End of training
Browse files- added_tokens.json +0 -0
- config.json +3 -21
- pytorch_model.bin +2 -2
- runs/Jan29_07-19-23_5970884deb1f/1643440883.1514513/events.out.tfevents.1643440883.5970884deb1f.34.1 +3 -0
- runs/Jan29_07-19-23_5970884deb1f/events.out.tfevents.1643440883.5970884deb1f.34.0 +3 -0
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.json +0 -0
added_tokens.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
config.json
CHANGED
@@ -1,9 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Helsinki-NLP/opus-
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"MarianMTModel"
|
9 |
],
|
@@ -14,7 +12,6 @@
|
|
14 |
]
|
15 |
],
|
16 |
"bos_token_id": 0,
|
17 |
-
"classif_dropout": 0.0,
|
18 |
"classifier_dropout": 0.0,
|
19 |
"d_model": 512,
|
20 |
"decoder_attention_heads": 8,
|
@@ -22,35 +19,20 @@
|
|
22 |
"decoder_layerdrop": 0.0,
|
23 |
"decoder_layers": 6,
|
24 |
"decoder_start_token_id": 65000,
|
25 |
-
"do_blenderbot_90_layernorm": false,
|
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 |
-
"extra_pos_embeddings": 0,
|
33 |
-
"force_bos_token_to_be_generated": false,
|
34 |
"forced_eos_token_id": 0,
|
35 |
-
"gradient_checkpointing": false,
|
36 |
-
"id2label": {
|
37 |
-
"0": "LABEL_0",
|
38 |
-
"1": "LABEL_1",
|
39 |
-
"2": "LABEL_2"
|
40 |
-
},
|
41 |
"init_std": 0.02,
|
42 |
"is_encoder_decoder": true,
|
43 |
-
"label2id": {
|
44 |
-
"LABEL_0": 0,
|
45 |
-
"LABEL_1": 1,
|
46 |
-
"LABEL_2": 2
|
47 |
-
},
|
48 |
"max_length": 512,
|
49 |
"max_position_embeddings": 512,
|
50 |
"model_type": "marian",
|
51 |
-
"normalize_before": false,
|
52 |
"normalize_embedding": false,
|
53 |
-
"num_beams":
|
54 |
"num_hidden_layers": 6,
|
55 |
"pad_token_id": 65000,
|
56 |
"scale_embedding": true,
|
@@ -58,5 +40,5 @@
|
|
58 |
"torch_dtype": "float32",
|
59 |
"transformers_version": "4.12.5",
|
60 |
"use_cache": true,
|
61 |
-
"vocab_size":
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
|
|
|
|
5 |
"architectures": [
|
6 |
"MarianMTModel"
|
7 |
],
|
|
|
12 |
]
|
13 |
],
|
14 |
"bos_token_id": 0,
|
|
|
15 |
"classifier_dropout": 0.0,
|
16 |
"d_model": 512,
|
17 |
"decoder_attention_heads": 8,
|
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 6,
|
21 |
"decoder_start_token_id": 65000,
|
|
|
22 |
"dropout": 0.1,
|
23 |
"encoder_attention_heads": 8,
|
24 |
"encoder_ffn_dim": 2048,
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
"encoder_layers": 6,
|
27 |
"eos_token_id": 0,
|
|
|
|
|
28 |
"forced_eos_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"init_std": 0.02,
|
30 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
31 |
"max_length": 512,
|
32 |
"max_position_embeddings": 512,
|
33 |
"model_type": "marian",
|
|
|
34 |
"normalize_embedding": false,
|
35 |
+
"num_beams": 6,
|
36 |
"num_hidden_layers": 6,
|
37 |
"pad_token_id": 65000,
|
38 |
"scale_embedding": true,
|
|
|
40 |
"torch_dtype": "float32",
|
41 |
"transformers_version": "4.12.5",
|
42 |
"use_cache": true,
|
43 |
+
"vocab_size": 97154
|
44 |
}
|
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:a8514afafbe887868a9e616ef77265dd3326dcc82d1e93c79b3fe2084a553e30
|
3 |
+
size 376008389
|
runs/Jan29_07-19-23_5970884deb1f/1643440883.1514513/events.out.tfevents.1643440883.5970884deb1f.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07677b52cf28ec8a5ae4d5daed3ed5097e9587cc936b32ccf8a94f78d8d4ac2b
|
3 |
+
size 4762
|
runs/Jan29_07-19-23_5970884deb1f/events.out.tfevents.1643440883.5970884deb1f.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e826b06f2b73c5ac85b6621448365ee668aa850c785ce96893a95955327905
|
3 |
+
size 9845
|
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
@@ -1 +1 @@
|
|
1 |
-
{"source_lang": "eng", "target_lang": "
|
|
|
1 |
+
{"source_lang": "eng", "target_lang": "jpn", "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-tatoeba-en-ja", "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 2991
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49bac0c85d7b019edec7a622cd96d1fc898b4f6863a046f1559fc968437dff18
|
3 |
size 2991
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|