trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 1.1355500221252441,
      "learning_rate": 0.000199392,
      "loss": 2.2663,
      "step": 20
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.7390090227127075,
      "learning_rate": 0.000198752,
      "loss": 1.3075,
      "step": 40
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.8225588798522949,
      "learning_rate": 0.00019811200000000002,
      "loss": 1.2692,
      "step": 60
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.39007440209388733,
      "learning_rate": 0.00019747200000000002,
      "loss": 1.2632,
      "step": 80
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5560928583145142,
      "learning_rate": 0.00019683200000000003,
      "loss": 1.2401,
      "step": 100
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.6265106797218323,
      "learning_rate": 0.000196192,
      "loss": 1.2026,
      "step": 120
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.41324910521507263,
      "learning_rate": 0.00019555200000000001,
      "loss": 1.2117,
      "step": 140
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.6018273234367371,
      "learning_rate": 0.000194912,
      "loss": 1.243,
      "step": 160
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.7157287001609802,
      "learning_rate": 0.000194272,
      "loss": 1.2232,
      "step": 180
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.318360835313797,
      "learning_rate": 0.000193632,
      "loss": 1.2553,
      "step": 200
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.37768101692199707,
      "learning_rate": 0.000192992,
      "loss": 1.2367,
      "step": 220
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.28085458278656006,
      "learning_rate": 0.000192352,
      "loss": 1.228,
      "step": 240
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.3715125024318695,
      "learning_rate": 0.000191712,
      "loss": 1.2367,
      "step": 260
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.5925875306129456,
      "learning_rate": 0.000191072,
      "loss": 1.2121,
      "step": 280
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5892595648765564,
      "learning_rate": 0.000190432,
      "loss": 1.2138,
      "step": 300
    }
  ],
  "logging_steps": 20,
  "max_steps": 6250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 9797016276172800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}