Update README.md

README.md

@@ -7,40 +7,34 @@ tags:
 metrics:
 - accuracy
 model-index:
-- name: ModernBERT-large-zeroshot-v2.0-2024-12-28-00-13
+- name: ModernBERT-large-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-large-zeroshot-v2.0-2024-12-28-00-13
-
-This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1803
-- F1 Macro: 0.6624
-- F1 Micro: 0.7304
-- Accuracy Balanced: 0.6979
-- Accuracy: 0.7304
-- Precision Macro: 0.6899
-- Recall Macro: 0.6979
-- Precision Micro: 0.7304
-- Recall Micro: 0.7304
+# ModernBERT-base-zeroshot-v2.0
 
 ## Model description
 
-More information needed
+This model is [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) 
+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
 
-More information needed
+## 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.
 
-## Training and evaluation data
 
-More information needed
+### Training results
+
+|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|0.85|0.851|0.942|0.944|0.894|0.812|0.717|0.716|0.836|0.909|0.815|0.899|0.964|0.951|0.984|0.814|0.8|0.744|0.752|0.802|0.544|0.899|0.735|0.934|0.864|0.877|0.913|0.953|0.921|0.821|0.989|0.901|0.927|0.931|0.959|0.911|0.497|0.73|
+|F1 macro|0.834|0.835|0.935|0.938|0.882|0.795|0.688|0.676|0.823|0.898|0.814|0.899|0.964|0.951|0.984|0.77|0.753|0.763|0.69|0.805|0.533|0.899|0.729|0.925|0.864|0.877|0.901|0.953|0.855|0.821|0.983|0.901|0.927|0.931|0.952|0.911|0.362|0.662|
+|Inference text/sec (A100 40GB GPU, batch=32)|1116.0|1104.0|1039.0|1241.0|1138.0|1102.0|1124.0|1133.0|1251.0|1240.0|1263.0|1231.0|1054.0|559.0|795.0|1238.0|1312.0|1285.0|1273.0|1268.0|992.0|1222.0|894.0|1176.0|1194.0|1197.0|1206.0|1166.0|1227.0|541.0|1199.0|1045.0|1054.0|1020.0|1005.0|1063.0|1214.0|1220.0|
 
-## Training procedure
 
 ### Training hyperparameters
 
@@ -56,23 +50,6 @@ 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 |
-|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
-| 0.3865        | 1.0    | 33915 | 0.3321          | 0.8584   | 0.8704   | 0.8600            | 0.8704   | 0.8569          | 0.8600       | 0.8704          | 0.8704       |
-| 0.2456        | 2.0000 | 67828 | 0.4069          | 0.8600   | 0.8728   | 0.8590            | 0.8728   | 0.8610          | 0.8590       | 0.8728          | 0.8728       |
-
-
-Breakdown by dataset
-
-|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|0.85|0.851|0.942|0.944|0.894|0.812|0.717|0.716|0.836|0.909|0.815|0.899|0.964|0.951|0.984|0.814|0.8|0.744|0.752|0.802|0.544|0.899|0.735|0.934|0.864|0.877|0.913|0.953|0.921|0.821|0.989|0.901|0.927|0.931|0.959|0.911|0.497|0.73|
-|F1 macro|0.834|0.835|0.935|0.938|0.882|0.795|0.688|0.676|0.823|0.898|0.814|0.899|0.964|0.951|0.984|0.77|0.753|0.763|0.69|0.805|0.533|0.899|0.729|0.925|0.864|0.877|0.901|0.953|0.855|0.821|0.983|0.901|0.927|0.931|0.952|0.911|0.362|0.662|
-|Inference text/sec (GPU, batch=32)|1116.0|1104.0|1039.0|1241.0|1138.0|1102.0|1124.0|1133.0|1251.0|1240.0|1263.0|1231.0|1054.0|559.0|795.0|1238.0|1312.0|1285.0|1273.0|1268.0|992.0|1222.0|894.0|1176.0|1194.0|1197.0|1206.0|1166.0|1227.0|541.0|1199.0|1045.0|1054.0|1020.0|1005.0|1063.0|1214.0|1220.0|
-
-
 
 ### Framework versions