checkpoints/checkpoint-12/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012,
  "eval_steps": 10,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 4.1214,
      "step": 1
    },
    {
      "epoch": 0.002,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 3.042,
      "step": 2
    },
    {
      "epoch": 0.003,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 5.3238,
      "step": 3
    },
    {
      "epoch": 0.004,
      "grad_norm": 93.87274932861328,
      "learning_rate": 4.389877161664096e-05,
      "loss": 2.8373,
      "step": 4
    },
    {
      "epoch": 0.005,
      "grad_norm": 124.21831512451172,
      "learning_rate": 4.070288237343632e-05,
      "loss": 2.8763,
      "step": 5
    },
    {
      "epoch": 0.006,
      "grad_norm": 58.87308120727539,
      "learning_rate": 3.572516817658065e-05,
      "loss": 2.0074,
      "step": 6
    },
    {
      "epoch": 0.007,
      "grad_norm": 96.29996490478516,
      "learning_rate": 2.945288237343632e-05,
      "loss": 2.7286,
      "step": 7
    },
    {
      "epoch": 0.008,
      "grad_norm": 66.82034301757812,
      "learning_rate": 2.25e-05,
      "loss": 2.2965,
      "step": 8
    },
    {
      "epoch": 0.009,
      "grad_norm": 46.8690299987793,
      "learning_rate": 1.5547117626563687e-05,
      "loss": 2.6891,
      "step": 9
    },
    {
      "epoch": 0.01,
      "grad_norm": 27.221912384033203,
      "learning_rate": 9.274831823419357e-06,
      "loss": 1.7942,
      "step": 10
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.7255595922470093,
      "eval_runtime": 23.6767,
      "eval_samples_per_second": 8.447,
      "eval_steps_per_second": 1.056,
      "step": 10
    },
    {
      "epoch": 0.011,
      "grad_norm": 48.90645217895508,
      "learning_rate": 4.297117626563685e-06,
      "loss": 1.7223,
      "step": 11
    },
    {
      "epoch": 0.012,
      "grad_norm": 46.31218719482422,
      "learning_rate": 1.1012283833590457e-06,
      "loss": 2.2946,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2213292344868864.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}