Upload folder using huggingface_hub

.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 +1,61 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: dpo
+  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. -->
+
+# dpo
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the spider_dpo dataset.
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.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_steps: 0.1
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.2.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_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 sha256:34951a2d4294a30f58b9f230364501ffaae66f8213e858bbfb46d59a9d07d3b2
+size 323014168

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.008142593959854e+17,
+    "train_loss": 0.22079544021533085,
+    "train_runtime": 3380.4206,
+    "train_samples_per_second": 0.615,
+    "train_steps_per_second": 0.038
+}

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 %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "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": 1.008142593959854e+17,
+    "train_loss": 0.22079544021533085,
+    "train_runtime": 3380.4206,
+    "train_samples_per_second": 0.615,
+    "train_steps_per_second": 0.038
+}

trainer_log.jsonl

@@ -0,0 +1,14 @@
+{"current_steps": 10, "total_steps": 130, "loss": 0.4812039852142334, "accuracy": 0.737500011920929, "lr": 3.461538461538462e-05, "epoch": 0.15384615384615385, "percentage": 7.69, "elapsed_time": "0:04:14", "remaining_time": "0:50:58"}
+{"current_steps": 20, "total_steps": 130, "loss": 0.38157622814178466, "accuracy": 0.8062500357627869, "lr": 4.967625656594782e-05, "epoch": 0.3076923076923077, "percentage": 15.38, "elapsed_time": "0:08:44", "remaining_time": "0:48:04"}
+{"current_steps": 30, "total_steps": 130, "loss": 0.31204392910003664, "accuracy": 0.824999988079071, "lr": 4.77281074950681e-05, "epoch": 0.46153846153846156, "percentage": 23.08, "elapsed_time": "0:13:04", "remaining_time": "0:43:36"}
+{"current_steps": 40, "total_steps": 130, "loss": 0.26097993850708007, "accuracy": 0.8687500357627869, "lr": 4.415111107797445e-05, "epoch": 0.6153846153846154, "percentage": 30.77, "elapsed_time": "0:17:23", "remaining_time": "0:39:08"}
+{"current_steps": 50, "total_steps": 130, "loss": 0.2709719896316528, "accuracy": 0.862500011920929, "lr": 3.920161866827889e-05, "epoch": 0.7692307692307693, "percentage": 38.46, "elapsed_time": "0:21:54", "remaining_time": "0:35:03"}
+{"current_steps": 60, "total_steps": 130, "loss": 0.4293703079223633, "accuracy": 0.8125, "lr": 3.323434381080199e-05, "epoch": 0.9230769230769231, "percentage": 46.15, "elapsed_time": "0:25:56", "remaining_time": "0:30:15"}
+{"current_steps": 70, "total_steps": 130, "loss": 0.22459855079650878, "accuracy": 0.893750011920929, "lr": 2.667694110977506e-05, "epoch": 1.0769230769230769, "percentage": 53.85, "elapsed_time": "0:30:16", "remaining_time": "0:25:56"}
+{"current_steps": 80, "total_steps": 130, "loss": 0.10246082544326782, "accuracy": 0.981249988079071, "lr": 1.9999357655598893e-05, "epoch": 1.2307692307692308, "percentage": 61.54, "elapsed_time": "0:34:24", "remaining_time": "0:21:30"}
+{"current_steps": 90, "total_steps": 130, "loss": 0.07779874801635742, "accuracy": 0.981249988079071, "lr": 1.3680153490759073e-05, "epoch": 1.3846153846153846, "percentage": 69.23, "elapsed_time": "0:38:56", "remaining_time": "0:17:18"}
+{"current_steps": 100, "total_steps": 130, "loss": 0.09446020126342773, "accuracy": 0.9750000238418579, "lr": 8.172204814310742e-06, "epoch": 1.5384615384615383, "percentage": 76.92, "elapsed_time": "0:43:13", "remaining_time": "0:12:58"}
+{"current_steps": 110, "total_steps": 130, "loss": 0.08398746848106384, "accuracy": 0.987500011920929, "lr": 3.8702478614051355e-06, "epoch": 1.6923076923076923, "percentage": 84.62, "elapsed_time": "0:47:27", "remaining_time": "0:08:37"}
+{"current_steps": 120, "total_steps": 130, "loss": 0.06980652809143066, "accuracy": 1.0, "lr": 1.0825894793143721e-06, "epoch": 1.8461538461538463, "percentage": 92.31, "elapsed_time": "0:51:48", "remaining_time": "0:04:19"}
+{"current_steps": 130, "total_steps": 130, "loss": 0.081082022190094, "accuracy": 0.96875, "lr": 9.011808227865625e-09, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:56:19", "remaining_time": "0:00:00"}
+{"current_steps": 130, "total_steps": 130, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:56:20", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.29832401871681213,
+      "learning_rate": 3.461538461538462e-05,
+      "logits/chosen": -1.1990242004394531,
+      "logits/rejected": -1.1565947532653809,
+      "logps/chosen": -34.47224044799805,
+      "logps/rejected": -57.595638275146484,
+      "loss": 0.4812039852142334,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.6355812549591064,
+      "rewards/margins": 1.8687772750854492,
+      "rewards/rejected": -3.5043587684631348,
+      "step": 10
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.31452351808547974,
+      "learning_rate": 4.967625656594782e-05,
+      "logits/chosen": -1.1797922849655151,
+      "logits/rejected": -1.1334644556045532,
+      "logps/chosen": -30.18818473815918,
+      "logps/rejected": -54.1025505065918,
+      "loss": 0.38157622814178466,
+      "rewards/accuracies": 0.8062500357627869,
+      "rewards/chosen": -1.2342875003814697,
+      "rewards/margins": 1.9759091138839722,
+      "rewards/rejected": -3.2101962566375732,
+      "step": 20
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.2767532467842102,
+      "learning_rate": 4.77281074950681e-05,
+      "logits/chosen": -1.218713641166687,
+      "logits/rejected": -1.1803112030029297,
+      "logps/chosen": -31.594274520874023,
+      "logps/rejected": -58.6033935546875,
+      "loss": 0.31204392910003664,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.2332490682601929,
+      "rewards/margins": 2.2641992568969727,
+      "rewards/rejected": -3.497448444366455,
+      "step": 30
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.3287574052810669,
+      "learning_rate": 4.415111107797445e-05,
+      "logits/chosen": -1.3382649421691895,
+      "logits/rejected": -1.30353581905365,
+      "logps/chosen": -36.43912887573242,
+      "logps/rejected": -70.29068756103516,
+      "loss": 0.26097993850708007,
+      "rewards/accuracies": 0.8687500357627869,
+      "rewards/chosen": -1.6973193883895874,
+      "rewards/margins": 3.017174005508423,
+      "rewards/rejected": -4.714493751525879,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.3445669710636139,
+      "learning_rate": 3.920161866827889e-05,
+      "logits/chosen": -1.4549230337142944,
+      "logits/rejected": -1.4277979135513306,
+      "logps/chosen": -41.87653732299805,
+      "logps/rejected": -82.90950012207031,
+      "loss": 0.2709719896316528,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -2.2981889247894287,
+      "rewards/margins": 3.5901012420654297,
+      "rewards/rejected": -5.8882904052734375,
+      "step": 50
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.4734262526035309,
+      "learning_rate": 3.323434381080199e-05,
+      "logits/chosen": -1.4583113193511963,
+      "logits/rejected": -1.4419019222259521,
+      "logps/chosen": -46.35929489135742,
+      "logps/rejected": -82.18633270263672,
+      "loss": 0.4293703079223633,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -2.7741143703460693,
+      "rewards/margins": 3.1638267040252686,
+      "rewards/rejected": -5.937941074371338,
+      "step": 60
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.14828024804592133,
+      "learning_rate": 2.667694110977506e-05,
+      "logits/chosen": -1.3716756105422974,
+      "logits/rejected": -1.3496290445327759,
+      "logps/chosen": -37.190982818603516,
+      "logps/rejected": -80.84061431884766,
+      "loss": 0.22459855079650878,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": -1.9332157373428345,
+      "rewards/margins": 3.8292477130889893,
+      "rewards/rejected": -5.762463569641113,
+      "step": 70
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.1763170063495636,
+      "learning_rate": 1.9999357655598893e-05,
+      "logits/chosen": -1.355380892753601,
+      "logits/rejected": -1.3304802179336548,
+      "logps/chosen": -39.43621826171875,
+      "logps/rejected": -82.64469909667969,
+      "loss": 0.10246082544326782,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -2.0429646968841553,
+      "rewards/margins": 3.7551822662353516,
+      "rewards/rejected": -5.798146724700928,
+      "step": 80
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.08582232892513275,
+      "learning_rate": 1.3680153490759073e-05,
+      "logits/chosen": -1.3984593152999878,
+      "logits/rejected": -1.3604938983917236,
+      "logps/chosen": -35.92609405517578,
+      "logps/rejected": -94.2962875366211,
+      "loss": 0.07779874801635742,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -1.6332558393478394,
+      "rewards/margins": 5.143055438995361,
+      "rewards/rejected": -6.776310920715332,
+      "step": 90
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.11894813179969788,
+      "learning_rate": 8.172204814310742e-06,
+      "logits/chosen": -1.4377853870391846,
+      "logits/rejected": -1.4119752645492554,
+      "logps/chosen": -33.87895965576172,
+      "logps/rejected": -80.11370086669922,
+      "loss": 0.09446020126342773,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -1.5904297828674316,
+      "rewards/margins": 4.260800838470459,
+      "rewards/rejected": -5.851230144500732,
+      "step": 100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.0858096107840538,
+      "learning_rate": 3.8702478614051355e-06,
+      "logits/chosen": -1.4167169332504272,
+      "logits/rejected": -1.3845655918121338,
+      "logps/chosen": -38.7296257019043,
+      "logps/rejected": -86.01542663574219,
+      "loss": 0.08398746848106384,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -2.0574593544006348,
+      "rewards/margins": 4.346583843231201,
+      "rewards/rejected": -6.404043674468994,
+      "step": 110
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.08499918133020401,
+      "learning_rate": 1.0825894793143721e-06,
+      "logits/chosen": -1.4523096084594727,
+      "logits/rejected": -1.4183976650238037,
+      "logps/chosen": -36.14750289916992,
+      "logps/rejected": -87.8320083618164,
+      "loss": 0.06980652809143066,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.8463581800460815,
+      "rewards/margins": 4.731562614440918,
+      "rewards/rejected": -6.577920436859131,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13648074865341187,
+      "learning_rate": 9.011808227865625e-09,
+      "logits/chosen": -1.44231116771698,
+      "logits/rejected": -1.4165829420089722,
+      "logps/chosen": -36.7476921081543,
+      "logps/rejected": -86.03533172607422,
+      "loss": 0.081082022190094,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -1.7559616565704346,
+      "rewards/margins": 4.578075885772705,
+      "rewards/rejected": -6.334037780761719,
+      "step": 130
+    },
+    {
+      "epoch": 2.0,
+      "step": 130,
+      "total_flos": 1.008142593959854e+17,
+      "train_loss": 0.22079544021533085,
+      "train_runtime": 3380.4206,
+      "train_samples_per_second": 0.615,
+      "train_steps_per_second": 0.038
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.008142593959854e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ab2bab02f3075b1bd6b20220e3f4d76681b555bce8eb919646fd52350a6613
+size 5585