MihaiIonascu commited on
Commit
fbc3926
1 Parent(s): 14e9738

Upload 13 files

Browse files
config.json CHANGED
@@ -1,61 +1,62 @@
1
  {
2
- "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-en-ro",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "swish",
6
- "add_bias_logits": false,
7
- "add_final_layer_norm": false,
8
- "architectures": [
9
- "MarianMTModel"
10
- ],
11
- "attention_dropout": 0.0,
12
- "bad_words_ids": [
13
- [
14
- 0
15
- ]
16
- ],
17
- "bos_token_id": 1,
18
- "classif_dropout": 0.0,
19
- "classifier_dropout": 0.0,
20
- "d_model": 512,
21
- "decoder_attention_heads": 8,
22
- "decoder_ffn_dim": 2048,
23
- "decoder_layerdrop": 0.0,
24
- "decoder_layers": 6,
25
- "decoder_start_token_id": 3,
26
- "decoder_vocab_size": 5000,
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
- "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": 4,
52
- "num_hidden_layers": 6,
53
- "pad_token_id": 3,
54
- "scale_embedding": true,
55
- "share_encoder_decoder_embeddings": true,
56
- "static_position_embeddings": true,
57
- "transformers_version": "4.26.0",
58
- "unk_token_id": 0,
59
- "use_cache": true,
60
- "vocab_size": 5000
61
- }
 
 
1
  {
2
+ "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-en-ro",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 0
15
+ ]
16
+ ],
17
+ "bos_token_id": 1,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 3,
26
+ "decoder_vocab_size": 5001,
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
+ "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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 3,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.28.1",
59
+ "unk_token_id": 0,
60
+ "use_cache": true,
61
+ "vocab_size": 5001
62
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 0
6
+ ]
7
+ ],
8
+ "bos_token_id": 1,
9
+ "decoder_start_token_id": 3,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 3,
15
+ "transformers_version": "4.28.1"
16
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3093ebd7eae18bd248aacbdae18693bfc4b3458e6f72c4a826a88071e1c14942
3
+ size 373740549
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66e53afd9fc3492db8807cc29a803876533e861c6232519429ab5c8aa7bf90f
3
+ size 186902533
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc339a7e6d71021c6a714aea6a5df0012f28c1a77e149f1deccb8b895ba7bc53
3
+ size 14639
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e44d69736afd2f1bb0b26ac65c545f9331c2366e965937dc44a11b28a3661d2
3
+ size 627
source.spm ADDED
Binary file (319 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 (319 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": null,
8
+ "sp_model_kwargs": {},
9
+ "target_lang": null,
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 5160,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.8e-05,
13
+ "loss": 3.0809,
14
+ "step": 516
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 1.6000000000000003e-05,
19
+ "loss": 1.5633,
20
+ "step": 1032
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 1.4e-05,
25
+ "loss": 1.2472,
26
+ "step": 1548
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 1.0916,
32
+ "step": 2064
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 1e-05,
37
+ "loss": 0.999,
38
+ "step": 2580
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 8.000000000000001e-06,
43
+ "loss": 0.9357,
44
+ "step": 3096
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 6e-06,
49
+ "loss": 0.8904,
50
+ "step": 3612
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 4.000000000000001e-06,
55
+ "loss": 0.8592,
56
+ "step": 4128
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 2.0000000000000003e-06,
61
+ "loss": 0.8373,
62
+ "step": 4644
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 0.0,
67
+ "loss": 0.8272,
68
+ "step": 5160
69
+ }
70
+ ],
71
+ "max_steps": 5160,
72
+ "num_train_epochs": 10,
73
+ "total_flos": 322635103469568.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92c9b87e48425fc304ec4661c09257088b93ffc93963a8f3393dc44ad8535f5
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff