checkpoint-150/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8846153846153846,
  "eval_steps": 25,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.6533744931221008,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 4.4051,
      "step": 10
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.7187979221343994,
      "learning_rate": 9.785714285714286e-05,
      "loss": 4.4664,
      "step": 20
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.8211218118667603,
      "learning_rate": 9.071428571428571e-05,
      "loss": 4.5301,
      "step": 30
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.206388235092163,
      "learning_rate": 8.357142857142858e-05,
      "loss": 4.2406,
      "step": 40
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 1.6155692338943481,
      "learning_rate": 7.642857142857143e-05,
      "loss": 3.9611,
      "step": 50
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 1.4896374940872192,
      "learning_rate": 6.928571428571429e-05,
      "loss": 3.8293,
      "step": 60
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 1.3265907764434814,
      "learning_rate": 6.214285714285714e-05,
      "loss": 3.6707,
      "step": 70
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.4570021629333496,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.6483,
      "step": 80
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 1.6197093725204468,
      "learning_rate": 4.785714285714286e-05,
      "loss": 3.4943,
      "step": 90
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.5315507650375366,
      "learning_rate": 4.0714285714285717e-05,
      "loss": 3.4465,
      "step": 100
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 1.952380895614624,
      "learning_rate": 3.357142857142857e-05,
      "loss": 3.4168,
      "step": 110
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 1.8006091117858887,
      "learning_rate": 2.642857142857143e-05,
      "loss": 3.271,
      "step": 120
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.5776447057724,
      "learning_rate": 1.928571428571429e-05,
      "loss": 3.1447,
      "step": 130
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 2.3255491256713867,
      "learning_rate": 1.2142857142857144e-05,
      "loss": 3.1587,
      "step": 140
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 2.2415945529937744,
      "learning_rate": 5e-06,
      "loss": 3.275,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 78871251124224.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}