Training in progress, step 500
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +59 -0
- pytorch_model.bin +3 -0
- runs/Dec11_12-20-01_oem-WS-C621E-SAGE-Series/1670728814.5524786/events.out.tfevents.1670728814.oem-WS-C621E-SAGE-Series.2355764.1 +3 -0
- runs/Dec11_12-20-01_oem-WS-C621E-SAGE-Series/events.out.tfevents.1670728814.oem-WS-C621E-SAGE-Series.2355764.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +42 -0
- tokenizer.json +3 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": true,
|
8 |
+
"architectures": [
|
9 |
+
"MBartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 12,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"encoder_attention_heads": 16,
|
22 |
+
"encoder_ffn_dim": 4096,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"id2label": {
|
28 |
+
"0": "LABEL_0",
|
29 |
+
"1": "LABEL_1",
|
30 |
+
"2": "LABEL_2"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_2": 2
|
38 |
+
},
|
39 |
+
"max_length": 1024,
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "mbart",
|
42 |
+
"normalize_before": true,
|
43 |
+
"normalize_embedding": true,
|
44 |
+
"num_beams": 5,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"output_past": true,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": true,
|
49 |
+
"static_position_embeddings": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"translation_en_to_ro": {
|
52 |
+
"decoder_start_token_id": 250020
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.25.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250027
|
59 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1222c1e9a1bbe3f70ee8fefebc74edfa6c19aced596854b1f22ec81c5a226d3a
|
3 |
+
size 2444579705
|
runs/Dec11_12-20-01_oem-WS-C621E-SAGE-Series/1670728814.5524786/events.out.tfevents.1670728814.oem-WS-C621E-SAGE-Series.2355764.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54246f27d2601ce7252d3a27733ccf28fbf117a71b1f16d6f259f2308c153af5
|
3 |
+
size 5895
|
runs/Dec11_12-20-01_oem-WS-C621E-SAGE-Series/events.out.tfevents.1670728814.oem-WS-C621E-SAGE-Series.2355764.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36e6e48cb4257a8de1559cf40c1c0abdd6d391a0e6245f518607d2691258ac4d
|
3 |
+
size 5141
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ar_AR",
|
4 |
+
"cs_CZ",
|
5 |
+
"de_DE",
|
6 |
+
"en_XX",
|
7 |
+
"es_XX",
|
8 |
+
"et_EE",
|
9 |
+
"fi_FI",
|
10 |
+
"fr_XX",
|
11 |
+
"gu_IN",
|
12 |
+
"hi_IN",
|
13 |
+
"it_IT",
|
14 |
+
"ja_XX",
|
15 |
+
"kk_KZ",
|
16 |
+
"ko_KR",
|
17 |
+
"lt_LT",
|
18 |
+
"lv_LV",
|
19 |
+
"my_MM",
|
20 |
+
"ne_NP",
|
21 |
+
"nl_XX",
|
22 |
+
"ro_RO",
|
23 |
+
"ru_RU",
|
24 |
+
"si_LK",
|
25 |
+
"tr_TR",
|
26 |
+
"vi_VN",
|
27 |
+
"zh_CN"
|
28 |
+
],
|
29 |
+
"bos_token": "<s>",
|
30 |
+
"cls_token": "<s>",
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"mask_token": {
|
33 |
+
"content": "<mask>",
|
34 |
+
"lstrip": true,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"pad_token": "<pad>",
|
40 |
+
"sep_token": "</s>",
|
41 |
+
"unk_token": "<unk>"
|
42 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:455dfb92e249d851a62d066eb2717d181216c83c42cbc64839f987a6c369284e
|
3 |
+
size 17088268
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1024,
|
15 |
+
"name_or_path": "facebook/mbart-large-cc25",
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"src_lang": null,
|
20 |
+
"tgt_lang": null,
|
21 |
+
"tokenizer_class": "MBartTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae2b2a26bae9aee5c622c1ddba130b87010e6e41d90da8a6e911ebe3c964686c
|
3 |
+
size 3631
|