Shaarang commited on
Commit
bdb9352
1 Parent(s): c474f9a

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: huggingface-course/marian-finetuned-kde4-en-to-fr
5
+ tags:
6
+ - translation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: marian-finetuned-kde4-en-to-fr
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # marian-finetuned-kde4-en-to-fr
17
+
18
+ This model is a fine-tuned version of [huggingface-course/marian-finetuned-kde4-en-to-fr](https://huggingface.co/huggingface-course/marian-finetuned-kde4-en-to-fr) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - eval_loss: 0.8554
21
+ - eval_model_preparation_time: 0.0066
22
+ - eval_bleu: 52.9488
23
+ - eval_runtime: 1574.6719
24
+ - eval_samples_per_second: 13.348
25
+ - eval_steps_per_second: 0.209
26
+ - step: 0
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 32
47
+ - eval_batch_size: 64
48
+ - seed: 42
49
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 3
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.46.3
57
+ - Pytorch 2.5.1+cu121
58
+ - Tokenizers 0.20.3
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huggingface-course/marian-finetuned-kde4-en-to-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
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 512,
16
+ "decoder_attention_heads": 8,
17
+ "decoder_ffn_dim": 2048,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 59513,
21
+ "decoder_vocab_size": 59514,
22
+ "dropout": 0.1,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 0,
28
+ "forced_eos_token_id": 0,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_length": null,
43
+ "max_position_embeddings": 512,
44
+ "model_type": "marian",
45
+ "normalize_before": false,
46
+ "normalize_embedding": false,
47
+ "num_beams": null,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 59513,
50
+ "scale_embedding": true,
51
+ "share_encoder_decoder_embeddings": true,
52
+ "static_position_embeddings": true,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.46.3",
55
+ "use_cache": true,
56
+ "vocab_size": 59514
57
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 59513
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 59513,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 59513,
14
+ "transformers_version": "4.46.3"
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781099a6e7b447bc3836bb6ab28c50f26d04f9bed0f17aa145f009876bbeb89e
3
+ size 298705768
runs/Dec11_03-28-22_daa4463e4c71/events.out.tfevents.1733889285.daa4463e4c71.226.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f42cd4780af8acd4f8c0122599f468bb4f366e253f797624d729971246146b
3
+ size 405
source.spm ADDED
Binary file (778 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 (802 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "59513": {
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": false,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "return_tensors": "pt",
33
+ "separate_vocabs": false,
34
+ "source_lang": "en",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "fr",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021571539a62b13087a0178a58f9fad195f66c9c15b0ba4bf9593eb2d4229789
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff