last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013472549680026945,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013472549680026945,
      "eval_loss": 0.7738643288612366,
      "eval_runtime": 63.2289,
      "eval_samples_per_second": 4.95,
      "eval_steps_per_second": 2.483,
      "step": 1
    },
    {
      "epoch": 0.0040417649040080834,
      "grad_norm": 0.36795666813850403,
      "learning_rate": 6e-05,
      "loss": 0.7352,
      "step": 3
    },
    {
      "epoch": 0.006736274840013472,
      "eval_loss": 0.7524806261062622,
      "eval_runtime": 63.7409,
      "eval_samples_per_second": 4.911,
      "eval_steps_per_second": 2.463,
      "step": 5
    },
    {
      "epoch": 0.008083529808016167,
      "grad_norm": 0.5426688194274902,
      "learning_rate": 0.00012,
      "loss": 0.7558,
      "step": 6
    },
    {
      "epoch": 0.01212529471202425,
      "grad_norm": 0.45750245451927185,
      "learning_rate": 0.00018,
      "loss": 0.749,
      "step": 9
    },
    {
      "epoch": 0.013472549680026945,
      "eval_loss": 0.6806786060333252,
      "eval_runtime": 63.7004,
      "eval_samples_per_second": 4.914,
      "eval_steps_per_second": 2.465,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5842362358038528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}