Training in progress, step 20000
Browse files
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"_num_labels": 3,
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
@@ -15,6 +16,7 @@
|
|
15 |
],
|
16 |
"bos_token_id": 0,
|
17 |
"classif_dropout": 0.0,
|
|
|
18 |
"d_model": 512,
|
19 |
"decoder_attention_heads": 8,
|
20 |
"decoder_ffn_dim": 2048,
|
@@ -27,6 +29,7 @@
|
|
27 |
"encoder_layerdrop": 0.0,
|
28 |
"encoder_layers": 6,
|
29 |
"eos_token_id": 0,
|
|
|
30 |
"id2label": {
|
31 |
"0": "LABEL_0",
|
32 |
"1": "LABEL_1",
|
@@ -46,8 +49,12 @@
|
|
46 |
"normalize_embedding": false,
|
47 |
"num_beams": 6,
|
48 |
"num_hidden_layers": 6,
|
|
|
49 |
"pad_token_id": 62517,
|
50 |
"scale_embedding": true,
|
51 |
"static_position_embeddings": true,
|
|
|
|
|
|
|
52 |
"vocab_size": 62518
|
53 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/alexey/work/ML/models/opus-mt-ru-en-finetuned",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "swish",
|
|
|
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,
|
|
|
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",
|
|
|
49 |
"normalize_embedding": false,
|
50 |
"num_beams": 6,
|
51 |
"num_hidden_layers": 6,
|
52 |
+
"output_attentions": true,
|
53 |
"pad_token_id": 62517,
|
54 |
"scale_embedding": true,
|
55 |
"static_position_embeddings": true,
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.16.2",
|
58 |
+
"use_cache": true,
|
59 |
"vocab_size": 62518
|
60 |
}
|
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 sha256:0079eb2e178ee979fd63d10e14e26e3150921aac2bde714f491ea3289ab29264
|
3 |
+
size 304935301
|
runs/Feb22_19-00-16_delta/1645556506.0858076/events.out.tfevents.1645556506.delta.916445.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3d0df605bcece004510d1625c7647105cc530382350f7cf665fb0422a86d22a
|
3 |
+
size 5122
|
runs/Feb22_19-00-16_delta/events.out.tfevents.1645556506.delta.916445.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0051074827e10b729ddaba466befa109573b22120dd61c2329043237cf6f9ccb
|
3 |
+
size 10559
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"target_lang": "en", "
|
|
|
1 |
+
{"source_lang": "ru", "target_lang": "en", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/alexey/work/ML/models/opus-mt-ru-en-finetuned/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/alexey/work/ML/models/opus-mt-ru-en-finetuned", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3247
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc5138131272e2bcbabc6046992c59ae80f2a267c529c5367e6829e235c62575
|
3 |
size 3247
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|