last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.881369329523226e-05,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.881369329523226e-06,
      "grad_norm": 33.241905212402344,
      "learning_rate": 2e-05,
      "loss": 10.4683,
      "step": 1
    },
    {
      "epoch": 8.881369329523226e-06,
      "eval_loss": 2.6784682273864746,
      "eval_runtime": 1748.0915,
      "eval_samples_per_second": 27.12,
      "eval_steps_per_second": 13.561,
      "step": 1
    },
    {
      "epoch": 1.7762738659046452e-05,
      "grad_norm": 33.4285774230957,
      "learning_rate": 4e-05,
      "loss": 12.0073,
      "step": 2
    },
    {
      "epoch": 2.6644107988569676e-05,
      "grad_norm": 26.936962127685547,
      "learning_rate": 6e-05,
      "loss": 10.546,
      "step": 3
    },
    {
      "epoch": 2.6644107988569676e-05,
      "eval_loss": 2.632350206375122,
      "eval_runtime": 1749.3146,
      "eval_samples_per_second": 27.101,
      "eval_steps_per_second": 13.551,
      "step": 3
    },
    {
      "epoch": 3.5525477318092904e-05,
      "grad_norm": 34.76826477050781,
      "learning_rate": 8e-05,
      "loss": 9.7859,
      "step": 4
    },
    {
      "epoch": 4.440684664761613e-05,
      "grad_norm": 30.317312240600586,
      "learning_rate": 0.0001,
      "loss": 11.2434,
      "step": 5
    },
    {
      "epoch": 5.328821597713935e-05,
      "grad_norm": 21.470661163330078,
      "learning_rate": 0.00012,
      "loss": 8.105,
      "step": 6
    },
    {
      "epoch": 5.328821597713935e-05,
      "eval_loss": 2.286210536956787,
      "eval_runtime": 1749.226,
      "eval_samples_per_second": 27.103,
      "eval_steps_per_second": 13.552,
      "step": 6
    },
    {
      "epoch": 6.216958530666259e-05,
      "grad_norm": 27.524154663085938,
      "learning_rate": 0.00014,
      "loss": 8.5708,
      "step": 7
    },
    {
      "epoch": 7.105095463618581e-05,
      "grad_norm": 34.48584747314453,
      "learning_rate": 0.00016,
      "loss": 9.1664,
      "step": 8
    },
    {
      "epoch": 7.993232396570903e-05,
      "grad_norm": 28.674095153808594,
      "learning_rate": 0.00018,
      "loss": 7.6291,
      "step": 9
    },
    {
      "epoch": 7.993232396570903e-05,
      "eval_loss": 1.760007619857788,
      "eval_runtime": 1751.4367,
      "eval_samples_per_second": 27.069,
      "eval_steps_per_second": 13.535,
      "step": 9
    },
    {
      "epoch": 8.881369329523226e-05,
      "grad_norm": 26.352710723876953,
      "learning_rate": 0.0002,
      "loss": 7.031,
      "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": 1927936764542976.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}