ZachBeesley commited on
Commit
a7c348f
1 Parent(s): c208918

Training in progress epoch 0

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ source.spm filter=lfs diff=lfs merge=lfs -text
37
+ target.spm filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-fr
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: ZachBeesley/marian-finetuned-kde4-en-to-fr
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ZachBeesley/marian-finetuned-kde4-en-to-fr
15
+
16
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.0624
19
+ - Validation Loss: 0.8783
20
+ - Epoch: 0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 17733, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
40
+ - training_precision: mixed_float16
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Epoch |
45
+ |:----------:|:---------------:|:-----:|
46
+ | 1.0624 | 0.8783 | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.31.0
52
+ - TensorFlow 2.12.0
53
+ - Datasets 2.13.1
54
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
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
+ 59513
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": 59513,
26
+ "decoder_vocab_size": 59514,
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
+ "gradient_checkpointing": false,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2"
39
+ },
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1,
45
+ "LABEL_2": 2
46
+ },
47
+ "max_length": 512,
48
+ "max_position_embeddings": 512,
49
+ "model_type": "marian",
50
+ "normalize_before": false,
51
+ "normalize_embedding": false,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 59513,
55
+ "scale_embedding": true,
56
+ "share_encoder_decoder_embeddings": true,
57
+ "static_position_embeddings": true,
58
+ "transformers_version": "4.31.0",
59
+ "use_cache": true,
60
+ "vocab_size": 59514
61
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 59513
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 59513,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 59513,
15
+ "transformers_version": "4.31.0"
16
+ }
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173e9f493a668fe396d599e28d414a201193094e6ffd7a4678e5aab0f6d3d838
3
+ size 778395
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d0e717c77053f1c4b856d8661d9cb87c64f083a35418c087b9146300e4f585
3
+ size 802397
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e68f0763b5839742fed52313bb1481f317a2b6b09ee5b48f8f23b7a3e2a30f
3
+ size 301061272
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": "en",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "fr",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff