last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00018890200708382527,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.8890200708382528e-05,
      "grad_norm": 0.014951430261135101,
      "learning_rate": 2e-05,
      "loss": 11.9301,
      "step": 1
    },
    {
      "epoch": 1.8890200708382528e-05,
      "eval_loss": 11.932638168334961,
      "eval_runtime": 201.8317,
      "eval_samples_per_second": 55.219,
      "eval_steps_per_second": 55.219,
      "step": 1
    },
    {
      "epoch": 3.7780401416765056e-05,
      "grad_norm": 0.015548283234238625,
      "learning_rate": 4e-05,
      "loss": 11.9334,
      "step": 2
    },
    {
      "epoch": 5.667060212514758e-05,
      "grad_norm": 0.010655771009624004,
      "learning_rate": 6e-05,
      "loss": 11.9315,
      "step": 3
    },
    {
      "epoch": 5.667060212514758e-05,
      "eval_loss": 11.932629585266113,
      "eval_runtime": 201.841,
      "eval_samples_per_second": 55.217,
      "eval_steps_per_second": 55.217,
      "step": 3
    },
    {
      "epoch": 7.556080283353011e-05,
      "grad_norm": 0.013106192462146282,
      "learning_rate": 8e-05,
      "loss": 11.9302,
      "step": 4
    },
    {
      "epoch": 9.445100354191263e-05,
      "grad_norm": 0.014484177343547344,
      "learning_rate": 0.0001,
      "loss": 11.9311,
      "step": 5
    },
    {
      "epoch": 0.00011334120425029516,
      "grad_norm": 0.010746832937002182,
      "learning_rate": 0.00012,
      "loss": 11.9321,
      "step": 6
    },
    {
      "epoch": 0.00011334120425029516,
      "eval_loss": 11.932599067687988,
      "eval_runtime": 201.8585,
      "eval_samples_per_second": 55.212,
      "eval_steps_per_second": 55.212,
      "step": 6
    },
    {
      "epoch": 0.0001322314049586777,
      "grad_norm": 0.008842287585139275,
      "learning_rate": 0.00014,
      "loss": 11.9327,
      "step": 7
    },
    {
      "epoch": 0.00015112160566706023,
      "grad_norm": 0.01369584258645773,
      "learning_rate": 0.00016,
      "loss": 11.9357,
      "step": 8
    },
    {
      "epoch": 0.00017001180637544273,
      "grad_norm": 0.014142693020403385,
      "learning_rate": 0.00018,
      "loss": 11.9336,
      "step": 9
    },
    {
      "epoch": 0.00017001180637544273,
      "eval_loss": 11.932548522949219,
      "eval_runtime": 201.9216,
      "eval_samples_per_second": 55.195,
      "eval_steps_per_second": 55.195,
      "step": 9
    },
    {
      "epoch": 0.00018890200708382527,
      "grad_norm": 0.013265196233987808,
      "learning_rate": 0.0002,
      "loss": 11.9353,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7494696960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}