last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0018389959082341042,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018389959082341041,
      "grad_norm": 0.2995776832103729,
      "learning_rate": 2e-05,
      "loss": 1.1687,
      "step": 1
    },
    {
      "epoch": 0.00018389959082341041,
      "eval_loss": 1.2216600179672241,
      "eval_runtime": 110.581,
      "eval_samples_per_second": 20.709,
      "eval_steps_per_second": 10.354,
      "step": 1
    },
    {
      "epoch": 0.00036779918164682083,
      "grad_norm": 0.4239529073238373,
      "learning_rate": 4e-05,
      "loss": 1.3116,
      "step": 2
    },
    {
      "epoch": 0.0005516987724702312,
      "grad_norm": 0.45381972193717957,
      "learning_rate": 6e-05,
      "loss": 1.3455,
      "step": 3
    },
    {
      "epoch": 0.0005516987724702312,
      "eval_loss": 1.217912197113037,
      "eval_runtime": 110.387,
      "eval_samples_per_second": 20.745,
      "eval_steps_per_second": 10.373,
      "step": 3
    },
    {
      "epoch": 0.0007355983632936417,
      "grad_norm": 0.35487285256385803,
      "learning_rate": 8e-05,
      "loss": 1.2765,
      "step": 4
    },
    {
      "epoch": 0.0009194979541170521,
      "grad_norm": 0.3256043493747711,
      "learning_rate": 0.0001,
      "loss": 1.2646,
      "step": 5
    },
    {
      "epoch": 0.0011033975449404624,
      "grad_norm": 0.29252171516418457,
      "learning_rate": 0.00012,
      "loss": 1.1082,
      "step": 6
    },
    {
      "epoch": 0.0011033975449404624,
      "eval_loss": 1.173251986503601,
      "eval_runtime": 110.4161,
      "eval_samples_per_second": 20.74,
      "eval_steps_per_second": 10.37,
      "step": 6
    },
    {
      "epoch": 0.001287297135763873,
      "grad_norm": 0.3630172312259674,
      "learning_rate": 0.00014,
      "loss": 1.2261,
      "step": 7
    },
    {
      "epoch": 0.0014711967265872833,
      "grad_norm": 0.3279069662094116,
      "learning_rate": 0.00016,
      "loss": 1.1697,
      "step": 8
    },
    {
      "epoch": 0.0016550963174106939,
      "grad_norm": 0.31991538405418396,
      "learning_rate": 0.00018,
      "loss": 1.0302,
      "step": 9
    },
    {
      "epoch": 0.0016550963174106939,
      "eval_loss": 1.02601158618927,
      "eval_runtime": 110.4765,
      "eval_samples_per_second": 20.728,
      "eval_steps_per_second": 10.364,
      "step": 9
    },
    {
      "epoch": 0.0018389959082341042,
      "grad_norm": 0.3872000277042389,
      "learning_rate": 0.0002,
      "loss": 1.1082,
      "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": 1353080297226240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}