checkpoint-826/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "autotrain-hu2ir-jotv8/checkpoint-826",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 826,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 12.926700592041016,
      "learning_rate": 7.459677419354839e-06,
      "loss": 6.1713,
      "step": 41
    },
    {
      "epoch": 0.1,
      "grad_norm": 5.053235054016113,
      "learning_rate": 1.5524193548387098e-05,
      "loss": 2.7995,
      "step": 82
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.710062026977539,
      "learning_rate": 2.3790322580645163e-05,
      "loss": 1.076,
      "step": 123
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.625478982925415,
      "learning_rate": 3.205645161290323e-05,
      "loss": 0.9209,
      "step": 164
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.7764992713928223,
      "learning_rate": 4.032258064516129e-05,
      "loss": 0.8778,
      "step": 205
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.6964770555496216,
      "learning_rate": 4.858870967741936e-05,
      "loss": 0.8273,
      "step": 246
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.7574260234832764,
      "learning_rate": 4.923766816143498e-05,
      "loss": 0.8135,
      "step": 287
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.3349592685699463,
      "learning_rate": 4.831838565022422e-05,
      "loss": 0.8023,
      "step": 328
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.5791077613830566,
      "learning_rate": 4.769058295964125e-05,
      "loss": 0.7892,
      "step": 369
    },
    {
      "epoch": 0.5,
      "grad_norm": NaN,
      "learning_rate": 4.76457399103139e-05,
      "loss": 0.0972,
      "step": 410
    },
    {
      "epoch": 0.55,
      "grad_norm": NaN,
      "learning_rate": 4.760089686098655e-05,
      "loss": 0.1088,
      "step": 451
    },
    {
      "epoch": 0.6,
      "grad_norm": NaN,
      "learning_rate": 4.757847533632287e-05,
      "loss": 0.0467,
      "step": 492
    },
    {
      "epoch": 0.65,
      "grad_norm": NaN,
      "learning_rate": 4.757847533632287e-05,
      "loss": 0.0,
      "step": 533
    },
    {
      "epoch": 0.69,
      "grad_norm": NaN,
      "learning_rate": 4.757847533632287e-05,
      "loss": 0.0,
      "step": 574
    },
    {
      "epoch": 0.74,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.1944,
      "step": 615
    },
    {
      "epoch": 0.79,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.0,
      "step": 656
    },
    {
      "epoch": 0.84,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.0,
      "step": 697
    },
    {
      "epoch": 0.89,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.0,
      "step": 738
    },
    {
      "epoch": 0.94,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.0,
      "step": 779
    },
    {
      "epoch": 0.99,
      "grad_norm": NaN,
      "learning_rate": 4.755605381165919e-05,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 0.0,
      "eval_loss": NaN,
      "eval_rouge1": 0.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0,
      "eval_rougeLsum": 0.0,
      "eval_runtime": 57.261,
      "eval_samples_per_second": 28.833,
      "eval_steps_per_second": 1.816,
      "step": 826
    }
  ],
  "logging_steps": 41,
  "max_steps": 2478,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1005084998369280.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}