Keep checkpoints only + simple model card

README.md

@@ -1,20 +1,14 @@
 ---
 license: apache-2.0
 library_name: pytorch
-pipeline_tag: text-classification
 tags:
-  - materials-science
-  - solid-state-batteries
-  - post-training
   - checkpoints
+  - qlora
+  - falcon3
+  - post-training
 base_model: tiiuae/Falcon3-10B-Base
 ---
 
-# Nexa Checkpoints Post-Training Bundle
-
-This repository contains metadata for the post-training checkpoint export workflow.
+# Nexa Checkpoints
 
-## Notes
-- Source project: `Nexa_compute`
-- Owner: `Allanatrix`
-- Created: 2026-02-02
+Checkpoint artifacts exported from `nexa_inference/checkpoints`.

nexa_inference/checkpoints/falcon3_qlora_v1/README.md

@@ -0,0 +1,48 @@
+# Falcon3-10B QLoRA Fine-Tuning Checkpoint
+
+## Model Information
+- **Base Model**: tiiuae/Falcon3-10B-Base
+- **Fine-tuning Method**: QLoRA (4-bit quantization + LoRA adapters)
+- **Training Date**: November 5-6, 2025
+- **Dataset**: Scientific QA pairs (sft_scientific_v1)
+- **Total Size**: ~436MB
+
+## Training Summary
+- **Loss Improvement**: 0.8 → 0.2 (75% reduction)
+- **Final Validation Loss**: 0.410
+- **Final Test Loss**: 0.413
+- **Training Steps**: 200 (early stopping due to convergence)
+- **Trainable Parameters**: 26,214,400 (0.25% of total)
+
+## Directory Structure
+- : Saved checkpoint-200 with full trainer state
+- : Final adapter model, tokenizer, configs, and metrics
+- : Weights & Biases run logs and metadata
+- : Training and data processing logs
+- : Final evaluation metrics (validation + test)
+
+## Key Files
+- : LoRA adapter weights
+- : LoRA configuration
+- : Final evaluation metrics
+- : Full checkpoint with optimizer state
+
+## Usage
+To load this checkpoint:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    "tiiuae/Falcon3-10B-Base",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(base_model, "artifacts/")
+tokenizer = AutoTokenizer.from_pretrained("artifacts/")
+```
+
+## Evaluation Results
+- Validation Loss: 0.410
+- Test Loss: 0.413
+- Samples/sec: ~2.39

nexa_inference/checkpoints/falcon3_qlora_v1/checkpoint-200/README.md

@@ -0,0 +1,207 @@
+---
+base_model: tiiuae/Falcon3-10B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:tiiuae/Falcon3-10B-Base
+- 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 0.17.1

nexa_inference/checkpoints/falcon3_qlora_v1/checkpoint-200/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/Falcon3-10B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

nexa_inference/checkpoints/falcon3_qlora_v1/checkpoint-200/special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

nexa_inference/checkpoints/falcon3_qlora_v1/checkpoint-200/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08177868642984921,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004088934321492461,
+      "grad_norm": 0.03981570154428482,
+      "learning_rate": 0.00011693877551020409,
+      "loss": 0.8532,
+      "step": 10
+    },
+    {
+      "epoch": 0.008177868642984922,
+      "grad_norm": 0.05976454168558121,
+      "learning_rate": 0.00011081632653061225,
+      "loss": 0.8066,
+      "step": 20
+    },
+    {
+      "epoch": 0.012266802964477384,
+      "grad_norm": 0.04222235828638077,
+      "learning_rate": 0.00010469387755102041,
+      "loss": 0.7199,
+      "step": 30
+    },
+    {
+      "epoch": 0.016355737285969844,
+      "grad_norm": 0.03708258271217346,
+      "learning_rate": 9.857142857142856e-05,
+      "loss": 0.68,
+      "step": 40
+    },
+    {
+      "epoch": 0.020444671607462304,
+      "grad_norm": 0.041671689599752426,
+      "learning_rate": 9.244897959183674e-05,
+      "loss": 0.6437,
+      "step": 50
+    },
+    {
+      "epoch": 0.024533605928954767,
+      "grad_norm": 0.04101754352450371,
+      "learning_rate": 8.63265306122449e-05,
+      "loss": 0.594,
+      "step": 60
+    },
+    {
+      "epoch": 0.028622540250447227,
+      "grad_norm": 0.04235270246863365,
+      "learning_rate": 8.020408163265306e-05,
+      "loss": 0.5803,
+      "step": 70
+    },
+    {
+      "epoch": 0.03271147457193969,
+      "grad_norm": 0.04695265367627144,
+      "learning_rate": 7.408163265306122e-05,
+      "loss": 0.539,
+      "step": 80
+    },
+    {
+      "epoch": 0.03680040889343215,
+      "grad_norm": 0.06645287573337555,
+      "learning_rate": 6.79591836734694e-05,
+      "loss": 0.5297,
+      "step": 90
+    },
+    {
+      "epoch": 0.04088934321492461,
+      "grad_norm": 0.0795179009437561,
+      "learning_rate": 6.183673469387755e-05,
+      "loss": 0.4886,
+      "step": 100
+    },
+    {
+      "epoch": 0.044978277536417074,
+      "grad_norm": 0.09964903444051743,
+      "learning_rate": 5.5714285714285715e-05,
+      "loss": 0.4841,
+      "step": 110
+    },
+    {
+      "epoch": 0.049067211857909535,
+      "grad_norm": 0.08603360503911972,
+      "learning_rate": 4.959183673469388e-05,
+      "loss": 0.4673,
+      "step": 120
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 0.0638309195637703,
+      "learning_rate": 4.346938775510204e-05,
+      "loss": 0.4392,
+      "step": 130
+    },
+    {
+      "epoch": 0.057245080500894455,
+      "grad_norm": 0.062022604048252106,
+      "learning_rate": 3.734693877551021e-05,
+      "loss": 0.4383,
+      "step": 140
+    },
+    {
+      "epoch": 0.061334014822386915,
+      "grad_norm": 0.08857443183660507,
+      "learning_rate": 3.122448979591837e-05,
+      "loss": 0.4348,
+      "step": 150
+    },
+    {
+      "epoch": 0.06542294914387937,
+      "grad_norm": 0.07222077250480652,
+      "learning_rate": 2.5102040816326533e-05,
+      "loss": 0.4252,
+      "step": 160
+    },
+    {
+      "epoch": 0.06951188346537183,
+      "grad_norm": 0.07325974106788635,
+      "learning_rate": 1.8979591836734696e-05,
+      "loss": 0.4094,
+      "step": 170
+    },
+    {
+      "epoch": 0.0736008177868643,
+      "grad_norm": 0.07118217647075653,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.4126,
+      "step": 180
+    },
+    {
+      "epoch": 0.07768975210835675,
+      "grad_norm": 0.06610973179340363,
+      "learning_rate": 6.734693877551021e-06,
+      "loss": 0.4011,
+      "step": 190
+    },
+    {
+      "epoch": 0.08177868642984921,
+      "grad_norm": 0.05844658240675926,
+      "learning_rate": 6.122448979591837e-07,
+      "loss": 0.4101,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "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": 3.904326196002816e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}