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

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f766690401ceff5f1fda12b3790967611fa346d51858ec4d0436d5fb82d9ad3
+size 25191384

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f556b63f85c8058978bf5f9b7e5e220ca967c9fc8585851d635b24e2911e2b3e
+size 50492858

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3501787c57b1b9c85fc079fda365c9d62f29d67e14a75cef07fddfbb606de8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8cc15cb1b30ee60888e24ad47c30cd1244bf7a821cb63aae0b7dd4e999274a
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
+size 11422959

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,219 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3589375448671931,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 138.55,
+      "epoch": 0.03589375448671931,
+      "grad_norm": 0.0010730335488915443,
+      "kl": 0.0005896038687205874,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.0,
+      "reward": 0.99,
+      "reward_std": 0.014142135381698609,
+      "rewards/reward_fn": 0.99,
+      "step": 25
+    },
+    {
+      "completion_length": 131.66,
+      "epoch": 0.07178750897343862,
+      "grad_norm": 0.0010653886711224914,
+      "kl": 0.0006372866354649886,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.0,
+      "reward": 0.965,
+      "reward_std": 0.04949747383594513,
+      "rewards/reward_fn": 0.965,
+      "step": 50
+    },
+    {
+      "epoch": 0.07178750897343862,
+      "eval_completion_length": 137.90506329113924,
+      "eval_kl": 0.0006547578797628514,
+      "eval_loss": 2.6065379643114284e-05,
+      "eval_reward": 0.995253164556962,
+      "eval_reward_std": 0.0067130389470088335,
+      "eval_rewards/reward_fn": 0.995253164556962,
+      "eval_runtime": 1868.146,
+      "eval_samples_per_second": 0.168,
+      "eval_steps_per_second": 0.021,
+      "step": 50
+    },
+    {
+      "completion_length": 135.84,
+      "epoch": 0.10768126346015794,
+      "grad_norm": 0.0006992756389081478,
+      "kl": 0.00064181099034613,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0,
+      "reward": 0.98,
+      "reward_std": 0.028284270763397217,
+      "rewards/reward_fn": 0.98,
+      "step": 75
+    },
+    {
+      "completion_length": 132.96,
+      "epoch": 0.14357501794687724,
+      "grad_norm": 0.0013170982711017132,
+      "kl": 0.0006926136535184924,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0,
+      "reward": 0.975,
+      "reward_std": 0.03535533845424652,
+      "rewards/reward_fn": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 0.14357501794687724,
+      "eval_completion_length": 134.5253164556962,
+      "eval_kl": 0.0006582768799006185,
+      "eval_loss": 2.6447118216310628e-05,
+      "eval_reward": 0.9746835443037974,
+      "eval_reward_std": 0.03580287438404711,
+      "eval_rewards/reward_fn": 0.9746835443037974,
+      "eval_runtime": 1865.6091,
+      "eval_samples_per_second": 0.168,
+      "eval_steps_per_second": 0.021,
+      "step": 100
+    },
+    {
+      "completion_length": 134.35,
+      "epoch": 0.17946877243359655,
+      "grad_norm": 0.000720625976100564,
+      "kl": 0.0006820108561078086,
+      "learning_rate": 4.907120743034056e-06,
+      "loss": 0.0,
+      "reward": 0.99,
+      "reward_std": 0.014142135381698609,
+      "rewards/reward_fn": 0.99,
+      "step": 125
+    },
+    {
+      "completion_length": 132.83,
+      "epoch": 0.21536252692031588,
+      "grad_norm": 0.0009368288447149098,
+      "kl": 0.0006625658516713884,
+      "learning_rate": 4.8103715170278645e-06,
+      "loss": 0.0,
+      "reward": 0.98,
+      "reward_std": 0.028284270763397217,
+      "rewards/reward_fn": 0.98,
+      "step": 150
+    },
+    {
+      "epoch": 0.21536252692031588,
+      "eval_completion_length": 136.07753164556962,
+      "eval_kl": 0.0006587035147932983,
+      "eval_loss": 2.6281333703082055e-05,
+      "eval_reward": 0.9889240506329114,
+      "eval_reward_std": 0.01566375754302061,
+      "eval_rewards/reward_fn": 0.9889240506329114,
+      "eval_runtime": 1842.521,
+      "eval_samples_per_second": 0.17,
+      "eval_steps_per_second": 0.022,
+      "step": 150
+    },
+    {
+      "completion_length": 137.885,
+      "epoch": 0.25125628140703515,
+      "grad_norm": 0.0010509429266676307,
+      "kl": 0.0006368485454004257,
+      "learning_rate": 4.713622291021672e-06,
+      "loss": 0.0,
+      "reward": 0.975,
+      "reward_std": 0.03535533845424652,
+      "rewards/reward_fn": 0.975,
+      "step": 175
+    },
+    {
+      "completion_length": 133.24,
+      "epoch": 0.2871500358937545,
+      "grad_norm": 0.0007394957356154919,
+      "kl": 0.0006816260272171349,
+      "learning_rate": 4.61687306501548e-06,
+      "loss": 0.0,
+      "reward": 0.995,
+      "reward_std": 0.007071067690849304,
+      "rewards/reward_fn": 0.995,
+      "step": 200
+    },
+    {
+      "epoch": 0.2871500358937545,
+      "eval_completion_length": 141.43037974683546,
+      "eval_kl": 0.0006899324428478751,
+      "eval_loss": 2.767087789834477e-05,
+      "eval_reward": 0.9857594936708861,
+      "eval_reward_std": 0.01566375754302061,
+      "eval_rewards/reward_fn": 0.9857594936708861,
+      "eval_runtime": 1829.9816,
+      "eval_samples_per_second": 0.171,
+      "eval_steps_per_second": 0.022,
+      "step": 200
+    },
+    {
+      "completion_length": 138.26,
+      "epoch": 0.3230437903804738,
+      "grad_norm": 0.0025397809222340584,
+      "kl": 0.0007233391245245002,
+      "learning_rate": 4.5201238390092885e-06,
+      "loss": 0.0,
+      "reward": 0.98,
+      "reward_std": 0.028284270763397217,
+      "rewards/reward_fn": 0.98,
+      "step": 225
+    },
+    {
+      "completion_length": 136.39,
+      "epoch": 0.3589375448671931,
+      "grad_norm": 0.001854633097536862,
+      "kl": 0.0006911460669653025,
+      "learning_rate": 4.423374613003097e-06,
+      "loss": 0.0,
+      "reward": 0.995,
+      "reward_std": 0.007071067690849304,
+      "rewards/reward_fn": 0.995,
+      "step": 250
+    },
+    {
+      "epoch": 0.3589375448671931,
+      "eval_completion_length": 142.51740506329114,
+      "eval_kl": 0.000728936185117198,
+      "eval_loss": 2.9135468139429577e-05,
+      "eval_reward": 0.9873417721518988,
+      "eval_reward_std": 0.017901437192023556,
+      "eval_rewards/reward_fn": 0.9873417721518988,
+      "eval_runtime": 1854.9938,
+      "eval_samples_per_second": 0.169,
+      "eval_steps_per_second": 0.022,
+      "step": 250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "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 sha256:08c7e6d65b45d5640a03a7264f5a07a6d8ee9bc4936fc268966f6f37df57c090
+size 5752