Training in progress, step 2000
Browse files- added_tokens.json +0 -0
- config.json +2 -2
- merges.txt +0 -0
- model.safetensors +2 -2
- runs/Aug11_01-44-41_d05ac286fe9b/events.out.tfevents.1723340682.d05ac286fe9b.3147.0 +3 -0
- special_tokens_map.json +23 -0
- tokenizer_config.json +0 -0
- training_args.bin +2 -2
- vocab.json +0 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/content/drive/MyDrive/Study/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -35,5 +35,5 @@
|
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.42.4",
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/Study/rus_gpt2_friday",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.42.4",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 54848
|
| 39 |
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
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:cacedc15131156b943e28e0ef96345179e373e4e487ec2967657a058416a0f3a
|
| 3 |
+
size 511877760
|
runs/Aug11_01-44-41_d05ac286fe9b/events.out.tfevents.1723340682.d05ac286fe9b.3147.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc21994fe179174209640c47d4430480bba1f9482ffda7a05bd3f9b69f4a20e3
|
| 3 |
+
size 5714
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.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 sha256:5de4233392d26cf2e1a7c3a68c04868de9634493b0447317dad612c31817169a
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|