last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009784735812133072,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009784735812133072,
      "eval_loss": 4.510274410247803,
      "eval_runtime": 40.6217,
      "eval_samples_per_second": 10.61,
      "eval_steps_per_second": 5.317,
      "step": 1
    },
    {
      "epoch": 0.0029354207436399216,
      "grad_norm": 8.555731773376465,
      "learning_rate": 6e-05,
      "loss": 4.4104,
      "step": 3
    },
    {
      "epoch": 0.005870841487279843,
      "grad_norm": 3.8659377098083496,
      "learning_rate": 0.00012,
      "loss": 3.6807,
      "step": 6
    },
    {
      "epoch": 0.007827788649706457,
      "eval_loss": 3.0672507286071777,
      "eval_runtime": 40.6608,
      "eval_samples_per_second": 10.6,
      "eval_steps_per_second": 5.312,
      "step": 8
    },
    {
      "epoch": 0.008806262230919765,
      "grad_norm": 3.3067519664764404,
      "learning_rate": 0.00018,
      "loss": 3.1889,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4118062710128640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}