Samaksh Khatri
commited on
Commit
•
a6ae086
1
Parent(s):
5e358ff
Saving model gmra_model_gpt2-medium_14082023T134929
Browse files- .gitignore +1 -0
- config.json +59 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Aug14_08-19-29_2784d686bd2f/events.out.tfevents.1692001175.2784d686bd2f.444.0 +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-medium",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "change_request",
|
13 |
+
"1": "discussion_participation",
|
14 |
+
"2": "discussion_trigger",
|
15 |
+
"3": "acknowledgement",
|
16 |
+
"4": "reference",
|
17 |
+
"5": "critical"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"acknowledgement": 3,
|
22 |
+
"change_request": 0,
|
23 |
+
"critical": 5,
|
24 |
+
"discussion_participation": 1,
|
25 |
+
"discussion_trigger": 2,
|
26 |
+
"reference": 4
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-05,
|
29 |
+
"model_type": "gpt2",
|
30 |
+
"n_ctx": 1024,
|
31 |
+
"n_embd": 1024,
|
32 |
+
"n_head": 16,
|
33 |
+
"n_inner": null,
|
34 |
+
"n_layer": 24,
|
35 |
+
"n_positions": 1024,
|
36 |
+
"n_special": 0,
|
37 |
+
"pad_token_id": 15,
|
38 |
+
"predict_special_tokens": true,
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"reorder_and_upcast_attn": false,
|
41 |
+
"resid_pdrop": 0.1,
|
42 |
+
"scale_attn_by_inverse_layer_idx": false,
|
43 |
+
"scale_attn_weights": true,
|
44 |
+
"summary_activation": null,
|
45 |
+
"summary_first_dropout": 0.1,
|
46 |
+
"summary_proj_to_labels": true,
|
47 |
+
"summary_type": "cls_index",
|
48 |
+
"summary_use_proj": true,
|
49 |
+
"task_specific_params": {
|
50 |
+
"text-generation": {
|
51 |
+
"do_sample": true,
|
52 |
+
"max_length": 50
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.31.0",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 50257
|
59 |
+
}
|
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 sha256:93a5689b714658e7ea202f4814172f9d6d83f19ac47de91a5f34f3dbd9eac823
|
3 |
+
size 1419412641
|
runs/Aug14_08-19-29_2784d686bd2f/events.out.tfevents.1692001175.2784d686bd2f.444.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:796a7c2029e5042c744b331c775a9a14affc469cf616f1fea3581b3630681000
|
3 |
+
size 13904
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1487128faef4b7043bad8e53137c4f59e0e416cdbad92b5ad56cebc7bc4a3bca
|
3 |
+
size 4027
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|