checkpoint-195/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.3267529010772705,
      "learning_rate": 3.984759689788058e-05,
      "loss": 3.9964,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.26488664746284485,
      "learning_rate": 3.923287969397442e-05,
      "loss": 3.6742,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3106290102005005,
      "learning_rate": 3.816256236058198e-05,
      "loss": 3.333,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.2936558425426483,
      "learning_rate": 3.6664941776944834e-05,
      "loss": 3.1105,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.29774364829063416,
      "learning_rate": 3.477961179759822e-05,
      "loss": 2.8481,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2768242657184601,
      "learning_rate": 3.255641647634906e-05,
      "loss": 2.5763,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.20273493230342865,
      "learning_rate": 3.005413229711771e-05,
      "loss": 2.3194,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.17480742931365967,
      "learning_rate": 2.7338914250614635e-05,
      "loss": 2.161,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.16872847080230713,
      "learning_rate": 2.4482546839229335e-05,
      "loss": 2.1031,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.15632902085781097,
      "learning_rate": 2.1560546249785927e-05,
      "loss": 2.0517,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.15166400372982025,
      "learning_rate": 1.8650163868619736e-05,
      "loss": 2.0657,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.15363118052482605,
      "learning_rate": 1.582834392172553e-05,
      "loss": 2.0917,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1388818472623825,
      "learning_rate": 1.3169689235561926e-05,
      "loss": 1.9709,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.13172218203544617,
      "learning_rate": 1.074448889940397e-05,
      "loss": 2.0095,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.13791440427303314,
      "learning_rate": 8.616859973592406e-06,
      "loss": 1.9759,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.1420830637216568,
      "learning_rate": 6.843052372901353e-06,
      "loss": 2.0029,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.13697461783885956,
      "learning_rate": 5.469961740247712e-06,
      "loss": 2.0174,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.13703729212284088,
      "learning_rate": 4.533889627150585e-06,
      "loss": 2.0217,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.1383812576532364,
      "learning_rate": 4.059583759092255e-06,
      "loss": 1.9305,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8825076824813568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}