checkpoint-75/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 1.3508174419403076,
      "learning_rate": 0.0002,
      "loss": 2.5227,
      "step": 5
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8602172136306763,
      "learning_rate": 0.0002,
      "loss": 2.6438,
      "step": 10
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.7185380458831787,
      "learning_rate": 0.0002,
      "loss": 0.7979,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.46760892868042,
      "learning_rate": 0.0002,
      "loss": 0.4091,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5913628935813904,
      "learning_rate": 0.0002,
      "loss": 0.274,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.46462497115135193,
      "learning_rate": 0.0002,
      "loss": 0.1921,
      "step": 30
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.47151607275009155,
      "learning_rate": 0.0002,
      "loss": 0.2399,
      "step": 35
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.45026347041130066,
      "learning_rate": 0.0002,
      "loss": 0.5266,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.8638098835945129,
      "learning_rate": 0.0002,
      "loss": 0.1596,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.41460809111595154,
      "learning_rate": 0.0002,
      "loss": 0.291,
      "step": 50
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.30362772941589355,
      "learning_rate": 0.0002,
      "loss": 0.0818,
      "step": 55
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.46699783205986023,
      "learning_rate": 0.0002,
      "loss": 0.1198,
      "step": 60
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.3688370883464813,
      "learning_rate": 0.0002,
      "loss": 0.0892,
      "step": 65
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6380140781402588,
      "learning_rate": 0.0002,
      "loss": 0.1068,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.31224119663238525,
      "learning_rate": 0.0002,
      "loss": 0.1673,
      "step": 75
    }
  ],
  "logging_steps": 5,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2408372071010304.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}