Update README.md

README.md

@@ -33,7 +33,7 @@ Palmyra was primarily pretrained with English text, there is still a trace amoun
 
 ## Training data
 
-Palmyra-small 128M was trained on 
+Palmyra-small 128M was trained on Writer custom dataset
 
 ## Intended Use and Limitations
 
@@ -66,60 +66,34 @@ tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
 
 ### Limitations and Biases
 
-The core functionality of GPT-J is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. When prompting GPT-J it is important to remember that the statistically most likely next token is often not the token that produces the most "accurate" text. Never depend upon GPT-J to produce factually accurate output.
+Palmyra's core functionality is to take a string of text and predict the next token. While language models are widely used for other tasks, there are many unknowns in this work. When prompting Palmyra, keep in mind that the statistically most likely next token is not always the token that produces the most "accurate" text. Never rely on Palmyra to produce factually correct results.
 
-GPT-J was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending upon use case GPT-J may produce socially unacceptable text. See [Sections 5 and 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a more detailed analysis of the biases in the Pile.
-
-As with all language models, it is hard to predict in advance how GPT-J will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
+Palmyra was trained on Writer custom data. As with all language models, it is difficult to predict how Palmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
 
 ## Evaluation results
 
-<figure>
-
-|  Model                   | Public      | Training FLOPs | LAMBADA PPL ↓ | LAMBADA Acc ↑ | Winogrande ↑ | Hellaswag ↑ | PIQA ↑    | Dataset Size (GB) |
-|--------------------------|-------------|----------------|---            |---            |---           |---          |---        |-------------------|
-| Random Chance            | &check;     | 0              | ~a lot        | ~0%           | 50%          | 25%         | 25%       | 0                 |
-| GPT-3 Ada&ddagger;       | &cross;     | -----          | 9.95          | 51.6%         | 52.9%        | 43.4%       | 70.5%     | -----             |
-| GPT-2 1.5B               | &check;     | -----          | 10.63         | 51.21%        | 59.4%        | 50.9%       | 70.8%     | 40                |
-| GPT-Neo 1.3B&ddagger;    | &check;     | 3.0e21         | 7.50          | 57.2%         | 55.0%        | 48.9%       | 71.1%     | 825               |
-| Megatron-2.5B&ast;       | &cross;     | 2.4e21         | -----         | 61.7%         | -----        | -----       | -----     | 174               |
-| GPT-Neo 2.7B&ddagger;    | &check;     | 6.8e21         | 5.63          | 62.2%         | 56.5%        | 55.8%       | 73.0%     | 825               |
-| GPT-3 1.3B&ast;&ddagger; | &cross;     | 2.4e21         | 5.44          | 63.6%         | 58.7%        | 54.7%       | 75.1%     | ~800              |
-| GPT-3 Babbage&ddagger;   | &cross;     | -----          | 5.58          | 62.4%         | 59.0%        | 54.5%       | 75.5%     | -----             |
-| Megatron-8.3B&ast;       | &cross;     | 7.8e21         | -----         | 66.5%         | -----        | -----       | -----     | 174               |
-| GPT-3 2.7B&ast;&ddagger; | &cross;     | 4.8e21         | 4.60          | 67.1%         | 62.3%        | 62.8%       | 75.6%     | ~800              |
-| Megatron-11B&dagger;     | &check;     | 1.0e22         | -----         | -----         | -----        | -----       | -----     | 161               |
-| **GPT-J 6B&ddagger;**    | **&check;** | **1.5e22**     | **3.99**      | **69.7%**     | **65.3%**    | **66.1%**   | **76.5%** | **825**           |
-| GPT-3 6.7B&ast;&ddagger; | &cross;     | 1.2e22         | 4.00          | 70.3%         | 64.5%        | 67.4%       | 78.0%     | ~800              |
-| GPT-3 Curie&ddagger;     | &cross;     | -----          | 4.00          | 69.3%         | 65.6%        | 68.5%       | 77.9%     | -----             |
-| GPT-3 13B&ast;&ddagger;  | &cross;     | 2.3e22         | 3.56          | 72.5%         | 67.9%        | 70.9%       | 78.5%     | ~800              |
-| GPT-3 175B&ast;&ddagger; | &cross;     | 3.1e23         | 3.00          | 76.2%         | 70.2%        | 78.9%       | 81.0%     | ~800              |
-| GPT-3 Davinci&ddagger;   | &cross;     | -----          | 3.0           | 75%           | 72%          | 78%         | 80%       | -----             |
-<figcaption><p>Models roughly sorted by performance, or by FLOPs if not available.</p>
-
-<p><strong>&ast;</strong> Evaluation numbers reported by their respective authors. All other numbers are provided by
-running <a href="https://github.com/EleutherAI/lm-evaluation-harness/"><code>lm-evaluation-harness</code></a> either with released
-weights or with API access. Due to subtle implementation differences as well as different zero shot task framing, these
-might not be directly comparable. See <a href="https://blog.eleuther.ai/gpt3-model-sizes/">this blog post</a> for more
-details.</p>
-
-<p><strong>†</strong> Megatron-11B provides no comparable metrics, and several implementations using the released weights do not
-reproduce the generation quality and evaluations. (see <a href="https://github.com/huggingface/transformers/pull/10301">1</a>
-<a href="https://github.com/pytorch/fairseq/issues/2358">2</a> <a href="https://github.com/pytorch/fairseq/issues/2719">3</a>)
-Thus, evaluation was not attempted.</p>
-
-<p><strong>‡</strong> These models have been trained with data which contains possible test set contamination. The OpenAI GPT-3 models
-failed to deduplicate training data for certain test sets, while the GPT-Neo models as well as this one is
-trained on the Pile, which has not been deduplicated against any test sets.</p></figcaption></figure>
+Evaluation of Palmyra-small model on the SuperGLUE benchmark
+|------------|--------|-------|
+|   Task     | Metric | Value |
+|------------|--------|-------|
+|   boolq    |  acc   | 64.43 |
+|   cb       |  acc   | 10.71 |
+|            |  f1    | 08.32 |
+|   copa     |  acc   | 76.00 |
+|   multirc  |  acc   | 01.26 |
+|   record   |  f1    | 84.02 |
+|            |  em    | 83.29 |
+|   wic      |  acc   | 50.00 |
+|   wsc      |  acc   | 36.54 |
+
 
 ## Citation and Related Information
 
-### BibTeX entry
 
 To cite this model:
 ```bibtex
-@misc{gpt-j,
-  author = {Wang, Ben and Komatsuzaki, Aran},
+@misc{Palmyra,
+  author = {Kiran and Komatsuzaki, Aran},
   title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
   howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
   year = 2021,
@@ -127,13 +101,3 @@ To cite this model:
 }
 ```
 
-To cite the codebase that trained this model:
-```bibtex
-@misc{mesh-transformer-jax,
-  author = {Wang, Ben},
-  title = {{Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX}},
-  howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
-  year = 2021,
-  month = May
-}
-```