Best Recall@10: 0.8827 at step 250

.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 +1,33 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "bfloat16",
+  "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,
+  "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",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

config.yaml

@@ -0,0 +1,55 @@
+data:
+  data_dir: sqale_dataset_mined
+  max_query_length: 128
+  max_table_length: 384
+  num_negatives_per_positive: 15
+  train_split: 0.9
+  val_split: 0.05
+  test_split: 0.05
+  seed: 42
+  max_samples: null
+  max_val_samples: 2000
+  complexity_ratios:
+    easy: 0.2
+    medium: 0.3
+    hard: 0.5
+model:
+  name: BAAI/bge-reranker-v2-m3
+  gradient_checkpointing: false
+  torch_dtype: bfloat16
+  trust_remote_code: true
+training:
+  output_dir: outputs/reranker_v2_curriculum
+  batch_size: 4
+  gradient_accumulation_steps: 4
+  learning_rate: 2.0e-05
+  warmup_ratio: 0.1
+  num_epochs: 5
+  weight_decay: 0.01
+  max_grad_norm: 1.0
+  loss_type: focal
+  temperature: 1.0
+  margin: 1.0
+  wandb_project: sqale-table-reranker
+  wandb_run_name: null
+  log_every_n_steps: 10
+  eval_every_n_steps: 250
+  save_every_n_steps: 500
+  device: cuda
+  mixed_precision: true
+  cudnn_benchmark: true
+  tf32: true
+  torch_compile: false
+  torch_compile_mode: reduce-overhead
+  flash_attention: false
+  push_to_hub: true
+  hub_model_id: Rubyando59/sqale-reranker-curriculum
+  hub_private_repo: true
+  hub_token: null
+eval:
+  k_values:
+  - 1
+  - 3
+  - 5
+  - 10
+  batch_size: 32

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528dbdb5f525f3258fd5683d76d6677e50eaf599ffd6e9040cca039aaef0239f
+size 1135560090

reranker_config.json

@@ -0,0 +1 @@
+{"model_name": "BAAI/bge-reranker-v2-m3", "gradient_checkpointing": false}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf8afbfd11306bd872018c53bfdf2e160a56f8edbcf49933324404791c148d3
+size 17082900

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3645a4eac52f89ce064d7813110f3c6268528822af8a1f2a6ca82454eab4313b
+size 2271364451