last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.098015192354815,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000490075961774075,
      "eval_loss": NaN,
      "eval_runtime": 20.257,
      "eval_samples_per_second": 21.227,
      "eval_steps_per_second": 10.614,
      "step": 1
    },
    {
      "epoch": 0.00490075961774075,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0098015192354815,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.014702278853222249,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.019603038470963,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.02450379808870375,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.02450379808870375,
      "eval_loss": NaN,
      "eval_runtime": 19.2564,
      "eval_samples_per_second": 22.33,
      "eval_steps_per_second": 11.165,
      "step": 50
    },
    {
      "epoch": 0.029404557706444498,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.03430531732418525,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.1023,
      "step": 70
    },
    {
      "epoch": 0.039206076941926,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 2.9289,
      "step": 80
    },
    {
      "epoch": 0.04410683655966675,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.0490075961774075,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.0490075961774075,
      "eval_loss": NaN,
      "eval_runtime": 19.2916,
      "eval_samples_per_second": 22.29,
      "eval_steps_per_second": 11.145,
      "step": 100
    },
    {
      "epoch": 0.05390835579514825,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.058809115412888996,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.06370987503062975,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.0686106346483705,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.07351139426611125,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.07351139426611125,
      "eval_loss": NaN,
      "eval_runtime": 19.2392,
      "eval_samples_per_second": 22.35,
      "eval_steps_per_second": 11.175,
      "step": 150
    },
    {
      "epoch": 0.078412153883852,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.08331291350159274,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.0882136731193335,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.09311443273707425,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.098015192354815,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.098015192354815,
      "eval_loss": NaN,
      "eval_runtime": 19.2339,
      "eval_samples_per_second": 22.356,
      "eval_steps_per_second": 11.178,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.659940467684147e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}