Upload folder using huggingface_hub

README.md

@@ -1,3 +1,207 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-8B
+- lora
+- transformers
+---
+
+# 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 0.18.1

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/Qwen3-8B",
+  "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": 0.05,
+  "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": [
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_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:e2425fca330e5bf4148f423d61594821c71ad6c8ad4af29d41d4b50830899787
+size 349243752

optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c634cb3cab99e426fff0a69b9b974dc226cffbae25fd040d5bc26b1175cdd392
+size 698863435

pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865797ccc443425bb0750f4d8abc969c2fc83e55017a1b743d422ab5a034b79c
+size 349364537

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab83fae9a0954fb792d137bc45aa43f063c346d7d90d28b5635ebf0e300c71d
+size 16325

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae0723373cd1db0f9f78c8c2151a3b6bad70e1eb87c15720a4b0b033c73d429
+size 16325

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d9a77bab553184d3cedcb2dc1877cd0d8b4d6dafcc57092c3e9719abd11b83
+size 16325

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e3f49f3d13c928a8ce0987185b9e6a1052941f92df26b899f27d882fdf2164
+size 16325

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50b2bf35987930fad4a9bfd1527d4cccbb0afb73a47c20252e89778d7cb9456
+size 16325

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcdf5a601553d87420f61ad6d821dc5e771b1f0ca2fbace940c6de0c9cdb9b7
+size 16325

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b62488d8474c883fa49397f82989cccb8dfa0532db9cf9ed62b93951cce268
+size 16325

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4baeab28b178c4f91de107bbe1a0ad80411ce291da2104ebafefb55b1eb7f51
+size 16325

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f152824963d9fd347bcf4f2f2f0f4922248cd0396552fc01cdbe26f478f8630a
+size 1465

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 80,
+  "best_metric": 0.9958399986721193,
+  "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen3-8b_r32/checkpoint-80",
+  "epoch": 1.8181818181818183,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36363636363636365,
+      "eval_accuracy": 0.9044056525353283,
+      "eval_balanced_accuracy": 0.901877133105802,
+      "eval_loss": 0.08732637017965317,
+      "eval_macro_f1": 0.90297659081011,
+      "eval_runtime": 39.9812,
+      "eval_samples_per_second": 30.089,
+      "eval_steps_per_second": 0.475,
+      "step": 20
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "eval_accuracy": 0.742310889443059,
+      "eval_balanced_accuracy": 0.735494880546075,
+      "eval_loss": 0.08577165752649307,
+      "eval_macro_f1": 0.7197970138129186,
+      "eval_runtime": 39.9877,
+      "eval_samples_per_second": 30.084,
+      "eval_steps_per_second": 0.475,
+      "step": 40
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.41501519083976746,
+      "learning_rate": 8.517573744099741e-05,
+      "loss": 0.26,
+      "step": 50
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "eval_accuracy": 0.9858686616791354,
+      "eval_balanced_accuracy": 0.985494880546075,
+      "eval_loss": 0.08195541054010391,
+      "eval_macro_f1": 0.9858461282921714,
+      "eval_runtime": 39.8666,
+      "eval_samples_per_second": 30.176,
+      "eval_steps_per_second": 0.477,
+      "step": 60
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "eval_accuracy": 0.9958437240232751,
+      "eval_balanced_accuracy": 0.9957337883959044,
+      "eval_loss": 0.07636160403490067,
+      "eval_macro_f1": 0.9958399986721193,
+      "eval_runtime": 39.884,
+      "eval_samples_per_second": 30.162,
+      "eval_steps_per_second": 0.476,
+      "step": 80
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.09980760514736176,
+      "learning_rate": 3.845094616073783e-05,
+      "loss": 0.0789,
+      "step": 100
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_accuracy": 0.9958437240232751,
+      "eval_balanced_accuracy": 0.9957337883959044,
+      "eval_loss": 0.07304411381483078,
+      "eval_macro_f1": 0.9958399986721193,
+      "eval_runtime": 39.9125,
+      "eval_samples_per_second": 30.141,
+      "eval_steps_per_second": 0.476,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 165,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.010343436759859e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aad672134762f08edfe26a8e5d66bb921b00624c83cbf739b5514986b03c3cb
+size 5969