Jatana commited on
Commit
a4029b3
1 Parent(s): bd80ff1

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "aa1bf2d3fd3e1b2dbd46e6862fe3bbadd420ecf1",
3
+ "_name_or_path": "facebook/wmt19-en-ru",
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "FSMTForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "d_model": 1024,
12
+ "decoder": {
13
+ "_name_or_path": "",
14
+ "add_cross_attention": false,
15
+ "architectures": null,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 2,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "min_length": 0,
44
+ "model_type": "fsmt_decoder",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_return_sequences": 1,
49
+ "output_attentions": false,
50
+ "output_hidden_states": false,
51
+ "output_scores": false,
52
+ "pad_token_id": null,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "remove_invalid_values": false,
57
+ "repetition_penalty": 1.0,
58
+ "return_dict": true,
59
+ "return_dict_in_generate": false,
60
+ "sep_token_id": null,
61
+ "suppress_tokens": null,
62
+ "task_specific_params": null,
63
+ "temperature": 1.0,
64
+ "tf_legacy_loss": false,
65
+ "tie_encoder_decoder": false,
66
+ "tie_word_embeddings": true,
67
+ "tokenizer_class": null,
68
+ "top_k": 50,
69
+ "top_p": 1.0,
70
+ "torch_dtype": null,
71
+ "torchscript": false,
72
+ "transformers_version": "4.29.2",
73
+ "typical_p": 1.0,
74
+ "use_bfloat16": false,
75
+ "vocab_size": 31232
76
+ },
77
+ "decoder_attention_heads": 16,
78
+ "decoder_ffn_dim": 4096,
79
+ "decoder_layerdrop": 0,
80
+ "decoder_layers": 6,
81
+ "decoder_start_token_id": 2,
82
+ "dropout": 0.2,
83
+ "encoder_attention_heads": 16,
84
+ "encoder_ffn_dim": 8192,
85
+ "encoder_layerdrop": 0,
86
+ "encoder_layers": 6,
87
+ "eos_token_id": 2,
88
+ "forced_eos_token_id": 2,
89
+ "init_std": 0.02,
90
+ "is_encoder_decoder": true,
91
+ "langs": [
92
+ "en",
93
+ "ru"
94
+ ],
95
+ "length_penalty": 1.15,
96
+ "max_length": 200,
97
+ "max_position_embeddings": 1024,
98
+ "model_type": "fsmt",
99
+ "num_beams": 5,
100
+ "num_hidden_layers": 6,
101
+ "pad_token_id": 1,
102
+ "scale_embedding": true,
103
+ "src_vocab_size": 31640,
104
+ "tgt_vocab_size": 31232,
105
+ "tie_word_embeddings": false,
106
+ "torch_dtype": "float32",
107
+ "transformers_version": null,
108
+ "use_cache": true
109
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17538c5550c74610ffee730a93023351b19f73ad7b71a24a5ddaf9c1045730f5
3
+ size 1164464453
runs/May21_10-39-28_c7ce4759df33/1684665582.059114/events.out.tfevents.1684665582.c7ce4759df33.31.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e287f51e3356a8d0b9f516e678229eee5f27c6e354a2a08453065c666edcd92
3
+ size 6201
runs/May21_10-39-28_c7ce4759df33/events.out.tfevents.1684665582.c7ce4759df33.31.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1caa9d8bbcde81a8aa6a3f01e134eeb050973dd3122a39e18afdf94e5e4f68c3
3
+ size 6476
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "pad_token": "<pad>",
4
+ "sep_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "langs": [
6
+ "en",
7
+ "ru"
8
+ ],
9
+ "model_max_length": 1024,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "FSMTTokenizer",
13
+ "unk_token": "<unk>"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0edb6ed81a53408d25bf020d2b420d6cc9914fe7e2c99c1130b2e618c96c23
3
+ size 4091
vocab-src.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab-tgt.json ADDED
The diff for this file is too large to render. See raw diff