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": 103.14805603027344,
      "learning_rate": 0.0003,
      "loss": 41.87,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 527.2064819335938,
      "learning_rate": 0.0003,
      "loss": 25.5059,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 83.18610382080078,
      "learning_rate": 0.0003,
      "loss": 31.8839,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 90.43904113769531,
      "learning_rate": 0.0003,
      "loss": 30.6464,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 39.171390533447266,
      "learning_rate": 0.0003,
      "loss": 28.5297,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 21.943239212036133,
      "learning_rate": 0.0003,
      "loss": 16.1482,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 20.39069175720215,
      "learning_rate": 0.0003,
      "loss": 20.6947,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 28.99578285217285,
      "learning_rate": 0.0003,
      "loss": 16.9118,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 20.83210563659668,
      "learning_rate": 0.0003,
      "loss": 17.7937,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.037144660949707,
      "learning_rate": 0.0003,
      "loss": 4.2743,
      "step": 10
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 22.04193878173828,
      "learning_rate": 0.0003,
      "loss": 15.8222,
      "step": 11
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 10.220871925354004,
      "learning_rate": 0.0003,
      "loss": 12.1743,
      "step": 12
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 15.529003143310547,
      "learning_rate": 0.0003,
      "loss": 15.0118,
      "step": 13
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 15.442506790161133,
      "learning_rate": 0.0003,
      "loss": 11.8558,
      "step": 14
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 5.861841201782227,
      "learning_rate": 0.0003,
      "loss": 3.9917,
      "step": 15
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 14.69842529296875,
      "learning_rate": 0.0003,
      "loss": 16.4242,
      "step": 16
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 9.839238166809082,
      "learning_rate": 0.0003,
      "loss": 11.1573,
      "step": 17
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 8.495640754699707,
      "learning_rate": 0.0003,
      "loss": 8.1271,
      "step": 18
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 13.988245010375977,
      "learning_rate": 0.0003,
      "loss": 10.0494,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.209702968597412,
      "learning_rate": 0.0003,
      "loss": 5.3355,
      "step": 20
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 4.782948017120361,
      "learning_rate": 0.0003,
      "loss": 7.3092,
      "step": 21
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 7.141439437866211,
      "learning_rate": 0.0003,
      "loss": 9.0511,
      "step": 22
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 7.136995792388916,
      "learning_rate": 0.0003,
      "loss": 10.9197,
      "step": 23
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 4.277120113372803,
      "learning_rate": 0.0003,
      "loss": 4.8889,
      "step": 24
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 7.76605749130249,
      "learning_rate": 0.0003,
      "loss": 11.0701,
      "step": 25
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 6.047715663909912,
      "learning_rate": 0.0003,
      "loss": 7.1726,
      "step": 26
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 5.533137321472168,
      "learning_rate": 0.0003,
      "loss": 4.9744,
      "step": 27
    },
    {
      "epoch": 2.736842105263158,
      "step": 27,
      "total_flos": 0.0,
      "train_loss": 14.799769171962032,
      "train_runtime": 201.5382,
      "train_samples_per_second": 4.466,
      "train_steps_per_second": 0.134
    }
  ],
  "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
}