checkpoint-50/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.75609756097561,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.975609756097561,
      "eval_runtime": 31.2072,
      "eval_samples_per_second": 9.004,
      "eval_steps_per_second": 0.577,
      "step": 5
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.05327402800321579,
      "learning_rate": 0.0001,
      "loss": 1.747,
      "step": 10
    },
    {
      "epoch": 1.951219512195122,
      "eval_runtime": 30.5362,
      "eval_samples_per_second": 9.202,
      "eval_steps_per_second": 0.589,
      "step": 10
    },
    {
      "epoch": 2.926829268292683,
      "eval_runtime": 30.4989,
      "eval_samples_per_second": 9.213,
      "eval_steps_per_second": 0.59,
      "step": 15
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 0.0818428099155426,
      "learning_rate": 0.0001,
      "loss": 1.6888,
      "step": 20
    },
    {
      "epoch": 3.902439024390244,
      "eval_runtime": 30.4648,
      "eval_samples_per_second": 9.224,
      "eval_steps_per_second": 0.591,
      "step": 20
    },
    {
      "epoch": 4.878048780487805,
      "eval_runtime": 30.4918,
      "eval_samples_per_second": 9.216,
      "eval_steps_per_second": 0.59,
      "step": 25
    },
    {
      "epoch": 5.853658536585366,
      "grad_norm": 0.09824156761169434,
      "learning_rate": 0.0001,
      "loss": 1.5914,
      "step": 30
    },
    {
      "epoch": 5.853658536585366,
      "eval_runtime": 30.452,
      "eval_samples_per_second": 9.228,
      "eval_steps_per_second": 0.591,
      "step": 30
    },
    {
      "epoch": 6.829268292682927,
      "eval_runtime": 53.8511,
      "eval_samples_per_second": 5.218,
      "eval_steps_per_second": 0.334,
      "step": 35
    },
    {
      "epoch": 7.804878048780488,
      "grad_norm": 0.12375161796808243,
      "learning_rate": 0.0001,
      "loss": 1.4667,
      "step": 40
    },
    {
      "epoch": 8.0,
      "eval_runtime": 30.4612,
      "eval_samples_per_second": 9.225,
      "eval_steps_per_second": 0.591,
      "step": 41
    },
    {
      "epoch": 8.975609756097562,
      "eval_runtime": 30.4658,
      "eval_samples_per_second": 9.223,
      "eval_steps_per_second": 0.591,
      "step": 46
    },
    {
      "epoch": 9.75609756097561,
      "grad_norm": 0.191155806183815,
      "learning_rate": 0.0001,
      "loss": 1.3056,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4608941991958938e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}