      "train_loss": 2.247535785515151,
      "train_runtime": 357.9632,
      "train_samples_per_second": 7.462,
      "train_steps_per_second": 3.732
    }
  ],
  "logging_steps": 100,
  "max_steps": 1336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4464433119232e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}