Update README.md
Browse files
README.md
CHANGED
|
@@ -56,7 +56,10 @@ datasets:
|
|
| 56 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 57 |
should probably proofread and complete it, then remove this comment. -->
|
| 58 |
|
| 59 |
-
# mega-ar-350m-L3t-v0.
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
This model is a fine-tuned version of [pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py](https://hf.co/pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
|
| 62 |
It achieves the following results on the evaluation set:
|
|
@@ -64,17 +67,27 @@ It achieves the following results on the evaluation set:
|
|
| 64 |
- Accuracy: 0.5746
|
| 65 |
- Num Input Tokens Seen: 3492282368
|
| 66 |
|
| 67 |
-
## Model description
|
| 68 |
|
| 69 |
-
|
| 70 |
|
| 71 |
-
|
| 72 |
|
| 73 |
-
More information needed
|
| 74 |
|
| 75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
|
| 77 |
-
More information needed
|
| 78 |
|
| 79 |
## Training procedure
|
| 80 |
|
|
|
|
| 56 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 57 |
should probably proofread and complete it, then remove this comment. -->
|
| 58 |
|
| 59 |
+
# mega-ar-350m-L3t-v0.08-ultraTBfw
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
## Model description
|
| 63 |
|
| 64 |
This model is a fine-tuned version of [pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py](https://hf.co/pszemraj/mega-ar-350m-L3t-v0.07-cosmo_webmath_py) on the BEE-spoke-data/UltraTextbooks-2.1-fw_mix dataset.
|
| 65 |
It achieves the following results on the evaluation set:
|
|
|
|
| 67 |
- Accuracy: 0.5746
|
| 68 |
- Num Input Tokens Seen: 3492282368
|
| 69 |
|
|
|
|
| 70 |
|
| 71 |
+
## Quick eval
|
| 72 |
|
| 73 |
+
Quick eval for: pszemraj/mega-ar-350m-L3t-v0.08-ultraTBfw
|
| 74 |
|
|
|
|
| 75 |
|
| 76 |
+
bootstrapping for stddev: perplexity
|
| 77 |
+
hf (pretrained=pszemraj/mega-ar-350m-L3t-v0.08-ultraTBfw,trust_remote_code=True,dtype=float), gen_kwargs: (None), limit: 0.99999, num_fewshot: None, batch_size: 8
|
| 78 |
+
| Tasks |Version|Filter|n-shot| Metric | Value | |Stderr|
|
| 79 |
+
|--------------|------:|------|-----:|----------|------:|---|-----:|
|
| 80 |
+
|arc_easy | 1|none | 0|acc | 0.4246|± |0.0139|
|
| 81 |
+
| | |none | 0|acc_norm | 0.4002|± |0.0138|
|
| 82 |
+
|boolq | 2|none | 0|acc | 0.5762|± |0.0139|
|
| 83 |
+
|lambada_openai| 1|none | 0|perplexity|76.7162|± |6.3531|
|
| 84 |
+
| | |none | 0|acc | 0.2605|± |0.0123|
|
| 85 |
+
|openbookqa | 1|none | 0|acc | 0.1840|± |0.0173|
|
| 86 |
+
| | |none | 0|acc_norm | 0.2720|± |0.0199|
|
| 87 |
+
|piqa | 1|none | 0|acc | 0.6377|± |0.0135|
|
| 88 |
+
| | |none | 0|acc_norm | 0.6172|± |0.0137|
|
| 89 |
+
|winogrande | 1|none | 0|acc | 0.5020|± |0.0141|
|
| 90 |
|
|
|
|
| 91 |
|
| 92 |
## Training procedure
|
| 93 |
|