last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017248070372127117,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017248070372127117,
      "grad_norm": 0.04714099317789078,
      "learning_rate": 2e-05,
      "loss": 11.9346,
      "step": 1
    },
    {
      "epoch": 0.00017248070372127117,
      "eval_loss": 11.933449745178223,
      "eval_runtime": 8.4249,
      "eval_samples_per_second": 289.854,
      "eval_steps_per_second": 144.927,
      "step": 1
    },
    {
      "epoch": 0.00034496140744254234,
      "grad_norm": 0.038016416132450104,
      "learning_rate": 4e-05,
      "loss": 11.9327,
      "step": 2
    },
    {
      "epoch": 0.0005174421111638135,
      "grad_norm": 0.0610128715634346,
      "learning_rate": 6e-05,
      "loss": 11.9345,
      "step": 3
    },
    {
      "epoch": 0.0005174421111638135,
      "eval_loss": 11.933433532714844,
      "eval_runtime": 8.5079,
      "eval_samples_per_second": 287.028,
      "eval_steps_per_second": 143.514,
      "step": 3
    },
    {
      "epoch": 0.0006899228148850847,
      "grad_norm": 0.025043468922376633,
      "learning_rate": 8e-05,
      "loss": 11.9273,
      "step": 4
    },
    {
      "epoch": 0.0008624035186063559,
      "grad_norm": 0.04784798249602318,
      "learning_rate": 0.0001,
      "loss": 11.9414,
      "step": 5
    },
    {
      "epoch": 0.001034884222327627,
      "grad_norm": 0.04146360605955124,
      "learning_rate": 0.00012,
      "loss": 11.9318,
      "step": 6
    },
    {
      "epoch": 0.001034884222327627,
      "eval_loss": 11.933374404907227,
      "eval_runtime": 8.6107,
      "eval_samples_per_second": 283.602,
      "eval_steps_per_second": 141.801,
      "step": 6
    },
    {
      "epoch": 0.0012073649260488982,
      "grad_norm": 0.04689552262425423,
      "learning_rate": 0.00014,
      "loss": 11.9323,
      "step": 7
    },
    {
      "epoch": 0.0013798456297701694,
      "grad_norm": 0.040808454155921936,
      "learning_rate": 0.00016,
      "loss": 11.9289,
      "step": 8
    },
    {
      "epoch": 0.0015523263334914405,
      "grad_norm": 0.031402040272951126,
      "learning_rate": 0.00018,
      "loss": 11.9277,
      "step": 9
    },
    {
      "epoch": 0.0015523263334914405,
      "eval_loss": 11.933272361755371,
      "eval_runtime": 8.5761,
      "eval_samples_per_second": 284.745,
      "eval_steps_per_second": 142.372,
      "step": 9
    },
    {
      "epoch": 0.0017248070372127117,
      "grad_norm": 0.037368640303611755,
      "learning_rate": 0.0002,
      "loss": 11.9342,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}