Training in progress, step 500
Browse files- .gitattributes +2 -0
- .gitignore +1 -0
- config.json +59 -0
- pytorch_model.bin +3 -0
- runs/Aug01_16-05-45_DESKTOP-B1IIUGJ/1659359155.2767544/events.out.tfevents.1659359155.DESKTOP-B1IIUGJ.16408.5 +3 -0
- runs/Aug01_16-05-45_DESKTOP-B1IIUGJ/events.out.tfevents.1659359155.DESKTOP-B1IIUGJ.16408.4 +3 -0
- runs/Aug01_16-08-10_DESKTOP-B1IIUGJ/1659359298.5039968/events.out.tfevents.1659359298.DESKTOP-B1IIUGJ.16408.7 +3 -0
- runs/Aug01_16-08-10_DESKTOP-B1IIUGJ/events.out.tfevents.1659359298.DESKTOP-B1IIUGJ.16408.6 +3 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -29,3 +29,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
32 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
33 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ru",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
62517
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 62517,
|
26 |
+
"dropout": 0.1,
|
27 |
+
"encoder_attention_heads": 8,
|
28 |
+
"encoder_ffn_dim": 2048,
|
29 |
+
"encoder_layerdrop": 0.0,
|
30 |
+
"encoder_layers": 6,
|
31 |
+
"eos_token_id": 0,
|
32 |
+
"forced_eos_token_id": 0,
|
33 |
+
"id2label": {
|
34 |
+
"0": "LABEL_0",
|
35 |
+
"1": "LABEL_1",
|
36 |
+
"2": "LABEL_2"
|
37 |
+
},
|
38 |
+
"init_std": 0.02,
|
39 |
+
"is_encoder_decoder": true,
|
40 |
+
"label2id": {
|
41 |
+
"LABEL_0": 0,
|
42 |
+
"LABEL_1": 1,
|
43 |
+
"LABEL_2": 2
|
44 |
+
},
|
45 |
+
"max_length": 512,
|
46 |
+
"max_position_embeddings": 512,
|
47 |
+
"model_type": "marian",
|
48 |
+
"normalize_before": false,
|
49 |
+
"normalize_embedding": false,
|
50 |
+
"num_beams": 4,
|
51 |
+
"num_hidden_layers": 6,
|
52 |
+
"pad_token_id": 62517,
|
53 |
+
"scale_embedding": true,
|
54 |
+
"static_position_embeddings": true,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.13.0",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 62518
|
59 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9006a8e0a80a03873ac272e1bfd03f87616d0ef321e85c8daf4f16d81a3d1c2
|
3 |
+
size 304935301
|
runs/Aug01_16-05-45_DESKTOP-B1IIUGJ/1659359155.2767544/events.out.tfevents.1659359155.DESKTOP-B1IIUGJ.16408.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb244acedce2b99c48b02fa77ac505b238f31e65ba6518c7feac814a2f9ae8e1
|
3 |
+
size 4977
|
runs/Aug01_16-05-45_DESKTOP-B1IIUGJ/events.out.tfevents.1659359155.DESKTOP-B1IIUGJ.16408.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36ffcdcf99b4635809e3e1f28d3685910d342067ba881f5edd4f2c716b186f2d
|
3 |
+
size 4094
|
runs/Aug01_16-08-10_DESKTOP-B1IIUGJ/1659359298.5039968/events.out.tfevents.1659359298.DESKTOP-B1IIUGJ.16408.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dc08a61363399263186a0cefc6ed861f8fbd18113b384e3a6195a9083b82d77
|
3 |
+
size 4977
|
runs/Aug01_16-08-10_DESKTOP-B1IIUGJ/events.out.tfevents.1659359298.DESKTOP-B1IIUGJ.16408.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3607979528cb734630b6ef4783668d82e1ea18d1902272c9560b1b2b3515ee7e
|
3 |
+
size 4621
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16bebef1389a0b8ab452772c4e35b9e605e5713f8ac7baa71ca701394eaa086d
|
3 |
+
size 802781
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
|
3 |
+
size 1080169
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "en", "target_lang": "ru", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-ru", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718eec6835b50f254535884fd13105251ac48379b6094c4c2eed6a118498391e
|
3 |
+
size 3055
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|