last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.030303030303030304,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030303030303030303,
      "grad_norm": 2.169158935546875,
      "learning_rate": 2e-05,
      "loss": 1.9868,
      "step": 1
    },
    {
      "epoch": 0.0030303030303030303,
      "eval_loss": 1.8467636108398438,
      "eval_runtime": 6.819,
      "eval_samples_per_second": 20.384,
      "eval_steps_per_second": 10.265,
      "step": 1
    },
    {
      "epoch": 0.006060606060606061,
      "grad_norm": 1.7196919918060303,
      "learning_rate": 4e-05,
      "loss": 1.4478,
      "step": 2
    },
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 1.4146144390106201,
      "learning_rate": 6e-05,
      "loss": 1.3928,
      "step": 3
    },
    {
      "epoch": 0.00909090909090909,
      "eval_loss": 1.8373674154281616,
      "eval_runtime": 6.7888,
      "eval_samples_per_second": 20.475,
      "eval_steps_per_second": 10.311,
      "step": 3
    },
    {
      "epoch": 0.012121212121212121,
      "grad_norm": 2.01965069770813,
      "learning_rate": 8e-05,
      "loss": 1.8594,
      "step": 4
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 2.7054171562194824,
      "learning_rate": 0.0001,
      "loss": 1.9402,
      "step": 5
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 1.8634957075119019,
      "learning_rate": 0.00012,
      "loss": 1.6187,
      "step": 6
    },
    {
      "epoch": 0.01818181818181818,
      "eval_loss": 1.6859822273254395,
      "eval_runtime": 6.9262,
      "eval_samples_per_second": 20.069,
      "eval_steps_per_second": 10.107,
      "step": 6
    },
    {
      "epoch": 0.021212121212121213,
      "grad_norm": 2.3415682315826416,
      "learning_rate": 0.00014,
      "loss": 1.6022,
      "step": 7
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 2.3357975482940674,
      "learning_rate": 0.00016,
      "loss": 1.6437,
      "step": 8
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 2.6000447273254395,
      "learning_rate": 0.00018,
      "loss": 1.3052,
      "step": 9
    },
    {
      "epoch": 0.02727272727272727,
      "eval_loss": 1.2580008506774902,
      "eval_runtime": 6.9222,
      "eval_samples_per_second": 20.08,
      "eval_steps_per_second": 10.112,
      "step": 9
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.899142265319824,
      "learning_rate": 0.0002,
      "loss": 1.3746,
      "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": 820048664985600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}