Upload CNN/DM Qwen3-Reranker-0.6B 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

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "problem_type": "regression",
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "salience_document_payload_format": "Document:\\n[indexed source sentences]\\n\\nCandidate sentence:\\n[Sxxx] sentence",
+  "salience_instruction": "Given an indexed document and a designated candidate sentence, judge whether the candidate sentence contains information that is important for representing the document as a whole.",
+  "salience_loss_type": "mse",
+  "salience_query": "Is the designated candidate sentence salient to the document as a whole?",
+  "salience_reranker_bias": 0.49982699751853943,
+  "salience_reranker_false_token_id": 2152,
+  "salience_reranker_scale": 0.09945447742938995,
+  "salience_reranker_true_token_id": 9693,
+  "salience_score_aggregation": "scalar",
+  "salience_score_semantics": "model_balanced_salience_probability",
+  "salience_score_transform": "affine_yes_no_logit_difference",
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

eval_metrics.json

@@ -0,0 +1,15 @@
+{
+  "eval_loss": 0.025318242609500885,
+  "eval_mse": 0.025318242609500885,
+  "eval_rmse": 0.1591170720240317,
+  "eval_mae": 0.11795498430728912,
+  "eval_pearson": 0.8350127545867635,
+  "eval_spearman": 0.8358440526327534,
+  "eval_article_spearman": 0.7503282767323686,
+  "eval_article_ndcg_at_3": 0.9025520167592553,
+  "eval_article_ndcg_at_5": 0.9049475539825387,
+  "eval_runtime": 128.5009,
+  "eval_samples_per_second": 52.863,
+  "eval_steps_per_second": 26.436,
+  "epoch": 2.8970709052193886
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6b7723ec60fd3dabd8c8f085a0673fcc692005dcda229c4d9db9f9c787343f
+size 1191588280

qwen3_reranker_sentence_scorer_config.json

@@ -0,0 +1,20 @@
+{
+  "schema_version": 1,
+  "model_name": "Qwen/Qwen3-Reranker-0.6B",
+  "resolved_model_name": "/lustre/fsmisc/dataset/HuggingFace_Models/Qwen/Qwen3-Reranker-0.6B",
+  "training_objective": "identity_mse",
+  "target_field": "salience_score_model_balanced",
+  "native_score": "yes_logit_minus_no_logit",
+  "scale": 0.09945447742938995,
+  "bias": 0.49982699751853943,
+  "initial_scale": 0.1,
+  "initial_bias": 0.5,
+  "instruction": "Given an indexed document and a designated candidate sentence, judge whether the candidate sentence contains information that is important for representing the document as a whole.",
+  "query": "Is the designated candidate sentence salient to the document as a whole?",
+  "text_field": "model_input_text",
+  "max_length": 4608,
+  "attn_implementation": "sdpa",
+  "pairwise": false,
+  "article_balanced": false,
+  "multihead": false
+}

run_summary.md

@@ -0,0 +1,52 @@
+# CNN/DailyMail Qwen3-Reranker Pointwise MSE Run
+
+- model_name: `Qwen/Qwen3-Reranker-0.6B`
+- resolved_model_name: `/lustre/fsmisc/dataset/HuggingFace_Models/Qwen/Qwen3-Reranker-0.6B`
+- target_mode: `model_balanced`
+- target_field: `salience_score_model_balanced`
+- loss_type: `mse`
+- score_transform: `identity_after_affine_yes_no_logit_difference`
+- pairwise: `False`
+- article_balanced: `False`
+- multihead: `False`
+- instruction: `Given an indexed document and a designated candidate sentence, judge whether the candidate sentence contains information that is important for representing the document as a whole.`
+- query: `Is the designated candidate sentence salient to the document as a whole?`
+- initial_scale: `0.1`
+- initial_bias: `0.5`
+- trained_scale: `0.09945447742938995`
+- trained_bias: `0.49982699751853943`
+- 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: `sdpa`
+- 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`
+- bf16: `True`
+- fp16: `False`
+- gradient_checkpointing: `True`
+
+## Eval Metrics
+
+- epoch: `2.8970709052193886`
+- eval_article_ndcg_at_3: `0.9025520167592553`
+- eval_article_ndcg_at_5: `0.9049475539825387`
+- eval_article_spearman: `0.7503282767323686`
+- eval_loss: `0.025318242609500885`
+- eval_mae: `0.11795498430728912`
+- eval_mse: `0.025318242609500885`
+- eval_pearson: `0.8350127545867635`
+- eval_rmse: `0.1591170720240317`
+- eval_runtime: `128.5009`
+- eval_samples_per_second: `52.863`
+- eval_spearman: `0.8358440526327534`
+- eval_steps_per_second: `26.436`

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ed0d3e22f11b44ffee65619d1099fb6fc9e16df506ceec57ae458f5c36e1e2
+size 11422749

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}