zaneas commited on
Commit
99f9bb3
1 Parent(s): 22903eb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-it-en
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - kde4
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: finetuned-model
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: kde4
18
+ type: kde4
19
+ config: en-it
20
+ split: train
21
+ args: en-it
22
+ metrics:
23
+ - name: Bleu
24
+ type: bleu
25
+ value: 49.84827474739364
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # finetuned-model
32
+
33
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-it-en](https://huggingface.co/Helsinki-NLP/opus-mt-it-en) on the kde4 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.0563
36
+ - Bleu: 49.8483
37
+ - Bert Score: 0.9570
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 64
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 3
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.38.2
72
+ - Pytorch 2.2.1+cu121
73
+ - Datasets 2.19.0
74
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-it-en",
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
+ 80378
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
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": 80378,
26
+ "decoder_vocab_size": 80379,
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": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 80378,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.38.2",
59
+ "use_cache": true,
60
+ "vocab_size": 80379
61
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 80378
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 80378,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 80378,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.38.2"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f506622c17168b98ee8961f280bf3185724ddd96605dd6bb27ba4477dc1befd2
3
+ size 341520748
runs/Apr21_13-20-22_84f7eeb3c140/events.out.tfevents.1713705643.84f7eeb3c140.191.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0337b0be654ff1098310895af28a922c97f3a8b75951279289580f4a784228
3
+ size 6213
runs/Apr21_13-20-22_84f7eeb3c140/events.out.tfevents.1713706127.84f7eeb3c140.191.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e8c178c63ee51658d3eecf959a4f49794ecbd5bdd548277bc0c8946ba755ea
3
+ size 6213
runs/Apr21_14-04-58_84f7eeb3c140/events.out.tfevents.1713708319.84f7eeb3c140.191.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de1a1fedaf2e163c59e1aa4af11108292aaeedc27afdfccb4a2d5b018b6564d6
3
+ size 4184
runs/Apr21_14-09-55_84f7eeb3c140/events.out.tfevents.1713708617.84f7eeb3c140.13373.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6473409f18336abe4dd859ebe1418e7f329f03eefbb4deb03738fe52beaeb7a
3
+ size 6635
runs/Apr21_14-09-55_84f7eeb3c140/events.out.tfevents.1713709884.84f7eeb3c140.13373.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322e0ee75e197d0753e40bb966a757676a9c61b12e9432f87e18a4783e30b4f5
3
+ size 461
runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713710136.84f7eeb3c140.20099.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457db3f995174ce5a01d833fbc866bb2bcb6a5e4b3a0c155558b46947339348a
3
+ size 6846
runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713711909.84f7eeb3c140.20099.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8285e758b3cebe5837caeaea02af98de050151028e1d6abda7ab8c8d66b1dd75
3
+ size 461
runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713712525.84f7eeb3c140.20099.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828573548c030ec2001020631dd42b752957bc4b90e9b1cfc8beee40a848856a
3
+ size 6846
runs/Apr21_14-35-17_84f7eeb3c140/events.out.tfevents.1713715617.84f7eeb3c140.20099.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14e87d2a12de913e38dce4481839ebafd88aa5cf376df6b3fe0c4d6e6293f4a
3
+ size 461
source.spm ADDED
Binary file (814 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 (790 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
+ "80378": {
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": "it",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
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 sha256:11ff27f283cd98f1131339625e468cd86c80c8ccf9dc8342678ec2d5859872ed
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff