last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021318552470287267,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021318552470287266,
      "grad_norm": 1.3028908967971802,
      "learning_rate": 2e-05,
      "loss": 1.2808,
      "step": 1
    },
    {
      "epoch": 0.0004263710494057453,
      "grad_norm": 1.0809484720230103,
      "learning_rate": 4e-05,
      "loss": 1.2506,
      "step": 2
    },
    {
      "epoch": 0.0006395565741086181,
      "grad_norm": 1.094404697418213,
      "learning_rate": 6e-05,
      "loss": 1.3033,
      "step": 3
    },
    {
      "epoch": 0.0006395565741086181,
      "eval_loss": 1.2599997520446777,
      "eval_runtime": 108.5087,
      "eval_samples_per_second": 18.201,
      "eval_steps_per_second": 9.105,
      "step": 3
    },
    {
      "epoch": 0.0008527420988114906,
      "grad_norm": 0.8515664935112,
      "learning_rate": 8e-05,
      "loss": 1.2406,
      "step": 4
    },
    {
      "epoch": 0.0010659276235143633,
      "grad_norm": 1.2079994678497314,
      "learning_rate": 0.0001,
      "loss": 1.1894,
      "step": 5
    },
    {
      "epoch": 0.0012791131482172361,
      "grad_norm": 1.3954782485961914,
      "learning_rate": 0.00012,
      "loss": 1.2558,
      "step": 6
    },
    {
      "epoch": 0.0012791131482172361,
      "eval_loss": 1.1807987689971924,
      "eval_runtime": 111.4626,
      "eval_samples_per_second": 17.719,
      "eval_steps_per_second": 8.864,
      "step": 6
    },
    {
      "epoch": 0.0014922986729201087,
      "grad_norm": 1.2520461082458496,
      "learning_rate": 0.00014,
      "loss": 1.1799,
      "step": 7
    },
    {
      "epoch": 0.0017054841976229813,
      "grad_norm": 0.7413159608840942,
      "learning_rate": 0.00016,
      "loss": 1.1628,
      "step": 8
    },
    {
      "epoch": 0.001918669722325854,
      "grad_norm": 0.740929126739502,
      "learning_rate": 0.00018,
      "loss": 1.0792,
      "step": 9
    },
    {
      "epoch": 0.001918669722325854,
      "eval_loss": 1.0034116506576538,
      "eval_runtime": 110.8915,
      "eval_samples_per_second": 17.81,
      "eval_steps_per_second": 8.91,
      "step": 9
    },
    {
      "epoch": 0.0021318552470287267,
      "grad_norm": 0.8884080648422241,
      "learning_rate": 0.0002,
      "loss": 1.0179,
      "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": 324298258513920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}