edwinlaw commited on
Commit
b4e480e
1 Parent(s): c360fc9

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
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
+ 65000
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": 65000,
25
+ "decoder_vocab_size": 65001,
26
+ "do_blenderbot_90_layernorm": false,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "extra_pos_embeddings": 0,
34
+ "force_bos_token_to_be_generated": false,
35
+ "forced_eos_token_id": 0,
36
+ "gradient_checkpointing": false,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1",
40
+ "2": "LABEL_2"
41
+ },
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1,
47
+ "LABEL_2": 2
48
+ },
49
+ "max_length": 512,
50
+ "max_position_embeddings": 512,
51
+ "model_type": "marian",
52
+ "normalize_before": false,
53
+ "normalize_embedding": false,
54
+ "num_beams": 4,
55
+ "num_hidden_layers": 6,
56
+ "pad_token_id": 65000,
57
+ "scale_embedding": true,
58
+ "share_encoder_decoder_embeddings": true,
59
+ "static_position_embeddings": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.39.2",
62
+ "use_cache": true,
63
+ "vocab_size": 65001
64
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4b889bd930bb9ef17b969f8327ba43302ed3875232fbf557280aa8c3b450d7
3
+ size 309965092
runs/Mar31_03-29-05_9106895eed54/events.out.tfevents.1711855759.9106895eed54.1341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6ad5ad86d71b00383a73174acf912727d1af7846a9b9fa8d8de0da9a14fdfa
3
+ size 9865
runs/Mar31_03-33-40_9106895eed54/events.out.tfevents.1711856065.9106895eed54.1341.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c6dc8c84e6e9d6c993d1241e14081760e92a1a782a6d6ffe6baf5d0ddb082d
3
+ size 8798
source.spm ADDED
Binary file (806 kB). View file
 
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
Binary file (805 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "65000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "eng",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "zho",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb45afcf821ddfc7fe43cf0533afa6e16b0483afef5e5ecfdbe16071717dd36
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff