last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0602409638554218,
  "eval_steps": 4,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0642570281124498,
      "eval_loss": 2.4946258068084717,
      "eval_runtime": 3.2848,
      "eval_samples_per_second": 31.965,
      "eval_steps_per_second": 4.262,
      "step": 1
    },
    {
      "epoch": 0.2570281124497992,
      "eval_loss": 1.9453781843185425,
      "eval_runtime": 3.3308,
      "eval_samples_per_second": 31.524,
      "eval_steps_per_second": 4.203,
      "step": 4
    },
    {
      "epoch": 0.5140562248995983,
      "eval_loss": 1.3580522537231445,
      "eval_runtime": 3.2898,
      "eval_samples_per_second": 31.917,
      "eval_steps_per_second": 4.256,
      "step": 8
    },
    {
      "epoch": 0.642570281124498,
      "grad_norm": 1.1430367231369019,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.9168,
      "step": 10
    },
    {
      "epoch": 0.7710843373493976,
      "eval_loss": 1.222444772720337,
      "eval_runtime": 3.2806,
      "eval_samples_per_second": 32.006,
      "eval_steps_per_second": 4.268,
      "step": 12
    },
    {
      "epoch": 1.0602409638554218,
      "eval_loss": 1.1985491514205933,
      "eval_runtime": 3.2919,
      "eval_samples_per_second": 31.897,
      "eval_steps_per_second": 4.253,
      "step": 16
    }
  ],
  "logging_steps": 10,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2802491666137088e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}