last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24691358024691357,
  "eval_steps": 1000,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024691358024691358,
      "grad_norm": 90107.5546875,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 1.6705,
      "step": 1
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 109766.1953125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4757,
      "step": 10
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 88927.2578125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4813,
      "step": 20
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 113868.796875,
      "learning_rate": 6e-06,
      "loss": 1.4161,
      "step": 30
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 97666.8828125,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.405,
      "step": 40
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 122125.1875,
      "learning_rate": 1e-05,
      "loss": 1.3828,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 111082.546875,
      "learning_rate": 1.2e-05,
      "loss": 1.3397,
      "step": 60
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 121515.2578125,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.2831,
      "step": 70
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 108325.3984375,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.3085,
      "step": 80
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 175475.78125,
      "learning_rate": 1.8e-05,
      "loss": 1.2624,
      "step": 90
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 116793.203125,
      "learning_rate": 2e-05,
      "loss": 1.2683,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.75181399015424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}