Upload 5 files
Browse files- config.json +31 -0
- eval_results.txt +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_fast",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": 3072,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
28 |
+
"transformers_version": "4.19.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32768
|
31 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
temperature 0.2: {'pass@1': 0.027439024390243896, 'pass@10': 0.041979293327556816, 'pass@100': 0.04268292682926801}
|
2 |
+
temperature 0.8: {'pass@1': 0.013262195121951224, 'pass@10': 0.04670902438514701, 'pass@100': 0.0899080946922357}
|
3 |
+
best: {'pass@1': 2.74% , 'pass@10': 4.67 , 'pass@100': 8.99%}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0207f6b427e3cbf1bcb9726abb6bbba6620e9912e1abf23087ccdef61818ffb2
|
3 |
+
size 247234217
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|