trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.736842105263158,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 66.80625915527344,
      "learning_rate": 0.0003,
      "loss": 59.0922,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 42.16349411010742,
      "learning_rate": 0.0003,
      "loss": 40.5625,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 34.7736930847168,
      "learning_rate": 0.0003,
      "loss": 37.6795,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 41.49787139892578,
      "learning_rate": 0.0003,
      "loss": 23.9383,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 52.929927825927734,
      "learning_rate": 0.0003,
      "loss": 19.2318,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 35.0192756652832,
      "learning_rate": 0.0003,
      "loss": 24.5318,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 22.34128761291504,
      "learning_rate": 0.0003,
      "loss": 20.694,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 33.19445037841797,
      "learning_rate": 0.0003,
      "loss": 15.9587,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 35.2607307434082,
      "learning_rate": 0.0003,
      "loss": 16.091,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.971670150756836,
      "learning_rate": 0.0003,
      "loss": 6.4848,
      "step": 10
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 70.17874908447266,
      "learning_rate": 0.0003,
      "loss": 21.502,
      "step": 11
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 9.148673057556152,
      "learning_rate": 0.0003,
      "loss": 9.0273,
      "step": 12
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 8.400835990905762,
      "learning_rate": 0.0003,
      "loss": 14.5862,
      "step": 13
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 8.655104637145996,
      "learning_rate": 0.0003,
      "loss": 14.0817,
      "step": 14
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 8.041231155395508,
      "learning_rate": 0.0003,
      "loss": 19.4253,
      "step": 15
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 11.80112361907959,
      "learning_rate": 0.0003,
      "loss": 10.6932,
      "step": 16
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 24.622623443603516,
      "learning_rate": 0.0003,
      "loss": 8.2083,
      "step": 17
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 12.404068946838379,
      "learning_rate": 0.0003,
      "loss": 16.6983,
      "step": 18
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 11.858294486999512,
      "learning_rate": 0.0003,
      "loss": 18.4896,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.483745574951172,
      "learning_rate": 0.0003,
      "loss": 4.207,
      "step": 20
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 8.02437973022461,
      "learning_rate": 0.0003,
      "loss": 14.6837,
      "step": 21
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 11.133962631225586,
      "learning_rate": 0.0003,
      "loss": 11.7229,
      "step": 22
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 14.599047660827637,
      "learning_rate": 0.0003,
      "loss": 11.4597,
      "step": 23
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 12.829426765441895,
      "learning_rate": 0.0003,
      "loss": 9.1055,
      "step": 24
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 6.030374050140381,
      "learning_rate": 0.0003,
      "loss": 11.2372,
      "step": 25
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 12.609663009643555,
      "learning_rate": 0.0003,
      "loss": 8.3892,
      "step": 26
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 6.034035682678223,
      "learning_rate": 0.0003,
      "loss": 10.5367,
      "step": 27
    },
    {
      "epoch": 2.736842105263158,
      "step": 27,
      "total_flos": 0.0,
      "train_loss": 17.715496469427038,
      "train_runtime": 155.5004,
      "train_samples_per_second": 5.788,
      "train_steps_per_second": 0.174
    }
  ],
  "logging_steps": 1,
  "max_steps": 27,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}