last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7619047619047619,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.6838904619216919,
      "learning_rate": 1e-05,
      "loss": 1.5071,
      "step": 1
    },
    {
      "epoch": 0.1523809523809524,
      "eval_loss": 1.6498456001281738,
      "eval_runtime": 45.3536,
      "eval_samples_per_second": 0.265,
      "eval_steps_per_second": 0.132,
      "step": 1
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.7086118459701538,
      "learning_rate": 2e-05,
      "loss": 1.5961,
      "step": 2
    },
    {
      "epoch": 0.3047619047619048,
      "eval_loss": 1.635055422782898,
      "eval_runtime": 0.2504,
      "eval_samples_per_second": 47.916,
      "eval_steps_per_second": 23.958,
      "step": 2
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.699629545211792,
      "learning_rate": 3e-05,
      "loss": 1.5273,
      "step": 3
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.7527002096176147,
      "learning_rate": 4e-05,
      "loss": 1.5479,
      "step": 4
    },
    {
      "epoch": 0.6095238095238096,
      "eval_loss": 1.6128654479980469,
      "eval_runtime": 0.2243,
      "eval_samples_per_second": 53.508,
      "eval_steps_per_second": 26.754,
      "step": 4
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.7976269721984863,
      "learning_rate": 5e-05,
      "loss": 1.5899,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1640097329971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}