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": 0.880057262218153,
      "learning_rate": 9.59731543624161e-06,
      "loss": -0.0129,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.2806340445646607,
      "learning_rate": 9.12751677852349e-06,
      "loss": -0.0213,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 1.8623258946792332,
      "learning_rate": 8.65771812080537e-06,
      "loss": -0.0447,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 2.282054440873389,
      "learning_rate": 8.18791946308725e-06,
      "loss": -0.0845,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 2.795562670914304,
      "learning_rate": 7.718120805369127e-06,
      "loss": -0.1401,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 3.4612003457116454,
      "learning_rate": 7.248322147651007e-06,
      "loss": -0.2187,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 4.444556419474341,
      "learning_rate": 6.778523489932887e-06,
      "loss": -0.3304,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 5.448210389022822,
      "learning_rate": 6.308724832214766e-06,
      "loss": -0.4451,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 5.637880517257596,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -0.5861,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 5.61454558742453,
      "learning_rate": 5.369127516778524e-06,
      "loss": -0.7104,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 5.245128498969688,
      "learning_rate": 4.899328859060403e-06,
      "loss": -0.8431,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 5.150744859127536,
      "learning_rate": 4.429530201342283e-06,
      "loss": -0.9372,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 5.256165269814733,
      "learning_rate": 3.959731543624161e-06,
      "loss": -1.0329,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 7.121902406786027,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -1.1279,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 10.692635238455521,
      "learning_rate": 3.02013422818792e-06,
      "loss": -1.2487,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 13.219580625568632,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -1.3794,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 13.798256730755003,
      "learning_rate": 2.080536912751678e-06,
      "loss": -1.5084,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 12.643325142065038,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -1.6658,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 13.032297818425516,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -1.7818,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 12.615474127581509,
      "learning_rate": 6.711409395973155e-07,
      "loss": -1.8635,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 12.48121071388992,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -1.9095,
      "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
}