checkpoint-65/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 0.9495770931243896,
      "learning_rate": 0.00019396926207859084,
      "loss": 2.771,
      "step": 10
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 0.3216956555843353,
      "learning_rate": 0.00016616858375968595,
      "loss": 1.0341,
      "step": 20
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.3832882344722748,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.8598,
      "step": 30
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 0.27541470527648926,
      "learning_rate": 7.291595318569951e-05,
      "loss": 0.889,
      "step": 40
    },
    {
      "epoch": 0.7751937984496124,
      "grad_norm": 0.2564274072647095,
      "learning_rate": 3.0176318191392726e-05,
      "loss": 0.9639,
      "step": 50
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.26876693964004517,
      "learning_rate": 4.442719421385922e-06,
      "loss": 0.8134,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 65,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9005196009415680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}