Training in progress, step 1600
Browse files- .gitignore +1 -0
- added_tokens.json +3 -0
- config.json +2 -2
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[ELIST]": 50257
|
3 |
+
}
|
config.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
"attn_pdrop": 0.1,
|
9 |
"bos_token_id": 50256,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
],
|
8 |
"attn_pdrop": 0.1,
|
9 |
"bos_token_id": 50256,
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c05b279927a5c425a1001b9888cc7b3d2f9f6a7966eb0db74a3277d7dbe58b1
|
3 |
+
size 333973241
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[ELIST]"
|
4 |
+
],
|
5 |
+
"bos_token": "<|endoftext|>",
|
6 |
+
"eos_token": "<|endoftext|>",
|
7 |
+
"pad_token": "<|endoftext|>",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "distilgpt2",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59c9b8f319bd05a33d3c824e4ea5ec08d7f2ca65e7908d98baddaba0dfc7948d
|
3 |
+
size 3387
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|