Training in progress, step 20000
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +7 -0
- pytorch_model.bin +2 -2
- runs/Feb20_22-04-56_delta/1645394773.327203/events.out.tfevents.1645394773.delta.323510.1 +3 -0
- runs/Feb20_22-04-56_delta/events.out.tfevents.1645394773.delta.323510.0 +3 -0
- runs/Feb20_22-46-07_delta/1645397262.9262424/events.out.tfevents.1645397262.delta.328165.1 +3 -0
- runs/Feb20_22-46-07_delta/events.out.tfevents.1645397262.delta.328165.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -1
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.spm filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
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:b68e11af89a65aedf53b6dd74366ba9d49ae2a57c1cd0617d493a3e4340e3eba
|
3 |
+
size 304935301
|
runs/Feb20_22-04-56_delta/1645394773.327203/events.out.tfevents.1645394773.delta.323510.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a7cf63b243f10db3ff2643c1456cc168a42067137da0b5356f16aba800ebb8a
|
3 |
+
size 5119
|
runs/Feb20_22-04-56_delta/events.out.tfevents.1645394773.delta.323510.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d497bd46feba627b1b0e4d6ded4121099ef833caa8aaaeebb8084720a539856c
|
3 |
+
size 7871
|
runs/Feb20_22-46-07_delta/1645397262.9262424/events.out.tfevents.1645397262.delta.328165.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f84736f3e9f21e66f6a769b9127fbd6714aa554dddea80abd323c3c5d2fab8
|
3 |
+
size 5119
|
runs/Feb20_22-46-07_delta/events.out.tfevents.1645397262.delta.328165.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dc96b5c9842b5c09409f46d078e9c6546b7bfede82d9116224155b687124680
|
3 |
+
size 10563
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
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": null, "tokenizer_file": null, "name_or_path": "/home/alexey/work/ML/models/opus-mt-ru-en-finetuned", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd930b5750b69685448f56d780f72137ea71afacaa82d136967da25bf09f47c6
|
3 |
+
size 3247
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|