Upload folder using huggingface_hub

README.md

@@ -1,6 +1,7 @@
-# Test LoRA Adapter for SGLang Embedding LoRA
+# Trained LoRA Adapter for SGLang Embedding LoRA Testing
 
-This is a test LoRA adapter (randomly initialized without tuning) for testing SGLang's embedding LoRA implementation.
+This is a **fine-tuned** LoRA adapter for testing SGLang's embedding LoRA implementation.
+Unlike randomly initialized adapters, this one produces coherent text outputs.
 
 ## Configuration
 
@@ -8,6 +9,8 @@ This is a test LoRA adapter (randomly initialized without tuning) for testing SG
 - **LoRA rank (r):** 8
 - **LoRA alpha:** 16
 - **Target modules:** embed_tokens, lm_head, q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+- **Training steps:** 500
+- **Training data:** alpaca dataset (instruction following)
 
 ## Weight Shapes
 
@@ -34,19 +37,20 @@ v_proj.lora_B: (256, 8)
 
 ## Purpose
 
-This adapter tests that SGLang's `ChunkedSgmvLoRABackend.run_lora_a_embedding()` correctly handles embedding LoRA layers (`embed_tokens`, `lm_head`).
+This adapter tests that SGLang's `ChunkedSgmvLoRABackend.run_lora_a_embedding()` correctly
+handles embedding LoRA layers (`embed_tokens`, `lm_head`).
 
 **Key:** `embed_tokens` is in `target_modules` (LoRA decomposition), NOT `modules_to_save` (full weights).
 
 ## Usage with SGLang
 
 ```python
-# This adapter contains randomly initialized weights for testing purposes only.
 # Used by: test/srt/lora/test_lora_hf_sgl_logprob_diff.py
+# The adapter produces coherent outputs for meaningful CI/CD verification.
 ```
 
 ## Created with
 
 ```bash
-python scripts/playground/lora/create_embedding_lora_adapter.py
+python scripts/playground/lora/train_embedding_lora_adapter.py --num_train_steps 500
 ```

adapter_config.json

@@ -31,13 +31,13 @@
   "target_modules": [
     "q_proj",
     "up_proj",
-    "v_proj",
+    "down_proj",
     "gate_proj",
-    "embed_tokens",
-    "lm_head",
+    "k_proj",
+    "v_proj",
     "o_proj",
-    "down_proj",
-    "k_proj"
+    "embed_tokens",
+    "lm_head"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656a39751852f5b1143f92ffd5d5a501cb1a70dcd0f6509fb1e6e40eb9aeefdf
+oid sha256:33625e6a90750f4c9b5536f49792fd814c3a57c60b39126e5a83dc827822bf9b
 size 289595592

checkpoints/README.md

@@ -0,0 +1,58 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: transformers
+model_name: checkpoints
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for checkpoints
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.26.0
+- Transformers: 4.57.3
+- Pytorch: 2.9.1
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

checkpoints/checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoints/checkpoint-500/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "embed_tokens",
+    "lm_head"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33625e6a90750f4c9b5536f49792fd814c3a57c60b39126e5a83dc827822bf9b
+size 289595592

checkpoints/checkpoint-500/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoints/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830dbcb017e3de1782a73e14533dc15e793dfa50eb5a65d43e6843ef6e8e7514
+size 55083083

checkpoints/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoints/checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec75da29c1cbf10b3263555aa2baf297b043d42aa8023b3a6dd492938dd97e8
+size 1383

checkpoints/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213e51f02242106184d4fda7fd6be7019344a155478d785080eb34a1159f7764
+size 1465

checkpoints/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoints/checkpoint-500/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6480721473693847,
+      "epoch": 0.05,
+      "grad_norm": 27.1102352142334,
+      "learning_rate": 8e-05,
+      "loss": 1.8005,
+      "mean_token_accuracy": 0.5941327238082885,
+      "num_tokens": 9693.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.3281144857406617,
+      "epoch": 0.1,
+      "grad_norm": 9.47355842590332,
+      "learning_rate": 0.00018,
+      "loss": 1.2936,
+      "mean_token_accuracy": 0.6876855921745301,
+      "num_tokens": 19797.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.2546486043930054,
+      "epoch": 0.15,
+      "grad_norm": 7.4732513427734375,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 1.2329,
+      "mean_token_accuracy": 0.691328091621399,
+      "num_tokens": 28636.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.1987505912780763,
+      "epoch": 0.2,
+      "grad_norm": 10.677826881408691,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.165,
+      "mean_token_accuracy": 0.7062379860877991,
+      "num_tokens": 38194.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2390620636940002,
+      "epoch": 0.25,
+      "grad_norm": 8.650012016296387,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 1.2323,
+      "mean_token_accuracy": 0.686786060333252,
+      "num_tokens": 49170.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.2445489859580994,
+      "epoch": 0.3,
+      "grad_norm": 6.545881748199463,
+      "learning_rate": 0.00017880107536067218,
+      "loss": 1.233,
+      "mean_token_accuracy": 0.6857695412635804,
+      "num_tokens": 58907.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.2420870399475097,
+      "epoch": 0.35,
+      "grad_norm": 24.16084098815918,
+      "learning_rate": 0.00016743023875837233,
+      "loss": 1.2297,
+      "mean_token_accuracy": 0.6925088000297547,
+      "num_tokens": 68206.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.2456481051445008,
+      "epoch": 0.4,
+      "grad_norm": 23.415494918823242,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 1.2531,
+      "mean_token_accuracy": 0.6884878659248352,
+      "num_tokens": 77989.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.2355119800567627,
+      "epoch": 0.45,
+      "grad_norm": 7.648189544677734,
+      "learning_rate": 0.00013810703763502744,
+      "loss": 1.2108,
+      "mean_token_accuracy": 0.6975953841209411,
+      "num_tokens": 87614.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.2422665166854858,
+      "epoch": 0.5,
+      "grad_norm": 7.272965908050537,
+      "learning_rate": 0.00012147353271670634,
+      "loss": 1.2552,
+      "mean_token_accuracy": 0.687971031665802,
+      "num_tokens": 97427.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.2536789083480835,
+      "epoch": 0.55,
+      "grad_norm": 7.070037364959717,
+      "learning_rate": 0.00010418756537291996,
+      "loss": 1.2526,
+      "mean_token_accuracy": 0.6898462009429932,
+      "num_tokens": 107088.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.2259885239601136,
+      "epoch": 0.6,
+      "grad_norm": 13.018112182617188,
+      "learning_rate": 8.677436097428775e-05,
+      "loss": 1.2247,
+      "mean_token_accuracy": 0.6857342338562011,
+      "num_tokens": 116177.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.2294299459457398,
+      "epoch": 0.65,
+      "grad_norm": 7.353261947631836,
+      "learning_rate": 6.976301092495556e-05,
+      "loss": 1.2238,
+      "mean_token_accuracy": 0.6885941863059998,
+      "num_tokens": 126328.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.2531250643730163,
+      "epoch": 0.7,
+      "grad_norm": 7.604862689971924,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 1.2219,
+      "mean_token_accuracy": 0.6879838514328003,
+      "num_tokens": 135285.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.2012500953674317,
+      "epoch": 0.75,
+      "grad_norm": 7.651504039764404,
+      "learning_rate": 3.8985483609873244e-05,
+      "loss": 1.2111,
+      "mean_token_accuracy": 0.6910693979263306,
+      "num_tokens": 145111.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.2419355368614198,
+      "epoch": 0.8,
+      "grad_norm": 8.24601936340332,
+      "learning_rate": 2.615446593741161e-05,
+      "loss": 1.2345,
+      "mean_token_accuracy": 0.685720636844635,
+      "num_tokens": 155061.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.2203574657440186,
+      "epoch": 0.85,
+      "grad_norm": 5.648503303527832,
+      "learning_rate": 1.5567207449798515e-05,
+      "loss": 1.1986,
+      "mean_token_accuracy": 0.6945811367034912,
+      "num_tokens": 164613.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.1166097807884217,
+      "epoch": 0.9,
+      "grad_norm": 7.915076732635498,
+      "learning_rate": 7.545396638768698e-06,
+      "loss": 1.1173,
+      "mean_token_accuracy": 0.7110410404205322,
+      "num_tokens": 174362.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.2107400488853455,
+      "epoch": 0.95,
+      "grad_norm": 8.340585708618164,
+      "learning_rate": 2.332772166583208e-06,
+      "loss": 1.1966,
+      "mean_token_accuracy": 0.7019165325164795,
+      "num_tokens": 183648.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.2142256331443786,
+      "epoch": 1.0,
+      "grad_norm": 8.785581588745117,
+      "learning_rate": 8.771699011416168e-08,
+      "loss": 1.1894,
+      "mean_token_accuracy": 0.7058351802825927,
+      "num_tokens": 193469.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2045157535088640.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b2da819e3a561790f622bce5c99c4124724dc2c931da23138645704238828e
+size 6289