Update README.md
Browse files
README.md
CHANGED
|
@@ -1,19 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: pszemraj/mega-ar-350m-v0.12-napierone_epub
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
-
|
| 9 |
-
-
|
| 10 |
-
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
# mega-ar-350m-v0.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [pszemraj/mega-ar-350m-v0.12-napierone_epub](https://huggingface.co/pszemraj/mega-ar-350m-v0.12-napierone_epub) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
|
@@ -21,17 +19,27 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
- Accuracy: 0.5885
|
| 22 |
- Num Input Tokens Seen: 3468165120
|
| 23 |
|
| 24 |
-
## Model description
|
| 25 |
|
| 26 |
-
|
|
|
|
|
|
|
| 27 |
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
-
More information needed
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
@@ -85,4 +93,4 @@ The following hyperparameters were used during training:
|
|
| 85 |
- Transformers 4.40.2
|
| 86 |
- Pytorch 2.2.0+cu121
|
| 87 |
- Datasets 2.19.1
|
| 88 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
+
language:
|
| 8 |
+
- en
|
|
|
|
| 9 |
---
|
| 10 |
|
|
|
|
|
|
|
| 11 |
|
| 12 |
+
# mega-ar-350m-v0.13
|
| 13 |
+
|
| 14 |
+
## Model description
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [pszemraj/mega-ar-350m-v0.12-napierone_epub](https://huggingface.co/pszemraj/mega-ar-350m-v0.12-napierone_epub) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
|
|
|
| 19 |
- Accuracy: 0.5885
|
| 20 |
- Num Input Tokens Seen: 3468165120
|
| 21 |
|
|
|
|
| 22 |
|
| 23 |
+
## Quick eval
|
| 24 |
+
|
| 25 |
+
Quick eval for: pszemraj/mega-ar-350m-v0.13
|
| 26 |
|
|
|
|
| 27 |
|
| 28 |
+
hf (pretrained=pszemraj/mega-ar-350m-v0.13,trust_remote_code=True,dtype=float), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: 8
|
| 29 |
|
| 30 |
+
| Tasks |Version|Filter|n-shot| Metric | Value | |Stderr|
|
| 31 |
+
|--------------|------:|------|-----:|----------|------:|---|-----:|
|
| 32 |
+
|arc_easy | 1|none | 0|acc | 0.4491|± |0.0102|
|
| 33 |
+
| | |none | 0|acc_norm | 0.4061|± |0.0101|
|
| 34 |
+
|boolq | 2|none | 0|acc | 0.5367|± |0.0087|
|
| 35 |
+
|lambada_openai| 1|none | 0|perplexity|55.3308|± |2.3100|
|
| 36 |
+
| | |none | 0|acc | 0.3113|± |0.0065|
|
| 37 |
+
|openbookqa | 1|none | 0|acc | 0.1760|± |0.0170|
|
| 38 |
+
| | |none | 0|acc_norm | 0.2680|± |0.0198|
|
| 39 |
+
|piqa | 1|none | 0|acc | 0.6366|± |0.0112|
|
| 40 |
+
| | |none | 0|acc_norm | 0.6213|± |0.0113|
|
| 41 |
+
|winogrande | 1|none | 0|acc | 0.5036|± |0.0141|
|
| 42 |
|
|
|
|
| 43 |
|
| 44 |
## Training procedure
|
| 45 |
|
|
|
|
| 93 |
- Transformers 4.40.2
|
| 94 |
- Pytorch 2.2.0+cu121
|
| 95 |
- Datasets 2.19.1
|
| 96 |
+
- Tokenizers 0.19.1
|