last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002139483635624542,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 3.2239,
      "step": 1
    },
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.4657363891601562,
      "eval_runtime": 2982.9015,
      "eval_samples_per_second": 6.598,
      "eval_steps_per_second": 3.299,
      "step": 1
    },
    {
      "epoch": 4.278967271249084e-05,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 3.339,
      "step": 2
    },
    {
      "epoch": 6.418450906873626e-05,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 3.5663,
      "step": 3
    },
    {
      "epoch": 6.418450906873626e-05,
      "eval_loss": 3.4657363891601562,
      "eval_runtime": 2998.628,
      "eval_samples_per_second": 6.563,
      "eval_steps_per_second": 3.282,
      "step": 3
    },
    {
      "epoch": 8.557934542498168e-05,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 3.3324,
      "step": 4
    },
    {
      "epoch": 0.0001069741817812271,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 3.7602,
      "step": 5
    },
    {
      "epoch": 0.0001283690181374725,
      "grad_norm": Infinity,
      "learning_rate": 0.00012,
      "loss": 3.1978,
      "step": 6
    },
    {
      "epoch": 0.0001283690181374725,
      "eval_loss": 3.4657363891601562,
      "eval_runtime": 2976.0057,
      "eval_samples_per_second": 6.613,
      "eval_steps_per_second": 3.307,
      "step": 6
    },
    {
      "epoch": 0.00014976385449371794,
      "grad_norm": Infinity,
      "learning_rate": 0.00014,
      "loss": 3.161,
      "step": 7
    },
    {
      "epoch": 0.00017115869084996337,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 3.1103,
      "step": 8
    },
    {
      "epoch": 0.0001925535272062088,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 3.6238,
      "step": 9
    },
    {
      "epoch": 0.0001925535272062088,
      "eval_loss": 3.4657363891601562,
      "eval_runtime": 2978.3578,
      "eval_samples_per_second": 6.608,
      "eval_steps_per_second": 3.304,
      "step": 9
    },
    {
      "epoch": 0.0002139483635624542,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 3.4239,
      "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": 2058737544069120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}