Commit
•
782234f
1
Parent(s):
266465a
Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +62 -0
- pytorch_model.bin +3 -0
- runs/Feb09_10-32-28_0a045820093f/1675938754.861113/events.out.tfevents.1675938754.0a045820093f.2806.1 +3 -0
- runs/Feb09_10-32-28_0a045820093f/1675939323.6748614/events.out.tfevents.1675939323.0a045820093f.2806.3 +3 -0
- runs/Feb09_10-32-28_0a045820093f/events.out.tfevents.1675938754.0a045820093f.2806.0 +3 -0
- runs/Feb09_10-32-28_0a045820093f/events.out.tfevents.1675939323.0a045820093f.2806.2 +3 -0
- tokenizer.json +16 -2
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/ruT5-base",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"T5ForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"max_length": 256,
|
20 |
+
"model_type": "t5",
|
21 |
+
"n_positions": 512,
|
22 |
+
"num_decoder_layers": 12,
|
23 |
+
"num_heads": 12,
|
24 |
+
"num_layers": 12,
|
25 |
+
"output_past": true,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"relative_attention_max_distance": 128,
|
28 |
+
"relative_attention_num_buckets": 32,
|
29 |
+
"task_specific_params": {
|
30 |
+
"summarization": {
|
31 |
+
"early_stopping": true,
|
32 |
+
"length_penalty": 2.0,
|
33 |
+
"max_length": 200,
|
34 |
+
"min_length": 30,
|
35 |
+
"no_repeat_ngram_size": 3,
|
36 |
+
"num_beams": 4,
|
37 |
+
"prefix": "summarize: "
|
38 |
+
},
|
39 |
+
"translation_en_to_de": {
|
40 |
+
"early_stopping": true,
|
41 |
+
"max_length": 300,
|
42 |
+
"num_beams": 4,
|
43 |
+
"prefix": "translate English to German: "
|
44 |
+
},
|
45 |
+
"translation_en_to_fr": {
|
46 |
+
"early_stopping": true,
|
47 |
+
"max_length": 300,
|
48 |
+
"num_beams": 4,
|
49 |
+
"prefix": "translate English to French: "
|
50 |
+
},
|
51 |
+
"translation_en_to_ro": {
|
52 |
+
"early_stopping": true,
|
53 |
+
"max_length": 300,
|
54 |
+
"num_beams": 4,
|
55 |
+
"prefix": "translate English to Romanian: "
|
56 |
+
}
|
57 |
+
},
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.26.0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 32128
|
62 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59e8ce5f82df532b736f73e4ce5ea302a95966900978eaa48e5042797fa6be19
|
3 |
+
size 891702929
|
runs/Feb09_10-32-28_0a045820093f/1675938754.861113/events.out.tfevents.1675938754.0a045820093f.2806.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f09f2d62863479d11d1721a79068ff531a467a648d0c6a23b7accb4d12ac5a3c
|
3 |
+
size 5900
|
runs/Feb09_10-32-28_0a045820093f/1675939323.6748614/events.out.tfevents.1675939323.0a045820093f.2806.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a65f59fb22143c5cb142f23253836a3c57e64cef00193acb87588f9c74a4716d
|
3 |
+
size 5900
|
runs/Feb09_10-32-28_0a045820093f/events.out.tfevents.1675938754.0a045820093f.2806.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d7068c7ddbd725be62832a5d29434f2b400e973b2873c1c3377a0d6fddda00
|
3 |
+
size 34324
|
runs/Feb09_10-32-28_0a045820093f/events.out.tfevents.1675939323.0a045820093f.2806.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5c7eb1cf433640be3c01259909e3fd99c31e5bb3c22f7f44c75144b06640bcc
|
3 |
+
size 84829
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 256
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6db653e1f5cc5c1a718f5f70c80404c7559621726f49ac066b408b40259d3004
|
3 |
+
size 3579
|