Upload task output b35aa752-f0ac-42cc-918c-14b2c5d1139c

.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 +1,137 @@
+
+        {%- if tools %}
+            {{- '<|im_start|>system
+' }}
+            {%- if messages[0].role == 'system' %}
+                {{- messages[0].content + '
+
+' }}
+            {%- else %} 
+                {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。
+如果没有一个函数可以使用，请直接使用自然语言回复用户。
+如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。
+如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} 
+            {%- endif %}
+            {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
+            {%- for tool in tools %}
+                {{- "
+" }}
+                {{- tool | tojson }}
+            {%- endfor %}
+            {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
+        {%- else %}
+            {%- if messages[0].role == 'system' %}
+                {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
+            {%- else %} 
+                {{- '<|im_start|>system
+你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>
+' }} 
+            {%- 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 message.content is string 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.content is string %}
+                {%- set content = message.content %}
+            {%- else %}
+                {%- set content = '' %}
+            {%- endif %}
+            {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+                {{- '<|im_start|>' + message.role + '
+' + content + '<|im_end|>' + '
+' }}
+            {%- elif message.role == "assistant" %}
+                {%- set reasoning_content = '' %}
+                {%- if message.reasoning_content is string %}
+                    {%- set reasoning_content = message.reasoning_content %}
+                {%- else %}
+                    {%- if '</think>' in content %}
+                        {%- set reasoning_content = content.split('</think>')[0].rstrip('
+').split('<think>')[-1].lstrip('
+') %}
+                        {%- set content = content.split('</think>')[-1].lstrip('
+') %}
+                    {%- endif %}
+                {%- endif %}
+                {%- if loop.index0 > ns.last_query_index or keep_all_think or (extra_body is defined and extra_body.keep_all_think) %}
+                    {%- if loop.last or (not loop.last and reasoning_content) %}
+                        {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
+                    {%- else %}
+                        {{- '<|im_start|>' + message.role + '
+' + content }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '<|im_start|>' + message.role + '
+' + content }}
+                {%- endif %}
+                {%- if message.tool_calls %}
+                    {%- for tool_call in message.tool_calls %}
+                        {%- if (loop.first and content) or (not loop.first) %}
+                            {{- '
+' }}
+                        {%- endif %}
+                        {%- if tool_call.function %}
+                            {%- set tool_call = tool_call.function %}
+                        {%- endif %}
+                        {{- '<tool_call>
+{"name": "' }}
+                        {{- tool_call.name }}
+                        {{- '", "arguments": ' }}
+                        {%- if tool_call.arguments is string %}
+                            {{- tool_call.arguments }}
+                        {%- else %}
+                            {{- tool_call.arguments | tojson }}
+                        {%- endif %}
+                        {{- '}
+</tool_call>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '<|im_end|>
+' }}
+            {%- elif message.role == "tool" %}
+                {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+                    {{- '<|im_start|>user' }}
+                {%- endif %}
+                {{- '
+<tool_response>
+' }}
+                {{- content }}
+                {{- '
+</tool_response>' }}
+                {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+                    {{- '<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endfor %}
+        {%- if add_generation_prompt %}
+            {{- '<|im_start|>assistant
+' }}
+        {%- endif %}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 166100,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 166101,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10496,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 70000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 166144
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 166100,
+  "eos_token_id": [
+    166101
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1"
+}

loss.txt

@@ -0,0 +1 @@
+100,0.6807754635810852

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa3d9455932bdc497f16a03b1965d01bd0a94bc319f9a684b66158de102de5e
+size 7867308040

run_meta.json

@@ -0,0 +1 @@
+{"global_step": 160, "max_steps": 400, "reached_max_steps": false, "epoch": 1.6, "train_s": 1079.3, "best_step": 160, "best_dev": 0.6330183148384094, "dev_curve": [[80, 0.69614], [100, 0.68078], [120, 0.74586], [140, 0.76211], [160, 0.74242], [160, 0.68078], [160, 0.64114], [160, 0.63302], [160, 0.64154], [160, 0.64679], [160, 0.65228]], "packed": true, "length_grouped": false, "max_length": 256, "per_device_bs": 48, "grad_accum": 1, "world_size": 1, "train_items": 4800, "devpass": true, "kept_prior": false, "pass_seed": "42", "one_epoch_pass": false, "E_pred": 22.0584, "ckpt_epoch": 1.6, "group": {"arch": "dense", "params_b": 3.934, "length_class": "short", "completion_p50": 10, "seq_p50": 39, "seq_p99": 188, "num_records": 7620, "total_tokens": 379971, "hours": 1.0, "epochs_est": 2.27, "epochs_measured": 33.125, "aug_marks": {"matrices": 224, "zero_frac_max": 0.0, "zero_frac_mean": 0.0, "pruned_frac": 0.0, "rms_scaled_frac": 0.005, "rms_log2_dev_max": 0.539, "grid_tested": 224, "grid_anomalous": 0, "grid_scaled": 0, "detector": "neighbour-v2+grid-v1"}, "aug_guess": "none-or-weak"}}

run_summary.json

@@ -0,0 +1 @@
+{"schema": 2, "task_type": "InstructTextTask", "hours": 1.0, "passes_planned": 4, "lean_passes": false, "passes": [{"n": 1, "seed": 42, "ok": true, "has_weights": true, "kept": true, "spent_s": 2113.8, "train_s_est": 1370.9, "gate": null, "meta": {"global_step": 160, "max_steps": 400, "reached_max_steps": false, "epoch": 1.6, "train_s": 1079.3, "best_step": 160, "best_dev": 0.6330183148384094, "kept_prior": false, "pass_seed": "42", "one_epoch_pass": false, "E_pred": 22.0584, "ckpt_epoch": 1.6}}], "stop_reason": "gate", "ship_source": "single", "scan_s": 743.0, "stop_gate": {"left_s": 1253, "need_s": 1371}, "passes_used": [1], "train_success": true, "weights_complete": true, "passes_run": 1, "remaining_at_end_s": 1250, "E_pred": 22.0584, "E_used": 1.6, "ckpt_epoch": [1.6]}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a002676e923776f5a59d21320d667920e732000f7762fb72e6be6e911790e060
+size 18450976

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}