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": 0.8407118915654288,
      "learning_rate": 9.59731543624161e-06,
      "loss": 0.0017,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.6841459171977524,
      "learning_rate": 9.12751677852349e-06,
      "loss": 0.0017,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 1.565808446982112,
      "learning_rate": 8.65771812080537e-06,
      "loss": -0.0105,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 3.2233455955288384,
      "learning_rate": 8.18791946308725e-06,
      "loss": -0.0372,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 3.6482958525546647,
      "learning_rate": 7.718120805369127e-06,
      "loss": -0.0901,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 2.2764884055018406,
      "learning_rate": 7.248322147651007e-06,
      "loss": -0.1529,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 2.36754870082029,
      "learning_rate": 6.778523489932887e-06,
      "loss": -0.2078,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 3.3652317155373117,
      "learning_rate": 6.308724832214766e-06,
      "loss": -0.2495,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 3.9698513896048135,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -0.3098,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 4.706367068473275,
      "learning_rate": 5.369127516778524e-06,
      "loss": -0.3806,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 5.140398624959974,
      "learning_rate": 4.899328859060403e-06,
      "loss": -0.4616,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 6.300761301102428,
      "learning_rate": 4.429530201342283e-06,
      "loss": -0.5456,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 6.508140437957886,
      "learning_rate": 3.959731543624161e-06,
      "loss": -0.6461,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 7.108682374552725,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -0.7474,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 9.041265651733072,
      "learning_rate": 3.02013422818792e-06,
      "loss": -0.8531,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 11.603695882589307,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -0.9615,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 12.18253737445184,
      "learning_rate": 2.080536912751678e-06,
      "loss": -1.0859,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 11.390269496823556,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -1.1872,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 11.993277841299637,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -1.2845,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 11.97815018546336,
      "learning_rate": 6.711409395973155e-07,
      "loss": -1.3516,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 11.901270546907066,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -1.3851,
      "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
}