checkpoint-80/trainer_state.json

{
  "best_metric": 0.8140808343887329,
  "best_model_checkpoint": "autotrain-g8xiw-ebx5n/checkpoint-80",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 18.177003860473633,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.7215,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 25.83134651184082,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9735,
      "step": 8
    },
    {
      "epoch": 0.15,
      "grad_norm": 28.273202896118164,
      "learning_rate": 2.5e-05,
      "loss": 0.9053,
      "step": 12
    },
    {
      "epoch": 0.2,
      "grad_norm": 77.66250610351562,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7484,
      "step": 16
    },
    {
      "epoch": 0.25,
      "grad_norm": 78.92176055908203,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.8162,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 24.40717315673828,
      "learning_rate": 5e-05,
      "loss": 1.2395,
      "step": 24
    },
    {
      "epoch": 0.35,
      "grad_norm": 20.296764373779297,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 1.2468,
      "step": 28
    },
    {
      "epoch": 0.4,
      "grad_norm": 17.20810890197754,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.7842,
      "step": 32
    },
    {
      "epoch": 0.45,
      "grad_norm": 13.720386505126953,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.8349,
      "step": 36
    },
    {
      "epoch": 0.5,
      "grad_norm": 19.7871150970459,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.6975,
      "step": 40
    },
    {
      "epoch": 0.55,
      "grad_norm": 8.968467712402344,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.6712,
      "step": 44
    },
    {
      "epoch": 0.6,
      "grad_norm": 14.593846321105957,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6436,
      "step": 48
    },
    {
      "epoch": 0.65,
      "grad_norm": 32.06483459472656,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.5649,
      "step": 52
    },
    {
      "epoch": 0.7,
      "grad_norm": 13.875551223754883,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.5657,
      "step": 56
    },
    {
      "epoch": 0.75,
      "grad_norm": 15.4502534866333,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.6948,
      "step": 60
    },
    {
      "epoch": 0.8,
      "grad_norm": 42.757694244384766,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.9738,
      "step": 64
    },
    {
      "epoch": 0.85,
      "grad_norm": 21.160280227661133,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.6472,
      "step": 68
    },
    {
      "epoch": 0.9,
      "grad_norm": 11.125871658325195,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.9644,
      "step": 72
    },
    {
      "epoch": 0.95,
      "grad_norm": 11.052087783813477,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.5686,
      "step": 76
    },
    {
      "epoch": 1.0,
      "grad_norm": 8.721762657165527,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.3979,
      "step": 80
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.71875,
      "eval_f1_macro": 0.7169680062645076,
      "eval_f1_micro": 0.71875,
      "eval_f1_weighted": 0.719803137322762,
      "eval_loss": 0.8140808343887329,
      "eval_precision_macro": 0.7124963414309661,
      "eval_precision_micro": 0.71875,
      "eval_precision_weighted": 0.7473707776787377,
      "eval_recall_macro": 0.7500480606863587,
      "eval_recall_micro": 0.71875,
      "eval_recall_weighted": 0.71875,
      "eval_runtime": 27.1736,
      "eval_samples_per_second": 5.888,
      "eval_steps_per_second": 0.368,
      "step": 80
    }
  ],
  "logging_steps": 4,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 41835033418752.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}