trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 278,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 0.5625,
      "learning_rate": 0.00010714285714285714,
      "loss": 1.6164,
      "step": 20
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00021428571428571427,
      "loss": 1.49,
      "step": 40
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00029975975238935744,
      "loss": 1.4566,
      "step": 60
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.50390625,
      "learning_rate": 0.0002914316168191626,
      "loss": 1.4481,
      "step": 80
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 0.451171875,
      "learning_rate": 0.00027184967850358286,
      "loss": 1.42,
      "step": 100
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 0.4453125,
      "learning_rate": 0.00024257208459621828,
      "loss": 1.4013,
      "step": 120
    },
    {
      "epoch": 0.5035971223021583,
      "grad_norm": 0.4609375,
      "learning_rate": 0.0002059284716670463,
      "loss": 1.424,
      "step": 140
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.443359375,
      "learning_rate": 0.00016483459505463747,
      "loss": 1.394,
      "step": 160
    },
    {
      "epoch": 0.6474820143884892,
      "grad_norm": 0.462890625,
      "learning_rate": 0.000122560320379142,
      "loss": 1.3847,
      "step": 180
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 0.44140625,
      "learning_rate": 8.246943827734897e-05,
      "loss": 1.3983,
      "step": 200
    },
    {
      "epoch": 0.7913669064748201,
      "grad_norm": 0.462890625,
      "learning_rate": 4.7752005465070094e-05,
      "loss": 1.3804,
      "step": 220
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 0.45703125,
      "learning_rate": 2.117050991693609e-05,
      "loss": 1.3835,
      "step": 240
    },
    {
      "epoch": 0.935251798561151,
      "grad_norm": 0.455078125,
      "learning_rate": 4.840057959975169e-06,
      "loss": 1.3881,
      "step": 260
    },
    {
      "epoch": 1.0,
      "step": 278,
      "total_flos": 5010632390737920.0,
      "train_loss": 1.4269454736503766,
      "train_runtime": 555.1964,
      "train_samples_per_second": 2.003,
      "train_steps_per_second": 0.501
    }
  ],
  "logging_steps": 20,
  "max_steps": 278,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5010632390737920.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}