samaksh-khatri commited on
Commit
503b110
1 Parent(s): cabe82d

Saving model gmra_model_gpt2_14082023T103028

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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": 768,
32
+ "n_head": 12,
33
+ "n_inner": null,
34
+ "n_layer": 12,
35
+ "n_positions": 1024,
36
+ "pad_token_id": 15,
37
+ "problem_type": "single_label_classification",
38
+ "reorder_and_upcast_attn": false,
39
+ "resid_pdrop": 0.1,
40
+ "scale_attn_by_inverse_layer_idx": false,
41
+ "scale_attn_weights": true,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "task_specific_params": {
48
+ "text-generation": {
49
+ "do_sample": true,
50
+ "max_length": 50
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.31.0",
55
+ "use_cache": true,
56
+ "vocab_size": 50257
57
+ }
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:e4137bba8e1c25871fddb31b4ae878bbc7226d6b744e1d4f93edc378da7a4691
3
+ size 497825889
runs/Aug14_05-00-28_863661a6503d/events.out.tfevents.1691989234.863661a6503d.240.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a4dceb1a6654af5c2c1cd935e373048a54039c6cee8537a6ee95f77415e3d6
3
+ size 8445
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 sha256:2c36e13c38e6311c01047529b1d5fba93fd728e5551f945ba34d7009d8c3b358
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff