trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 150.0,
  "eval_steps": 0,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.0,
      "grad_norm": 0.8327094292994284,
      "learning_rate": 9.59731543624161e-06,
      "loss": 0.0099,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.25329450711663565,
      "learning_rate": 9.12751677852349e-06,
      "loss": 0.0078,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 0.9632489679647264,
      "learning_rate": 8.65771812080537e-06,
      "loss": 0.0032,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.09212476899718587,
      "learning_rate": 8.18791946308725e-06,
      "loss": 0.0006,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.11199914644363453,
      "learning_rate": 7.718120805369127e-06,
      "loss": 0.0027,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 0.23248105032315738,
      "learning_rate": 7.248322147651007e-06,
      "loss": 0.0014,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 0.5170030782447789,
      "learning_rate": 6.778523489932887e-06,
      "loss": -0.002,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 1.9523625507728002,
      "learning_rate": 6.308724832214766e-06,
      "loss": -0.012,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 2.9984629780443024,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -0.0485,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 3.2940523689308154,
      "learning_rate": 5.369127516778524e-06,
      "loss": -0.1101,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 3.46285077459721,
      "learning_rate": 4.899328859060403e-06,
      "loss": -0.183,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 4.364446814661824,
      "learning_rate": 4.429530201342283e-06,
      "loss": -0.2578,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 5.635889519224495,
      "learning_rate": 3.959731543624161e-06,
      "loss": -0.3457,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 6.317511734841832,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -0.4428,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 8.22783960068216,
      "learning_rate": 3.02013422818792e-06,
      "loss": -0.5522,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 8.768166783804736,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -0.6652,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 8.966456937586369,
      "learning_rate": 2.080536912751678e-06,
      "loss": -0.7698,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 8.554926142951212,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -0.8601,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 9.350544511045596,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -0.9424,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 9.532208815188003,
      "learning_rate": 6.711409395973155e-07,
      "loss": -1.001,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 9.603636014024755,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -1.0341,
      "step": 147
    }
  ],
  "logging_steps": 7,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}