checkpoint-6/trainer_state.json

{
  "best_metric": 9.164422988891602,
  "best_model_checkpoint": "autotrain-tuac9-vfsuc/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": 141.18881225585938,
      "learning_rate": 3e-05,
      "loss": 5.5753,
      "step": 1
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 113.59857940673828,
      "learning_rate": 2.8858192987669303e-05,
      "loss": 3.8769,
      "step": 2
    },
    {
      "epoch": 1.0,
      "grad_norm": 62.12335205078125,
      "learning_rate": 2.5606601717798212e-05,
      "loss": 0.6162,
      "step": 3
    },
    {
      "epoch": 1.0,
      "eval_loss": 9.552681922912598,
      "eval_runtime": 0.1556,
      "eval_samples_per_second": 32.136,
      "eval_steps_per_second": 6.427,
      "eval_validation_pearson_cosine": -0.05720032020910332,
      "eval_validation_pearson_dot": -0.05720025912665361,
      "eval_validation_pearson_euclidean": -0.00422203561181958,
      "eval_validation_pearson_manhattan": -0.016885377525531375,
      "eval_validation_pearson_max": -0.00422203561181958,
      "eval_validation_spearman_cosine": -0.05129891760425771,
      "eval_validation_spearman_dot": -0.05129891760425771,
      "eval_validation_spearman_euclidean": -0.05129891760425771,
      "eval_validation_spearman_manhattan": -0.05129891760425771,
      "eval_validation_spearman_max": -0.05129891760425771,
      "step": 3
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 45.422462463378906,
      "learning_rate": 2.074025148547635e-05,
      "loss": 0.9801,
      "step": 4
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 78.78740692138672,
      "learning_rate": 1.5e-05,
      "loss": 1.1051,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 40.24138641357422,
      "learning_rate": 9.259748514523654e-06,
      "loss": 0.6455,
      "step": 6
    },
    {
      "epoch": 2.0,
      "eval_loss": 9.164422988891602,
      "eval_runtime": 0.1273,
      "eval_samples_per_second": 39.273,
      "eval_steps_per_second": 7.855,
      "eval_validation_pearson_cosine": -0.10073561135203735,
      "eval_validation_pearson_dot": -0.1007351930231386,
      "eval_validation_pearson_euclidean": -0.056592337170460805,
      "eval_validation_pearson_manhattan": -0.07223520049199797,
      "eval_validation_pearson_max": -0.056592337170460805,
      "eval_validation_spearman_cosine": -0.05129891760425771,
      "eval_validation_spearman_dot": -0.05129891760425771,
      "eval_validation_spearman_euclidean": -0.05129891760425771,
      "eval_validation_spearman_manhattan": -0.05129891760425771,
      "eval_validation_spearman_max": -0.05129891760425771,
      "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
}