Upload 2 files
Browse files
base-2.8b-eval-files/EleutherAI-pythia-2.8b-0shot-shelloutput.txt
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrapping for stddev: perplexity
|
| 2 |
+
hf (pretrained=EleutherAI/pythia-2.8b), limit: None, num_fewshot: 0, batch_size: 16
|
| 3 |
+
| Task |Version|Filter| Metric | Value | |Stderr|
|
| 4 |
+
|--------------|-------|------|---------------|------:|---|-----:|
|
| 5 |
+
|arc_challenge |Yaml |none |acc | 0.2952|± |0.0133|
|
| 6 |
+
| | |none |acc_norm | 0.3311|± |0.0138|
|
| 7 |
+
|arc_easy |Yaml |none |acc | 0.6448|± |0.0098|
|
| 8 |
+
| | |none |acc_norm | 0.5871|± |0.0101|
|
| 9 |
+
|boolq |Yaml |none |acc | 0.6474|± |0.0084|
|
| 10 |
+
|hellaswag |Yaml |none |acc | 0.4532|± |0.0050|
|
| 11 |
+
| | |none |acc_norm | 0.5926|± |0.0049|
|
| 12 |
+
|lambada_openai|Yaml |none |perplexity | 5.0370|± |0.1191|
|
| 13 |
+
| | |none |acc | 0.6472|± |0.0067|
|
| 14 |
+
|openbookqa |Yaml |none |acc | 0.2400|± |0.0191|
|
| 15 |
+
| | |none |acc_norm | 0.3580|± |0.0215|
|
| 16 |
+
|piqa |Yaml |none |acc | 0.7394|± |0.0102|
|
| 17 |
+
| | |none |acc_norm | 0.7356|± |0.0103|
|
| 18 |
+
|sciq |Yaml |none |acc | 0.8870|± |0.0100|
|
| 19 |
+
| | |none |acc_norm | 0.8350|± |0.0117|
|
| 20 |
+
|wikitext |Yaml |none |word_perplexity|20.0571| | |
|
| 21 |
+
| | |none |byte_perplexity| 1.6394| | |
|
| 22 |
+
| | |none |bits_per_byte | 0.7132| | |
|
| 23 |
+
|winogrande |Yaml |none |acc | 0.5975|± |0.0138|
|
| 24 |
+
|
base-2.8b-eval-files/EleutherAI-pythia-2.8b-5shot-shelloutput.txt
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrapping for stddev: perplexity
|
| 2 |
+
hf (pretrained=EleutherAI/pythia-2.8b), limit: None, num_fewshot: 5, batch_size: 8
|
| 3 |
+
| Task |Version|Filter| Metric | Value | |Stderr|
|
| 4 |
+
|--------------|-------|------|---------------|------:|---|-----:|
|
| 5 |
+
|arc_challenge |Yaml |none |acc | 0.3123|± |0.0135|
|
| 6 |
+
| | |none |acc_norm | 0.3549|± |0.0140|
|
| 7 |
+
|arc_easy |Yaml |none |acc | 0.6700|± |0.0096|
|
| 8 |
+
| | |none |acc_norm | 0.6759|± |0.0096|
|
| 9 |
+
|boolq |Yaml |none |acc | 0.6664|± |0.0082|
|
| 10 |
+
|hellaswag |Yaml |none |acc | 0.4504|± |0.0050|
|
| 11 |
+
| | |none |acc_norm | 0.6031|± |0.0049|
|
| 12 |
+
|lambada_openai|Yaml |none |perplexity | 6.4479|± |0.1602|
|
| 13 |
+
| | |none |acc | 0.5948|± |0.0068|
|
| 14 |
+
|openbookqa |Yaml |none |acc | 0.2480|± |0.0193|
|
| 15 |
+
| | |none |acc_norm | 0.3720|± |0.0216|
|
| 16 |
+
|piqa |Yaml |none |acc | 0.7427|± |0.0102|
|
| 17 |
+
| | |none |acc_norm | 0.7443|± |0.0102|
|
| 18 |
+
|sciq |Yaml |none |acc | 0.9440|± |0.0073|
|
| 19 |
+
| | |none |acc_norm | 0.9400|± |0.0075|
|
| 20 |
+
|wikitext |Yaml |none |word_perplexity|20.0571| | |
|
| 21 |
+
| | |none |byte_perplexity| 1.6394| | |
|
| 22 |
+
| | |none |bits_per_byte | 0.7132| | |
|
| 23 |
+
|winogrande |Yaml |none |acc | 0.5943|± |0.0138|
|
| 24 |
+
|