Upload folder using huggingface_hub

README.md

@@ -0,0 +1,158 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- generated_from_trainer
+- axolotl
+datasets:
+- winglian/codeforces-cot-16k-context-topk64-prepared
+model-index:
+- name: outputs/out-kd-7b
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+
+plugins:
+  - axolotl.integrations.kd.KDPlugin
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rms_norm: true
+liger_glu_activation: true
+
+# torch_compile: true
+
+strict: false
+
+chat_template_jinja: "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>' }}\n{%- endif %}\n"
+
+kd_trainer: true
+kd_ce_alpha: 0.2
+kd_alpha: 0.8
+kd_temperature: 1.0
+  # kd_zscore_base_temp: 1.0
+kd_top_k_before_softmax: true
+
+dataloader_prefetch_factor: 256
+dataloader_num_workers: 4
+dataloader_pin_memory: true
+
+gc_steps: -1  # gc at the end of each epoch
+
+datasets:
+- field_messages: messages
+  message_field_content: content
+  message_field_role: role
+  logprobs_field: llm_text_generation_vllm_logprobs
+  path: winglian/codeforces-cot-16k-context-topk64-prepared
+  name: solutions_decontaminated
+  type: axolotl.integrations.kd.chat_template
+  split: train
+  temperature: 1.0
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+output_dir: ./outputs/out-kd-7b
+skip_prepare_dataset: true
+
+sequence_len: 16384
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: kd-7b-codeforces
+wandb_entity: axolotl-ai
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 10
+optimizer: adamw_torch_fused
+lr_scheduler: rex
+learning_rate: 4e-5
+save_safetensors: true
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: true
+
+gradient_checkpointing: offload
+gradient_checkpointing_kwargs:
+use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 280
+evals_per_epoch: 
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: deepspeed_configs/zero2.json
+weight_decay: 0.0
+special_tokens:
+  pad_token: <|endoftext|>
+
+```
+
+</details><br>
+
+# outputs/out-kd-7b
+
+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 winglian/codeforces-cot-16k-context-topk64-prepared 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- 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: rex
+- lr_scheduler_warmup_steps: 280
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5b777611f921d6fd91f00536f59bc6e66373432e11217ae61e4d2388a671e2
+oid sha256:b0a8c6b4b61864f33ff6cf32c4190745cafeae8453ee0d5eff30bcd1692a4de3
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdecd6b6463de4bcc28f106f71066d02c76c2505f3081eb7327f1a32a27a61f7
+oid sha256:72347692641bb2da052989385467f22262bcfbcde430b91bd5d101f3c4634af2
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873d6dc238a86fd494bbe418eb142ac2db38871ae24dae48f7558482b03a42c7
+oid sha256:2a981e34e5fd00d9442ac405faf79a446e744e7af731ef76658a1036b0d14dd6
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148a974b4a6c4e53a6591c4728a07d73b51dbcbe653f21cb191de11b06d65e17
+oid sha256:1d8ccffead1f53d442090c03e0bae36be51cb744f940b518525505a264c66706
 size 1089994880