End of training
Browse files- .gitignore +1 -0
- config.json +51 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/Feb25_13-05-07_7755d8d5a95f/1677330336.619338/events.out.tfevents.1677330336.7755d8d5a95f.1805.1 +3 -0
- runs/Feb25_13-05-07_7755d8d5a95f/events.out.tfevents.1677330336.7755d8d5a95f.1805.0 +3 -0
- runs/Feb25_13-05-07_7755d8d5a95f/events.out.tfevents.1677332828.7755d8d5a95f.1805.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "skt/kogpt2-base-v2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"created_date": "2021-04-28",
|
12 |
+
"embd_pdrop": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0
|
21 |
+
},
|
22 |
+
"layer_norm_epsilon": 1e-05,
|
23 |
+
"license": "CC-BY-NC-SA 4.0",
|
24 |
+
"model_type": "gpt2",
|
25 |
+
"n_ctx": 1024,
|
26 |
+
"n_embd": 768,
|
27 |
+
"n_head": 12,
|
28 |
+
"n_inner": null,
|
29 |
+
"n_layer": 12,
|
30 |
+
"n_positions": 1024,
|
31 |
+
"pad_token_id": 3,
|
32 |
+
"reorder_and_upcast_attn": false,
|
33 |
+
"resid_pdrop": 0.1,
|
34 |
+
"scale_attn_by_inverse_layer_idx": false,
|
35 |
+
"scale_attn_weights": true,
|
36 |
+
"summary_activation": null,
|
37 |
+
"summary_first_dropout": 0.1,
|
38 |
+
"summary_proj_to_labels": true,
|
39 |
+
"summary_type": "cls_index",
|
40 |
+
"summary_use_proj": true,
|
41 |
+
"task_specific_params": {
|
42 |
+
"text-generation": {
|
43 |
+
"do_sample": true,
|
44 |
+
"max_length": 50
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.26.1",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 51200
|
51 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e7d87417a44b138786faff1e6747ae8d1e1c7c9ee3e3f8e13cf54723f35728f
|
3 |
+
size 513294909
|
runs/Feb25_13-05-07_7755d8d5a95f/1677330336.619338/events.out.tfevents.1677330336.7755d8d5a95f.1805.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5699b053e4cedc34a6897599d74bbb8557f3a25d2bb9184f71cabe5e7e363861
|
3 |
+
size 5685
|
runs/Feb25_13-05-07_7755d8d5a95f/events.out.tfevents.1677330336.7755d8d5a95f.1805.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6729f43287688d3dbe64a895674e0ebe4301c7cd97f013d2670817407872bd8e
|
3 |
+
size 7867
|
runs/Feb25_13-05-07_7755d8d5a95f/events.out.tfevents.1677332828.7755d8d5a95f.1805.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4fee48d17997596150bcfca83f773143742978f61c57d5b6923663fd489728d
|
3 |
+
size 311
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a3257068dc3b68ef9cdf145bdc47397c1b4d4b4d823fb5c6bdb98a5e5ce58cf
|
3 |
+
size 3515
|