KimByeongSu
commited on
Commit
•
66f3d0a
1
Parent(s):
4c084cc
Training in progress, step 500
Browse files- config.json +83 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-2.7B",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local",
|
21 |
+
"global",
|
22 |
+
"local",
|
23 |
+
"global",
|
24 |
+
"local",
|
25 |
+
"global",
|
26 |
+
"local",
|
27 |
+
"global",
|
28 |
+
"local",
|
29 |
+
"global",
|
30 |
+
"local",
|
31 |
+
"global",
|
32 |
+
"local",
|
33 |
+
"global",
|
34 |
+
"local",
|
35 |
+
"global",
|
36 |
+
"local",
|
37 |
+
"global",
|
38 |
+
"local",
|
39 |
+
"global",
|
40 |
+
"local"
|
41 |
+
],
|
42 |
+
"attention_types": [
|
43 |
+
[
|
44 |
+
[
|
45 |
+
"global",
|
46 |
+
"local"
|
47 |
+
],
|
48 |
+
16
|
49 |
+
]
|
50 |
+
],
|
51 |
+
"bos_token_id": 50256,
|
52 |
+
"classifier_dropout": 0.1,
|
53 |
+
"embed_dropout": 0,
|
54 |
+
"eos_token_id": 50256,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_size": 2560,
|
57 |
+
"initializer_range": 0.02,
|
58 |
+
"intermediate_size": null,
|
59 |
+
"layer_norm_epsilon": 1e-05,
|
60 |
+
"max_position_embeddings": 2048,
|
61 |
+
"model_type": "gpt_neo",
|
62 |
+
"num_heads": 20,
|
63 |
+
"num_layers": 32,
|
64 |
+
"resid_dropout": 0,
|
65 |
+
"summary_activation": null,
|
66 |
+
"summary_first_dropout": 0.1,
|
67 |
+
"summary_proj_to_labels": true,
|
68 |
+
"summary_type": "cls_index",
|
69 |
+
"summary_use_proj": true,
|
70 |
+
"task_specific_params": {
|
71 |
+
"text-generation": {
|
72 |
+
"do_sample": true,
|
73 |
+
"max_length": 50,
|
74 |
+
"temperature": 0.9
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"tokenizer_class": "GPT2Tokenizer",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.37.2",
|
80 |
+
"use_cache": true,
|
81 |
+
"vocab_size": 50257,
|
82 |
+
"window_size": 256
|
83 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6edaa02fa2ba4f23bdccbe82736f489c7bf74ab183e73fef99ba6466ca451d7c
|
3 |
+
size 4728
|