update to /home/yuchenl/models/reverse-instruct/prefixgen_v2_flan-small/checkpoint-10500
Browse files- config.json +2 -1
- generation_config.json +1 -1
- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- tokenizer.json +6 -1
- tokenizer_config.json +0 -1
- trainer_state.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
6 |
"d_ff": 1024,
|
7 |
"d_kv": 64,
|
8 |
"d_model": 512,
|
@@ -55,7 +56,7 @@
|
|
55 |
},
|
56 |
"tie_word_embeddings": false,
|
57 |
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32100
|
61 |
}
|
|
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
"d_ff": 1024,
|
8 |
"d_kv": 64,
|
9 |
"d_model": 512,
|
|
|
56 |
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.33.0.dev0",
|
60 |
"use_cache": true,
|
61 |
"vocab_size": 32100
|
62 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.33.0.dev0"
|
7 |
}
|
optimizer.pt
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:c5e7e3ade67e046cf678a327a74d1e89b94fc58bd74d72b97fb643ab6bec9afa
|
3 |
+
size 615619525
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307795461
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67b5fc5f47b76355aff1f518749b7211e26b9bf8b2cc7dc047b5c92c98881294
|
3 |
size 307795461
|
rng_state.pth
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 sha256:31d7d5a866cab29e4fbac2d608873c623722d7400b86b077e6ce1aeb0981c397
|
3 |
+
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a29a21453c7398ab3fb0d582b9ee3135dbbce28ad21e7e1c69411ee7ce947db
|
3 |
size 627
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 10,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -107,7 +107,6 @@
|
|
107 |
"model_max_length": 512,
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
-
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
|
111 |
"tokenizer_class": "T5Tokenizer",
|
112 |
"unk_token": "<unk>"
|
113 |
}
|
|
|
107 |
"model_max_length": 512,
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
|
|
110 |
"tokenizer_class": "T5Tokenizer",
|
111 |
"unk_token": "<unk>"
|
112 |
}
|
trainer_state.json
CHANGED
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 sha256:599372305a54fd3c64dc6d378e365a32a0e2fec180e36381656c0d0e1b395bfb
|
3 |
+
size 4347
|