Training in progress, step 500
Browse files- .gitattributes +2 -0
- .gitignore +1 -0
- config.json +61 -0
- pytorch_model.bin +3 -0
- runs/Mar25_15-08-33_8d1f5b72a889/1679756927.754141/events.out.tfevents.1679756927.8d1f5b72a889.877.1 +3 -0
- runs/Mar25_15-08-33_8d1f5b72a889/1679756955.3317573/events.out.tfevents.1679756955.8d1f5b72a889.877.2 +3 -0
- runs/Mar25_15-08-33_8d1f5b72a889/1679756966.0453916/events.out.tfevents.1679756966.8d1f5b72a889.877.3 +3 -0
- runs/Mar25_15-08-33_8d1f5b72a889/events.out.tfevents.1679756927.8d1f5b72a889.877.0 +3 -0
- runs/Mar25_15-09-52_8d1f5b72a889/1679756999.8386106/events.out.tfevents.1679756999.8d1f5b72a889.877.5 +3 -0
- runs/Mar25_15-09-52_8d1f5b72a889/events.out.tfevents.1679756999.8d1f5b72a889.877.4 +3 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +3 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
36 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-mul-en",
|
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 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
64171
|
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,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 64171,
|
25 |
+
"decoder_vocab_size": 64172,
|
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": 64172,
|
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": 64171,
|
54 |
+
"scale_embedding": true,
|
55 |
+
"share_encoder_decoder_embeddings": true,
|
56 |
+
"static_position_embeddings": true,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.27.3",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 64172
|
61 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a2e8fce5241b09e4e002f0d2844ccda3df72122f35420202f7e44fbef839fc5
|
3 |
+
size 308321413
|
runs/Mar25_15-08-33_8d1f5b72a889/1679756927.754141/events.out.tfevents.1679756927.8d1f5b72a889.877.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a85afa9ab2fbe6c6d812586377aa7471400916d698db246c0f8b0a3056e145e4
|
3 |
+
size 6059
|
runs/Mar25_15-08-33_8d1f5b72a889/1679756955.3317573/events.out.tfevents.1679756955.8d1f5b72a889.877.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a50d658580e336d6921936ccfed74c1b3deb0f49a0b365fa076bd702625e5b8c
|
3 |
+
size 6059
|
runs/Mar25_15-08-33_8d1f5b72a889/1679756966.0453916/events.out.tfevents.1679756966.8d1f5b72a889.877.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a7dc07e0d2d544c8340343c5ef3a64057be7755543cde44ec8c415094495ab5
|
3 |
+
size 6059
|
runs/Mar25_15-08-33_8d1f5b72a889/events.out.tfevents.1679756927.8d1f5b72a889.877.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5950fbf0a056ee0db12b8fa899ef1d32a841a880c4e125ce014a21938442ede
|
3 |
+
size 14422
|
runs/Mar25_15-09-52_8d1f5b72a889/1679756999.8386106/events.out.tfevents.1679756999.8d1f5b72a889.877.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad3988c5039281751d198f6d341b75ffcf9dc027bae98fcfda0581e0a79edfb
|
3 |
+
size 6059
|
runs/Mar25_15-09-52_8d1f5b72a889/events.out.tfevents.1679756999.8d1f5b72a889.877.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49e4c1a11b8740dccf95665b9512324c0888bd4e35a6dd03c41b1f2c7c8050ef
|
3 |
+
size 6103
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
|
3 |
+
size 706917
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
|
3 |
+
size 791194
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"model_max_length": 512,
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"separate_vocabs": false,
|
6 |
+
"source_lang": "mul",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"target_lang": "eng",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c52709dc4b1803df8e2ee670830122e245d7cf4cc04b5f9653250a01edf5ccd
|
3 |
+
size 3707
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|