checkpoint-6/trainer_state.json

{
  "best_metric": 6.586054801940918,
  "best_model_checkpoint": "autotrain-ShauryaNova/checkpoint-6",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 138.7187042236328,
      "learning_rate": 3e-05,
      "loss": 1.8178,
      "step": 1
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0,
      "learning_rate": 2.625e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0,
      "learning_rate": 2.25e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 1.0,
      "eval_loss": 6.602341651916504,
      "eval_runtime": 0.1399,
      "eval_samples_per_second": 35.746,
      "eval_steps_per_second": 7.149,
      "eval_validation_pearson_cosine": 0.10354138591630481,
      "eval_validation_pearson_dot": 0.10354118663474862,
      "eval_validation_pearson_euclidean": 0.1672423788935215,
      "eval_validation_pearson_manhattan": 0.15792507924082888,
      "eval_validation_pearson_max": 0.1672423788935215,
      "eval_validation_spearman_cosine": 0.28867513459481287,
      "eval_validation_spearman_dot": 0.28867513459481287,
      "eval_validation_spearman_euclidean": 0.28867513459481287,
      "eval_validation_spearman_manhattan": 0.28867513459481287,
      "eval_validation_spearman_max": 0.28867513459481287,
      "step": 3
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.602425456047058,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.0134,
      "step": 4
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0,
      "learning_rate": 1.125e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.586054801940918,
      "eval_runtime": 0.1445,
      "eval_samples_per_second": 34.594,
      "eval_steps_per_second": 6.919,
      "eval_validation_pearson_cosine": 0.15590647163663807,
      "eval_validation_pearson_dot": 0.15590640231031966,
      "eval_validation_pearson_euclidean": 0.21989747670451043,
      "eval_validation_pearson_manhattan": 0.20874094632850035,
      "eval_validation_pearson_max": 0.21989747670451043,
      "eval_validation_spearman_cosine": 0.28867513459481287,
      "eval_validation_spearman_dot": 0.28867513459481287,
      "eval_validation_spearman_euclidean": 0.28867513459481287,
      "eval_validation_spearman_manhattan": 0.28867513459481287,
      "eval_validation_spearman_max": 0.28867513459481287,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 9,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}