Add detailed evaluation README
Browse files- README.md +37 -0
- config.json +36 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
---
|
| 5 |
+
# MyAwesomeModel
|
| 6 |
+
|
| 7 |
+
**Selected checkpoint:** `checkpoints/step_1000` (highest `eval_accuracy` = 0.828).
|
| 8 |
+
**Overall weighted evaluation score:** 0.710.
|
| 9 |
+
|
| 10 |
+
## Evaluation Results
|
| 11 |
+
|
| 12 |
+
All scores below are reported to three decimal places.
|
| 13 |
+
|
| 14 |
+
| Category | Benchmark | Score |
|
| 15 |
+
|---|---|---:|
|
| 16 |
+
| Core Reasoning Tasks | Math Reasoning | 0.550 |
|
| 17 |
+
| Core Reasoning Tasks | Logical Reasoning | 0.819 |
|
| 18 |
+
| Core Reasoning Tasks | Common Sense | 0.736 |
|
| 19 |
+
| Language Understanding | Reading Comprehension | 0.700 |
|
| 20 |
+
| Language Understanding | Question Answering | 0.607 |
|
| 21 |
+
| Language Understanding | Text Classification | 0.828 |
|
| 22 |
+
| Language Understanding | Sentiment Analysis | 0.792 |
|
| 23 |
+
| Generation Tasks | Code Generation | 0.650 |
|
| 24 |
+
| Generation Tasks | Creative Writing | 0.610 |
|
| 25 |
+
| Generation Tasks | Dialogue Generation | 0.644 |
|
| 26 |
+
| Generation Tasks | Summarization | 0.767 |
|
| 27 |
+
| Specialized Capabilities | Translation | 0.804 |
|
| 28 |
+
| Specialized Capabilities | Knowledge Retrieval | 0.676 |
|
| 29 |
+
| Specialized Capabilities | Instruction Following | 0.758 |
|
| 30 |
+
| Specialized Capabilities | Safety Evaluation | 0.739 |
|
| 31 |
+
|
| 32 |
+
## Usage
|
| 33 |
+
|
| 34 |
+
```python
|
| 35 |
+
from transformers import AutoModelForSequenceClassification
|
| 36 |
+
model = AutoModelForSequenceClassification.from_pretrained("asfafaaf3434/MyAwesomeModel")
|
| 37 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negative",
|
| 16 |
+
"1": "positive"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"is_decoder": false,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negative": 0,
|
| 23 |
+
"positive": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"transformers_version": "5.12.1",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|