results/checkpoint-165/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 2.0566840171813965,
      "learning_rate": 0.0001890909090909091,
      "loss": 2.2925,
      "step": 10
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.6935901641845703,
      "learning_rate": 0.00017696969696969698,
      "loss": 1.2339,
      "step": 20
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.615734338760376,
      "learning_rate": 0.00016484848484848487,
      "loss": 0.818,
      "step": 30
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.5262166261672974,
      "learning_rate": 0.00015272727272727275,
      "loss": 0.7725,
      "step": 40
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.3781743049621582,
      "learning_rate": 0.0001406060606060606,
      "loss": 0.9613,
      "step": 50
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.1576794385910034,
      "learning_rate": 0.0001284848484848485,
      "loss": 0.8358,
      "step": 60
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.6639708280563354,
      "learning_rate": 0.00011636363636363636,
      "loss": 0.7019,
      "step": 70
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.7895197868347168,
      "learning_rate": 0.00010424242424242425,
      "loss": 0.6415,
      "step": 80
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 2.112809896469116,
      "learning_rate": 9.212121212121214e-05,
      "loss": 0.7502,
      "step": 90
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.8200409412384033,
      "learning_rate": 8e-05,
      "loss": 0.5876,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7709088325500488,
      "learning_rate": 6.787878787878789e-05,
      "loss": 0.7004,
      "step": 110
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.6113712787628174,
      "learning_rate": 5.5757575757575766e-05,
      "loss": 0.6379,
      "step": 120
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 2.378659248352051,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.5522,
      "step": 130
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 3.1287972927093506,
      "learning_rate": 3.151515151515151e-05,
      "loss": 0.4459,
      "step": 140
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 2.7817366123199463,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 0.5497,
      "step": 150
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 2.7594664096832275,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.5575,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1346006811663360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}