Training in progress, epoch 1
Browse files- config.json +24 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +4 -0
- tokenizer_config.json +6 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"afn": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"OpenAIGPTLMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"embd_pdrop": 0.1,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"layer_norm_epsilon": 1e-05,
|
10 |
+
"model_type": "openai-gpt",
|
11 |
+
"n_embd": 512,
|
12 |
+
"n_head": 4,
|
13 |
+
"n_layer": 4,
|
14 |
+
"n_positions": 531,
|
15 |
+
"resid_pdrop": 0.1,
|
16 |
+
"summary_activation": null,
|
17 |
+
"summary_first_dropout": 0.1,
|
18 |
+
"summary_proj_to_labels": true,
|
19 |
+
"summary_type": "cls_index",
|
20 |
+
"summary_use_proj": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.0",
|
23 |
+
"vocab_size": 40478
|
24 |
+
}
|
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 sha256:688d8ac2c3e3dd30e40c46c9941cab691f267ac1ad62c2644f06ed3d03d852ee
|
3 |
+
size 134440647
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<PAD>",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3177855b1c17e2988fe036ad704546e821d56223585178841806ab91c7ee91f0
|
3 |
+
size 4027
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|