specialized_llm_1b_base_100/checkpoint-50/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 156.9064188116979,
      "learning_rate": 2e-05,
      "loss": 4.8316,
      "step": 5
    },
    {
      "epoch": 0.2,
      "grad_norm": 82.19226082448304,
      "learning_rate": 2e-05,
      "loss": 2.013,
      "step": 10
    },
    {
      "epoch": 0.3,
      "grad_norm": 57.27306485371414,
      "learning_rate": 2e-05,
      "loss": 1.2974,
      "step": 15
    },
    {
      "epoch": 0.4,
      "grad_norm": 48.83225730679657,
      "learning_rate": 2e-05,
      "loss": 1.0968,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 24.709557874315326,
      "learning_rate": 2e-05,
      "loss": 1.0172,
      "step": 25
    },
    {
      "epoch": 0.6,
      "grad_norm": 43.78869302264833,
      "learning_rate": 2e-05,
      "loss": 1.1018,
      "step": 30
    },
    {
      "epoch": 0.7,
      "grad_norm": 33.479250288798106,
      "learning_rate": 2e-05,
      "loss": 1.4642,
      "step": 35
    },
    {
      "epoch": 0.8,
      "grad_norm": 46.04180725501253,
      "learning_rate": 2e-05,
      "loss": 0.9675,
      "step": 40
    },
    {
      "epoch": 0.9,
      "grad_norm": 31.218425949463782,
      "learning_rate": 2e-05,
      "loss": 0.9244,
      "step": 45
    },
    {
      "epoch": 1.0,
      "grad_norm": 35.29186854691775,
      "learning_rate": 2e-05,
      "loss": 0.9531,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 10380902400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}