last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00914703864623828,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000914703864623828,
      "grad_norm": 1.235713243484497,
      "learning_rate": 2e-05,
      "loss": 2.2327,
      "step": 1
    },
    {
      "epoch": 0.000914703864623828,
      "eval_loss": 2.0998167991638184,
      "eval_runtime": 15.4374,
      "eval_samples_per_second": 29.863,
      "eval_steps_per_second": 14.964,
      "step": 1
    },
    {
      "epoch": 0.001829407729247656,
      "grad_norm": 1.291617751121521,
      "learning_rate": 4e-05,
      "loss": 2.0275,
      "step": 2
    },
    {
      "epoch": 0.002744111593871484,
      "grad_norm": 1.3160033226013184,
      "learning_rate": 6e-05,
      "loss": 2.1415,
      "step": 3
    },
    {
      "epoch": 0.002744111593871484,
      "eval_loss": 2.0901479721069336,
      "eval_runtime": 14.2083,
      "eval_samples_per_second": 32.446,
      "eval_steps_per_second": 16.258,
      "step": 3
    },
    {
      "epoch": 0.003658815458495312,
      "grad_norm": 1.4082257747650146,
      "learning_rate": 8e-05,
      "loss": 2.1747,
      "step": 4
    },
    {
      "epoch": 0.00457351932311914,
      "grad_norm": 1.4099056720733643,
      "learning_rate": 0.0001,
      "loss": 2.1174,
      "step": 5
    },
    {
      "epoch": 0.005488223187742968,
      "grad_norm": 1.70159113407135,
      "learning_rate": 0.00012,
      "loss": 2.0766,
      "step": 6
    },
    {
      "epoch": 0.005488223187742968,
      "eval_loss": 1.8992050886154175,
      "eval_runtime": 14.2562,
      "eval_samples_per_second": 32.337,
      "eval_steps_per_second": 16.204,
      "step": 6
    },
    {
      "epoch": 0.006402927052366796,
      "grad_norm": 1.59661066532135,
      "learning_rate": 0.00014,
      "loss": 1.8453,
      "step": 7
    },
    {
      "epoch": 0.007317630916990624,
      "grad_norm": 1.6485153436660767,
      "learning_rate": 0.00016,
      "loss": 1.6767,
      "step": 8
    },
    {
      "epoch": 0.008232334781614453,
      "grad_norm": 1.4121031761169434,
      "learning_rate": 0.00018,
      "loss": 1.5341,
      "step": 9
    },
    {
      "epoch": 0.008232334781614453,
      "eval_loss": 1.4102096557617188,
      "eval_runtime": 14.2189,
      "eval_samples_per_second": 32.422,
      "eval_steps_per_second": 16.246,
      "step": 9
    },
    {
      "epoch": 0.00914703864623828,
      "grad_norm": 1.488721489906311,
      "learning_rate": 0.0002,
      "loss": 1.3194,
      "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": 1849596460400640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}