checkpoint-20/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 96.66002655029297,
      "learning_rate": 0.0003,
      "loss": 41.9798,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 105.88143157958984,
      "learning_rate": 0.0003,
      "loss": 17.5779,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 40.82188034057617,
      "learning_rate": 0.0003,
      "loss": 25.1734,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 19.96090316772461,
      "learning_rate": 0.0003,
      "loss": 25.8685,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 60.25835418701172,
      "learning_rate": 0.0003,
      "loss": 26.6593,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 26.36891746520996,
      "learning_rate": 0.0003,
      "loss": 14.5893,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 18.092010498046875,
      "learning_rate": 0.0003,
      "loss": 19.1589,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 10.055710792541504,
      "learning_rate": 0.0003,
      "loss": 15.2533,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 51.80908966064453,
      "learning_rate": 0.0003,
      "loss": 16.4943,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.591441631317139,
      "learning_rate": 0.0003,
      "loss": 3.9702,
      "step": 10
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 23.278759002685547,
      "learning_rate": 0.0003,
      "loss": 15.4623,
      "step": 11
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 16.832366943359375,
      "learning_rate": 0.0003,
      "loss": 12.2007,
      "step": 12
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 10.488984107971191,
      "learning_rate": 0.0003,
      "loss": 14.9671,
      "step": 13
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 7.7098822593688965,
      "learning_rate": 0.0003,
      "loss": 11.9326,
      "step": 14
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 7.323145866394043,
      "learning_rate": 0.0003,
      "loss": 4.2892,
      "step": 15
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 11.282801628112793,
      "learning_rate": 0.0003,
      "loss": 16.3127,
      "step": 16
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 6.448109149932861,
      "learning_rate": 0.0003,
      "loss": 11.0428,
      "step": 17
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 5.937119007110596,
      "learning_rate": 0.0003,
      "loss": 8.4818,
      "step": 18
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 9.459013938903809,
      "learning_rate": 0.0003,
      "loss": 10.7878,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.8392691612243652,
      "learning_rate": 0.0003,
      "loss": 5.4878,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}