Add SetFit model

README.md

@@ -10,14 +10,17 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.
-- text: PRNG seed key Pre-loaded during the manufacturing process, compiled in the
-    binary.
+- text: Approved PRNG initial seeds and seed keys used for initialization are securely
+    stored in flash memory.
 - text: ANSI X9.31 PRNG key Triple DES key Generated internally by non-approved RNG
     Volatile memory only (plaintext) Zeroized when the module reboots.
-- text: All CSPs are injected during manufacture.
-- text: The internal DRBG state value of the RNG is stored in NVRAM for persistent
-    use.
+- text: PRNG ANSI X9.31 Key K1, K2 Internal 3DES Key Automatically Generated per seeding
+    This is an internal key used for ANSI X9.31 192 bits Internal Key generate from
+    the seed and seed key
+- text: PRNG Seed Key A new ANSI X9.31 RNG Seed Key is generated from a block of 160
+    bits output by the random noise source software library.
+- text: FIPS-Approved random number generation ANSI X9.31 PRNG Key AES 128-bit key
+    Hard-coded in the module.
 inference: true
 ---
 
@@ -49,10 +52,10 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label    | Examples                                                                                                                                                                                                                                                                                                                                                                                                                          |
-|:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| negative | <ul><li>'PRNG ANSI X9.31 Key K1, K2 Internal 3DES Key Automatically Generated per seeding This is an internal key used for ANSI X9.31 192 bits Internal Key generate from the seed and seed key'</li><li>'ANSI X9.31 PRNG key AES-128 Generated internally by the Kernel.'</li><li>'The seed key is used as an input to the X9.31 RNG, a deterministic random number generator, and is generally not stored long term.'</li></ul> |
-| positive | <ul><li>'The ANSI X9.31 RNG is seeded using a 128-bit AES seed key generated external to the module.'</li><li>'An AES-256 seed key generated during manufacturing is used to initialize the RNG in the encryption algorithm.'</li><li>'PRNG seed key is static during the lifetime of the module.'</li></ul>                                                                                                                      |
+| Label    | Examples                                                                                                                                                                                                                                                                                                                                                  |
+|:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| negative | <ul><li>'X Seed Key for RNG: Seed created by NDRNG and used as the Triple DES key in the ANSI X9.31 RNG.'</li><li>'The ANSI X9.31 Seed key is held in volatile system memory and destroyed on power cycle.'</li><li>'ANSI X9.31 PRNG key AES-128 Generated internally by the Kernel.'</li></ul>                                                           |
+| positive | <ul><li>'The private key component of an ANSI X9.31-compliant PRNG is stored securely in NVRAM.'</li><li>'Secure storage of the RNG seed key in tamper-resistant hardware ensures reliable random number generation.'</li><li>'A FIPS-approved RNG utilizes an ANSI X9.31 PRNG key with an AES 128-bit key that is hard-coded into the module.'</li></ul> |
 
 ## Uses
 
@@ -72,7 +75,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("yasirdemircan/setfit_rng_v5")
 # Run inference
-preds = model("All CSPs are injected during manufacture.")
+preds = model("FIPS-Approved random number generation ANSI X9.31 PRNG Key AES 128-bit key Hard-coded in the module.")
 ```
 
 <!--
@@ -104,12 +107,12 @@ preds = model("All CSPs are injected during manufacture.")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 6   | 20.8222 | 59  |
+| Word count   | 6   | 19.1778 | 53  |
 
 | Label    | Training Sample Count |
 |:---------|:----------------------|
-| negative | 21                    |
-| positive | 24                    |
+| negative | 22                    |
+| positive | 23                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
@@ -132,13 +135,13 @@ preds = model("All CSPs are injected during manufacture.")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0294 | 1    | 0.2472        | -               |
-| 1.0    | 34   | -             | 0.2296          |
-| 1.4706 | 50   | 0.0969        | -               |
-| 2.0    | 68   | -             | 0.3144          |
+| 0.0294 | 1    | 0.2337        | -               |
+| 1.0    | 34   | -             | 0.1687          |
+| 1.4706 | 50   | 0.1015        | -               |
+| 2.0    | 68   | -             | 0.1004          |
 | 2.9412 | 100  | 0.0006        | -               |
-| 3.0    | 102  | -             | 0.3090          |
-| 4.0    | 136  | -             | 0.3083          |
+| 3.0    | 102  | -             | 0.1020          |
+| 4.0    | 136  | -             | 0.1021          |
 
 ### Framework Versions
 - Python: 3.10.15

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba1a3febe1d337cb9daa6b774111b0bdfb5c64ff158bee9a9a1d05cd2cdf5ed
+oid sha256:20188c8a8e6449a67f433e5291757c320ce4f7f783a7e85ebb6906c4b75a00e7
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c7aa63a7a0904f0ca3803bd3508b835b6af58f19c5937cf14934400f78b83d
+oid sha256:faad5660c72ed5eafb75c45dc67f3478f451053598a3bc652fa8234216652eb7
 size 7055