Training in progress, epoch 1
Browse files- config.json +21 -6
- model.safetensors +2 -2
- runs/Apr09_20-51-58_6fc8090ca396/events.out.tfevents.1712698718.6fc8090ca396.107.9 +3 -0
- runs/Apr09_21-43-19_6fc8090ca396/events.out.tfevents.1712699074.6fc8090ca396.107.10 +3 -0
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +3 -3
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,25 +1,29 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Helsinki-NLP/opus-
|
|
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
|
|
|
|
5 |
"architectures": [
|
6 |
"MarianMTModel"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"bad_words_ids": [
|
10 |
[
|
11 |
-
|
12 |
]
|
13 |
],
|
14 |
"bos_token_id": 0,
|
|
|
15 |
"classifier_dropout": 0.0,
|
16 |
"d_model": 512,
|
17 |
"decoder_attention_heads": 8,
|
18 |
"decoder_ffn_dim": 2048,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 6,
|
21 |
-
"decoder_start_token_id":
|
22 |
-
"decoder_vocab_size":
|
23 |
"dropout": 0.1,
|
24 |
"encoder_attention_heads": 8,
|
25 |
"encoder_ffn_dim": 2048,
|
@@ -27,20 +31,31 @@
|
|
27 |
"encoder_layers": 6,
|
28 |
"eos_token_id": 0,
|
29 |
"forced_eos_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
30 |
"init_std": 0.02,
|
31 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
32 |
"max_length": 512,
|
33 |
"max_position_embeddings": 512,
|
34 |
"model_type": "marian",
|
|
|
35 |
"normalize_embedding": false,
|
36 |
"num_beams": 6,
|
37 |
"num_hidden_layers": 6,
|
38 |
-
"pad_token_id":
|
39 |
"scale_embedding": true,
|
40 |
"share_encoder_decoder_embeddings": true,
|
41 |
"static_position_embeddings": true,
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.38.2",
|
44 |
"use_cache": true,
|
45 |
-
"vocab_size":
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-tr-en",
|
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 |
+
62388
|
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": 62388,
|
26 |
+
"decoder_vocab_size": 62389,
|
27 |
"dropout": 0.1,
|
28 |
"encoder_attention_heads": 8,
|
29 |
"encoder_ffn_dim": 2048,
|
|
|
31 |
"encoder_layers": 6,
|
32 |
"eos_token_id": 0,
|
33 |
"forced_eos_token_id": 0,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1",
|
37 |
+
"2": "LABEL_2"
|
38 |
+
},
|
39 |
"init_std": 0.02,
|
40 |
"is_encoder_decoder": true,
|
41 |
+
"label2id": {
|
42 |
+
"LABEL_0": 0,
|
43 |
+
"LABEL_1": 1,
|
44 |
+
"LABEL_2": 2
|
45 |
+
},
|
46 |
"max_length": 512,
|
47 |
"max_position_embeddings": 512,
|
48 |
"model_type": "marian",
|
49 |
+
"normalize_before": false,
|
50 |
"normalize_embedding": false,
|
51 |
"num_beams": 6,
|
52 |
"num_hidden_layers": 6,
|
53 |
+
"pad_token_id": 62388,
|
54 |
"scale_embedding": true,
|
55 |
"share_encoder_decoder_embeddings": true,
|
56 |
"static_position_embeddings": true,
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.38.2",
|
59 |
"use_cache": true,
|
60 |
+
"vocab_size": 62389
|
61 |
}
|
model.safetensors
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 sha256:8ba9e8283148c12d0267aae39cf3b18c5ab72c63f5e9f47750499e9d37049887
|
3 |
+
size 304605268
|
runs/Apr09_20-51-58_6fc8090ca396/events.out.tfevents.1712698718.6fc8090ca396.107.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98b9aec4f751df8ad31841210b1d67f28e7d227db5cf2c7c9154fe50cbfd4d6
|
3 |
+
size 407
|
runs/Apr09_21-43-19_6fc8090ca396/events.out.tfevents.1712699074.6fc8090ca396.107.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5911f61a781a4cb06d06e1654454c1d02fefacfc2ce4829845fc8ab7386ecd29
|
3 |
+
size 5706
|
source.spm
CHANGED
Binary files a/source.spm and b/source.spm differ
|
|
target.spm
CHANGED
Binary files a/target.spm and b/target.spm differ
|
|
tokenizer_config.json
CHANGED
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -31,9 +31,9 @@
|
|
31 |
"pad_token": "<pad>",
|
32 |
"return_tensors": "pt",
|
33 |
"separate_vocabs": false,
|
34 |
-
"source_lang": "
|
35 |
"sp_model_kwargs": {},
|
36 |
-
"target_lang": "
|
37 |
"tokenizer_class": "MarianTokenizer",
|
38 |
"unk_token": "<unk>"
|
39 |
}
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"62388": {
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
31 |
"pad_token": "<pad>",
|
32 |
"return_tensors": "pt",
|
33 |
"separate_vocabs": false,
|
34 |
+
"source_lang": "tr",
|
35 |
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "en",
|
37 |
"tokenizer_class": "MarianTokenizer",
|
38 |
"unk_token": "<unk>"
|
39 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02a5e59a03214ae703bcf2dda91023973a8cc9b396428b2f748b1ff030331b15
|
3 |
size 5048
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|