checkpoint-9/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005580530150364285,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006200589055960316,
      "grad_norm": 0.6006524562835693,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4363,
      "step": 1
    },
    {
      "epoch": 0.0012401178111920632,
      "grad_norm": 0.4452102482318878,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1641,
      "step": 2
    },
    {
      "epoch": 0.0018601767167880949,
      "grad_norm": 0.418393075466156,
      "learning_rate": 1.2e-05,
      "loss": 1.0005,
      "step": 3
    },
    {
      "epoch": 0.0018601767167880949,
      "eval_loss": 1.2559138536453247,
      "eval_runtime": 50.2632,
      "eval_samples_per_second": 1.99,
      "eval_steps_per_second": 1.99,
      "step": 3
    },
    {
      "epoch": 0.0024802356223841263,
      "grad_norm": 0.4599858820438385,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1938,
      "step": 4
    },
    {
      "epoch": 0.0031002945279801583,
      "grad_norm": 0.4313387870788574,
      "learning_rate": 2e-05,
      "loss": 0.9897,
      "step": 5
    },
    {
      "epoch": 0.0037203534335761897,
      "grad_norm": 0.4715091586112976,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.1105,
      "step": 6
    },
    {
      "epoch": 0.0037203534335761897,
      "eval_loss": 1.2492942810058594,
      "eval_runtime": 49.6589,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 6
    },
    {
      "epoch": 0.004340412339172222,
      "grad_norm": 0.4590495824813843,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.0824,
      "step": 7
    },
    {
      "epoch": 0.004960471244768253,
      "grad_norm": 0.6232957243919373,
      "learning_rate": 1.76e-05,
      "loss": 1.2176,
      "step": 8
    },
    {
      "epoch": 0.005580530150364285,
      "grad_norm": 0.4820755422115326,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.0774,
      "step": 9
    },
    {
      "epoch": 0.005580530150364285,
      "eval_loss": 1.2356064319610596,
      "eval_runtime": 49.9029,
      "eval_samples_per_second": 2.004,
      "eval_steps_per_second": 2.004,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.052529333627699e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}