Update README.md

README.md

@@ -7,42 +7,39 @@ tags:
 metrics:
 - accuracy
 model-index:
-- name: ModernBERT-base-zeroshot-v2.0-2024-12-28-09-01
+- name: ModernBERT-base-zeroshot-v2.0
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
-# ModernBERT-base-zeroshot-v2.0-2024-12-28-09-01
-
-This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1856
-- F1 Macro: 0.6373
-- F1 Micro: 0.7076
-- Accuracy Balanced: 0.6761
-- Accuracy: 0.7076
-- Precision Macro: 0.6700
-- Recall Macro: 0.6761
-- Precision Micro: 0.7076
-- Recall Micro: 0.7076
+# ModernBERT-base-zeroshot-v2.0
 
 ## Model description
 
-More information needed
+This model is [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) 
+fine-tuned on the same dataset mix as the `zeroshot-v2.0` models in the [Zeroshot Classifiers Collection](https://huggingface.co/collections/MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f).
+
 
-## Intended uses & limitations
+## General takeaways: 
+- The model is very fast and memory efficient. It's multiple times faster and consumes multiple times less memory than DeBERTav3.
+The memory efficiency enables larger batch sizes. I got a ~2x speed increase by enabling bf16 (instead of fp16).
+- It performs slightly worse then DeBERTav3 on average on the tasks tested below.
+- I'm in the process of preparing a newer version trained on better synthetic data to make full use of the 8k context window
+and to update the training mix of the older `zeroshot-v2.0` models.
 
-More information needed
 
-## Training and evaluation data
+## Training results
 
-More information needed
+Per-dataset breakdown:
+
+|Datasets|Mean|Mean w/o NLI|mnli_m|mnli_mm|fevernli|anli_r1|anli_r2|anli_r3|wanli|lingnli|wellformedquery|rottentomatoes|amazonpolarity|imdb|yelpreviews|hatexplain|massive|banking77|emotiondair|emocontext|empathetic|agnews|yahootopics|biasframes_sex|biasframes_offensive|biasframes_intent|financialphrasebank|appreviews|hateoffensive|trueteacher|spam|wikitoxic_toxicaggregated|wikitoxic_obscene|wikitoxic_identityhate|wikitoxic_threat|wikitoxic_insult|manifesto|capsotu|
+| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+|Accuracy|0.831|0.835|0.932|0.936|0.884|0.763|0.647|0.657|0.823|0.889|0.753|0.864|0.949|0.935|0.974|0.798|0.788|0.727|0.789|0.793|0.489|0.893|0.717|0.927|0.851|0.859|0.907|0.952|0.926|0.726|0.978|0.912|0.914|0.93|0.951|0.906|0.476|0.708|
+|F1 macro|0.813|0.818|0.925|0.93|0.872|0.74|0.61|0.611|0.81|0.874|0.751|0.864|0.949|0.935|0.974|0.751|0.738|0.746|0.733|0.798|0.475|0.893|0.712|0.919|0.851|0.859|0.892|0.952|0.847|0.721|0.966|0.912|0.914|0.93|0.942|0.906|0.329|0.637|
+|Inference text/sec (A100 40GB GPU, batch=128)|3472.0|3474.0|2338.0|4416.0|2993.0|2959.0|2904.0|3003.0|4647.0|4486.0|5032.0|4354.0|2466.0|1140.0|1582.0|4392.0|5446.0|5296.0|4904.0|4787.0|2251.0|4042.0|1884.0|4048.0|4032.0|4121.0|4275.0|3746.0|4485.0|1114.0|4322.0|2260.0|2274.0|2189.0|2085.0|2410.0|3933.0|4388.0|
 
-## Training procedure
 
-### Training hyperparameters
+## Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
@@ -54,25 +51,8 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.06
 - num_epochs: 2
 
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
-| 0.2321        | 1.0   | 33915 | 0.3726          | 0.8316   | 0.8458   | 0.8332            | 0.8458   | 0.8301          | 0.8332       | 0.8458          | 0.8458       |
-| 0.1305        | 2.0   | 67830 | 0.4350          | 0.8396   | 0.8541   | 0.8389            | 0.8541   | 0.8403          | 0.8389       | 0.8541          | 0.8541       |
-
-
-Per-dataset breakdown:
-
-|Datasets|Mean|Mean w/o NLI|mnli_m|mnli_mm|fevernli|anli_r1|anli_r2|anli_r3|wanli|lingnli|wellformedquery|rottentomatoes|amazonpolarity|imdb|yelpreviews|hatexplain|massive|banking77|emotiondair|emocontext|empathetic|agnews|yahootopics|biasframes_sex|biasframes_offensive|biasframes_intent|financialphrasebank|appreviews|hateoffensive|trueteacher|spam|wikitoxic_toxicaggregated|wikitoxic_obscene|wikitoxic_identityhate|wikitoxic_threat|wikitoxic_insult|manifesto|capsotu|
-| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
-|Accuracy|0.831|0.835|0.932|0.936|0.884|0.763|0.647|0.657|0.823|0.889|0.753|0.864|0.949|0.935|0.974|0.798|0.788|0.727|0.789|0.793|0.489|0.893|0.717|0.927|0.851|0.859|0.907|0.952|0.926|0.726|0.978|0.912|0.914|0.93|0.951|0.906|0.476|0.708|
-|F1 macro|0.813|0.818|0.925|0.93|0.872|0.74|0.61|0.611|0.81|0.874|0.751|0.864|0.949|0.935|0.974|0.751|0.738|0.746|0.733|0.798|0.475|0.893|0.712|0.919|0.851|0.859|0.892|0.952|0.847|0.721|0.966|0.912|0.914|0.93|0.942|0.906|0.329|0.637|
-|Inference text/sec (GPU, batch=128)|3472.0|3474.0|2338.0|4416.0|2993.0|2959.0|2904.0|3003.0|4647.0|4486.0|5032.0|4354.0|2466.0|1140.0|1582.0|4392.0|5446.0|5296.0|4904.0|4787.0|2251.0|4042.0|1884.0|4048.0|4032.0|4121.0|4275.0|3746.0|4485.0|1114.0|4322.0|2260.0|2274.0|2189.0|2085.0|2410.0|3933.0|4388.0|
-
-
 
-### Framework versions
+## Framework versions
 
 - Transformers 4.48.0.dev0
 - Pytorch 2.5.1+cu124