Upload 18 files

.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

README.md

@@ -1,3 +1,72 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: sft_v2_61w
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+本项工作在同元软控实习期间完成，旨在通过微调得到更适配 Julia 语言的大模型。
+
+# sft_v2_61w
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) on the julia_func_datasetv2_61w dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9146
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9108        | 0.8828 | 4000 | 0.9155          |
+| 0.904         | 1.7654 | 8000 | 0.9145          |
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3dfbb80bb1f2e31bbfbebe0b9ed5143d7f399d1bf1fa602b8bcf85eb199e1df
+size 80792096

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.9146204590797424,
+    "eval_runtime": 247.06,
+    "eval_samples_per_second": 121.428,
+    "eval_steps_per_second": 7.589,
+    "total_flos": 1.2106519982783857e+19,
+    "train_loss": 0.9370549143886313,
+    "train_runtime": 28045.4399,
+    "train_samples_per_second": 41.361,
+    "train_steps_per_second": 0.323
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.9146204590797424,
+    "eval_runtime": 247.06,
+    "eval_samples_per_second": 121.428,
+    "eval_steps_per_second": 7.589
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.2106519982783857e+19,
+    "train_loss": 0.9370549143886313,
+    "train_runtime": 28045.4399,
+    "train_samples_per_second": 41.361,
+    "train_steps_per_second": 0.323
+}

trainer_log.jsonl

@@ -0,0 +1,14 @@
+{"current_steps": 800, "total_steps": 9064, "loss": 1.2362, "lr": 8.809261300992283e-05, "epoch": 0.17655172413793102, "percentage": 8.83, "elapsed_time": "0:40:10", "remaining_time": "6:54:58"}
+{"current_steps": 1600, "total_steps": 9064, "loss": 0.9159, "lr": 9.823469895169365e-05, "epoch": 0.35310344827586204, "percentage": 17.65, "elapsed_time": "1:20:49", "remaining_time": "6:17:05"}
+{"current_steps": 2400, "total_steps": 9064, "loss": 0.9125, "lr": 9.19696754273079e-05, "epoch": 0.5296551724137931, "percentage": 26.48, "elapsed_time": "2:01:31", "remaining_time": "5:37:25"}
+{"current_steps": 3200, "total_steps": 9064, "loss": 0.9134, "lr": 8.175175096510351e-05, "epoch": 0.7062068965517241, "percentage": 35.3, "elapsed_time": "2:41:49", "remaining_time": "4:56:32"}
+{"current_steps": 4000, "total_steps": 9064, "loss": 0.9108, "lr": 6.854329762962416e-05, "epoch": 0.8827586206896552, "percentage": 44.13, "elapsed_time": "3:22:08", "remaining_time": "4:15:54"}
+{"current_steps": 4000, "total_steps": 9064, "eval_loss": 0.9154898524284363, "epoch": 0.8827586206896552, "percentage": 44.13, "elapsed_time": "3:26:15", "remaining_time": "4:21:07"}
+{"current_steps": 4800, "total_steps": 9064, "loss": 0.9084, "lr": 5.358834952514551e-05, "epoch": 1.059144827586207, "percentage": 52.96, "elapsed_time": "4:07:28", "remaining_time": "3:39:50"}
+{"current_steps": 5600, "total_steps": 9064, "loss": 0.9046, "lr": 3.8295433827190085e-05, "epoch": 1.2356965517241378, "percentage": 61.78, "elapsed_time": "4:47:53", "remaining_time": "2:58:05"}
+{"current_steps": 6400, "total_steps": 9064, "loss": 0.9043, "lr": 2.4104909084852035e-05, "epoch": 1.412248275862069, "percentage": 70.61, "elapsed_time": "5:28:10", "remaining_time": "2:16:36"}
+{"current_steps": 7200, "total_steps": 9064, "loss": 0.9047, "lr": 1.2353305495017958e-05, "epoch": 1.5888, "percentage": 79.44, "elapsed_time": "6:08:58", "remaining_time": "1:35:31"}
+{"current_steps": 8000, "total_steps": 9064, "loss": 0.904, "lr": 4.147444217922592e-06, "epoch": 1.765351724137931, "percentage": 88.26, "elapsed_time": "6:49:27", "remaining_time": "0:54:27"}
+{"current_steps": 8000, "total_steps": 9064, "eval_loss": 0.9144690036773682, "epoch": 1.765351724137931, "percentage": 88.26, "elapsed_time": "6:53:34", "remaining_time": "0:55:00"}
+{"current_steps": 8800, "total_steps": 9064, "loss": 0.9044, "lr": 2.6019176748554587e-07, "epoch": 1.9419034482758621, "percentage": 97.09, "elapsed_time": "7:34:00", "remaining_time": "0:13:37"}
+{"current_steps": 9064, "total_steps": 9064, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:47:24", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 4000,
+  "global_step": 9064,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17655172413793102,
+      "grad_norm": 0.11938353627920151,
+      "learning_rate": 8.809261300992283e-05,
+      "loss": 1.2362,
+      "step": 800
+    },
+    {
+      "epoch": 0.35310344827586204,
+      "grad_norm": 0.148575097322464,
+      "learning_rate": 9.823469895169365e-05,
+      "loss": 0.9159,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5296551724137931,
+      "grad_norm": 0.21376433968544006,
+      "learning_rate": 9.19696754273079e-05,
+      "loss": 0.9125,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7062068965517241,
+      "grad_norm": 0.09860826283693314,
+      "learning_rate": 8.175175096510351e-05,
+      "loss": 0.9134,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8827586206896552,
+      "grad_norm": 0.11440066993236542,
+      "learning_rate": 6.854329762962416e-05,
+      "loss": 0.9108,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8827586206896552,
+      "eval_loss": 0.9154898524284363,
+      "eval_runtime": 247.4123,
+      "eval_samples_per_second": 121.255,
+      "eval_steps_per_second": 7.578,
+      "step": 4000
+    },
+    {
+      "epoch": 1.059144827586207,
+      "grad_norm": 0.10314279049634933,
+      "learning_rate": 5.358834952514551e-05,
+      "loss": 0.9084,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2356965517241378,
+      "grad_norm": 0.15208840370178223,
+      "learning_rate": 3.8295433827190085e-05,
+      "loss": 0.9046,
+      "step": 5600
+    },
+    {
+      "epoch": 1.412248275862069,
+      "grad_norm": 0.10573920607566833,
+      "learning_rate": 2.4104909084852035e-05,
+      "loss": 0.9043,
+      "step": 6400
+    },
+    {
+      "epoch": 1.5888,
+      "grad_norm": 0.2402600795030594,
+      "learning_rate": 1.2353305495017958e-05,
+      "loss": 0.9047,
+      "step": 7200
+    },
+    {
+      "epoch": 1.765351724137931,
+      "grad_norm": 0.10216963291168213,
+      "learning_rate": 4.147444217922592e-06,
+      "loss": 0.904,
+      "step": 8000
+    },
+    {
+      "epoch": 1.765351724137931,
+      "eval_loss": 0.9144690036773682,
+      "eval_runtime": 247.1254,
+      "eval_samples_per_second": 121.396,
+      "eval_steps_per_second": 7.587,
+      "step": 8000
+    },
+    {
+      "epoch": 1.9419034482758621,
+      "grad_norm": 0.17538346350193024,
+      "learning_rate": 2.6019176748554587e-07,
+      "loss": 0.9044,
+      "step": 8800
+    },
+    {
+      "epoch": 2.0,
+      "step": 9064,
+      "total_flos": 1.2106519982783857e+19,
+      "train_loss": 0.9370549143886313,
+      "train_runtime": 28045.4399,
+      "train_samples_per_second": 41.361,
+      "train_steps_per_second": 0.323
+    }
+  ],
+  "logging_steps": 800,
+  "max_steps": 9064,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 4000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2106519982783857e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13b2aa364c3d808469a6e54c1dc7bdb748951588e2d452e41a0844ab80023c5
+size 6161