PontifexMaximus
commited on
Commit
•
61e8a84
1
Parent(s):
9443b75
Training in progress, step 500
Browse files- .gitattributes +2 -0
- .gitignore +1 -0
- config.json +61 -0
- pytorch_model.bin +3 -0
- runs/Jun02_10-22-10_a7e93b83523a/1654165341.5081027/events.out.tfevents.1654165341.a7e93b83523a.32262.1 +3 -0
- runs/Jun02_10-22-10_a7e93b83523a/events.out.tfevents.1654165341.a7e93b83523a.32262.0 +3 -0
- runs/Jun02_10-30-17_a7e93b83523a/1654165827.3800356/events.out.tfevents.1654165827.a7e93b83523a.32517.1 +3 -0
- runs/Jun02_10-30-17_a7e93b83523a/events.out.tfevents.1654165827.a7e93b83523a.32517.0 +3 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ 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 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
29 |
+
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": "PontifexMaximus/opus-mt-iir-en-finetuned-fa-to-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 |
+
62147
|
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": 62147,
|
25 |
+
"decoder_vocab_size": 62148,
|
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": 62148,
|
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": 62147,
|
54 |
+
"scale_embedding": true,
|
55 |
+
"share_encoder_decoder_embeddings": true,
|
56 |
+
"static_position_embeddings": true,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.19.2",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 62148
|
61 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61ed8f682b53568c696a76e15520d408fa76e9e9b922e7a249ed921f617cc092
|
3 |
+
size 304169960
|
runs/Jun02_10-22-10_a7e93b83523a/1654165341.5081027/events.out.tfevents.1654165341.a7e93b83523a.32262.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f441508ec1bf00706736bcf28964343bffd806b52d0c924c4c358c120b42811
|
3 |
+
size 5499
|
runs/Jun02_10-22-10_a7e93b83523a/events.out.tfevents.1654165341.a7e93b83523a.32262.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a44ff2f5af9559c81b5db09567073e5b403e2c37ae3dcd0a15fee980f636d36
|
3 |
+
size 4533
|
runs/Jun02_10-30-17_a7e93b83523a/1654165827.3800356/events.out.tfevents.1654165827.a7e93b83523a.32517.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db1168de896b877e27962f98eadf7457af2622177bb9d3c5a94d0954964fc9b2
|
3 |
+
size 5499
|
runs/Jun02_10-30-17_a7e93b83523a/events.out.tfevents.1654165827.a7e93b83523a.32517.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a0222fde71ed3774edd052405c912e9bb484e44ff4c1833f93b2cd40f0d9034
|
3 |
+
size 5060
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f14c1840d33660c20369afce6f7622f636157502a01a1b0587a39b97839f86e
|
3 |
+
size 928483
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc1189e0d60b63e3d1aac08def7f982b3b635c17dfc393c441408280e97ec55
|
3 |
+
size 801972
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "iir", "target_lang": "eng", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "PontifexMaximus/opus-mt-iir-en-finetuned-fa-to-en", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fdbe5498b320ff8e0fd2e699b783628fb603bbec75fefc74e9abc52900ffa72
|
3 |
+
size 3375
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|