Upload CNN/DM BGE-M3 pointwise MSE sentence scorer

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,43 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "salience_article_balanced": false,
+  "salience_loss_type": "mse",
+  "salience_multihead_names": [],
+  "salience_score_aggregation": "scalar",
+  "salience_score_semantics": "model_balanced_salience_probability",
+  "salience_score_transform": "identity",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

eval_metrics.json

@@ -0,0 +1,15 @@
+{
+  "eval_loss": 0.03421084210276604,
+  "eval_mse": 0.03421084379263475,
+  "eval_rmse": 0.18496173602298058,
+  "eval_mae": 0.13758335639960514,
+  "eval_pearson": 0.7992694624484324,
+  "eval_spearman": 0.7975893083370461,
+  "eval_article_spearman": 0.6913812102325307,
+  "eval_article_ndcg_at_3": 0.8912648201819963,
+  "eval_article_ndcg_at_5": 0.8810350116689233,
+  "eval_runtime": 136.7425,
+  "eval_samples_per_second": 49.677,
+  "eval_steps_per_second": 24.842,
+  "epoch": 2.3068926781013697
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e5fe49345d26bb119ee830a1bcd8177324d49a9ff536fdecf897e2b0f04a2a
+size 2271071852

run_summary.md

@@ -0,0 +1,53 @@
+# CNN/DailyMail Pointwise Sentence Scorer Run
+
+- model_size: `base`
+- model_name: `BAAI/bge-m3`
+- resolved_model_name: `/lustre/fsmisc/dataset/HuggingFace_Models/BAAI/bge-m3`
+- target_mode: `model_balanced`
+- target_field: `salience_score_model_balanced`
+- loss_type: `mse`
+- score_transform: `identity`
+- article_balanced: `False`
+- multihead: `False`
+- multihead_names: `[]`
+- score_aggregation: `scalar`
+- eval_loss_semantics: `mse`
+- input_field: `model_input_text`
+- train_file: `data/CNN_DM/representative_subset/salience_generation/recovery_f2_all6/sentence_scorer_data/modernbert_pointwise/train.jsonl`
+- dev_file: `data/CNN_DM/representative_subset/salience_generation/recovery_f2_all6/sentence_scorer_data/modernbert_pointwise/dev.jsonl`
+- train_rows: `59643`
+- dev_rows: `6793`
+- train_articles: `1000`
+- dev_articles: `200`
+- max_length: `4608`
+- attn_implementation: `eager`
+- learning_rate: `1e-05`
+- weight_decay: `0.01`
+- num_train_epochs: `3.0`
+- warmup_ratio: `0.06`
+- per_device_train_batch_size: `1`
+- per_device_eval_batch_size: `2`
+- gradient_accumulation_steps: `16`
+- effective_train_batch_size: `16`
+- eval_strategy: `steps`
+- save_strategy: `steps`
+- early_stopping_patience: `5`
+- bf16: `True`
+- fp16: `False`
+- gradient_checkpointing: `True`
+
+## Eval Metrics
+
+- epoch: `2.3068926781013697`
+- eval_article_ndcg_at_3: `0.8912648201819963`
+- eval_article_ndcg_at_5: `0.8810350116689233`
+- eval_article_spearman: `0.6913812102325307`
+- eval_loss: `0.03421084210276604`
+- eval_mae: `0.13758335639960514`
+- eval_mse: `0.03421084379263475`
+- eval_pearson: `0.7992694624484324`
+- eval_rmse: `0.18496173602298058`
+- eval_runtime: `136.7425`
+- eval_samples_per_second: `49.677`
+- eval_spearman: `0.7975893083370461`
+- eval_steps_per_second: `24.842`

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df1f55d60c9705a501ab9a75550728625740741fe4be308dac4806c16b7d51d
+size 17098085

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": true,
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045a81719ef84d308535e918ef0c3afa2e713598fd11c3ca3c3f81a28bf97708
+size 5329