trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 0.930652379989624,
      "learning_rate": 1.8e-05,
      "loss": 2.2801,
      "step": 50
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4636040925979614,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.7522,
      "step": 100
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1993882805109024,
      "learning_rate": 1.4e-05,
      "loss": 1.5261,
      "step": 150
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.18588915467262268,
      "learning_rate": 1.2e-05,
      "loss": 1.4629,
      "step": 200
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.19438068568706512,
      "learning_rate": 1e-05,
      "loss": 1.4175,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.20929713547229767,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3581,
      "step": 300
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.22034268081188202,
      "learning_rate": 6e-06,
      "loss": 1.3108,
      "step": 350
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.22668711841106415,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2769,
      "step": 400
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.24719643592834473,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2565,
      "step": 450
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2223932147026062,
      "learning_rate": 0.0,
      "loss": 1.229,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.424668716888064e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}