wingo-dz commited on
Commit
b301389
1 Parent(s): 7e9a0fc

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - ar
5
+ license: apache-2.0
6
+ base_model: Helsinki-NLP/opus-mt-en-ar
7
+ tags:
8
+ - generated_from_trainer
9
+ metrics:
10
+ - bleu
11
+ model-index:
12
+ - name: opus_2
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # opus_2
20
+
21
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0955
24
+ - Bleu: 88.6881
25
+ - Gen Len: 9.3881
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 4
46
+ - eval_batch_size: 4
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 3.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.39.0.dev0
59
+ - Pytorch 2.2.1+cu121
60
+ - Datasets 2.18.0
61
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 88.6881,
4
+ "eval_gen_len": 9.3881,
5
+ "eval_loss": 0.09552541375160217,
6
+ "eval_runtime": 5.5974,
7
+ "eval_samples": 67,
8
+ "eval_samples_per_second": 11.97,
9
+ "eval_steps_per_second": 3.037,
10
+ "train_loss": 0.2668434212741242,
11
+ "train_runtime": 32.5365,
12
+ "train_samples": 581,
13
+ "train_samples_per_second": 53.571,
14
+ "train_steps_per_second": 13.462
15
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bad_words_ids": [
12
+ [
13
+ 62801
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 512,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 2048,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 62801,
25
+ "decoder_vocab_size": 62802,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "extra_pos_embeddings": 62802,
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": 62801,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.39.0.dev0",
59
+ "use_cache": true,
60
+ "vocab_size": 62802
61
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 88.6881,
4
+ "eval_gen_len": 9.3881,
5
+ "eval_loss": 0.09552541375160217,
6
+ "eval_runtime": 5.5974,
7
+ "eval_samples": 67,
8
+ "eval_samples_per_second": 11.97,
9
+ "eval_steps_per_second": 3.037
10
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62801
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62801,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62801,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.0.dev0"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd780f0254cd9a15a40d79fa580c080150823c7ed7784f08d889f6baf94f06d
3
+ size 305452744
runs/Mar20_11-45-23_183c4c161347/events.out.tfevents.1710935136.183c4c161347.2177.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e13e32364ee8f68aabc7e2a72d205422b6b24111be5b345fecb7f54f22658b9
3
+ size 5820
runs/Mar20_11-45-23_183c4c161347/events.out.tfevents.1710935175.183c4c161347.2177.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac111cc55b917f567ebdda11c387068c3568884a691e25be5d421aa776d8886
3
+ size 458
source.spm ADDED
Binary file (801 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 (917 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
+ "62801": {
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": "eng",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "ara",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.2668434212741242,
4
+ "train_runtime": 32.5365,
5
+ "train_samples": 581,
6
+ "train_samples_per_second": 53.571,
7
+ "train_steps_per_second": 13.462
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 438,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.0,
13
+ "step": 438,
14
+ "total_flos": 8514051047424.0,
15
+ "train_loss": 0.2668434212741242,
16
+ "train_runtime": 32.5365,
17
+ "train_samples_per_second": 53.571,
18
+ "train_steps_per_second": 13.462
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 438,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 8514051047424.0,
27
+ "train_batch_size": 4,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae7b00033336a58b397405b448d55a837f7e24a76bbf015dc1fe5431c579f19
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff