Hugging Face's logo

brendaogutu
/
mul-sw-en-translation-phase2

Translation
TensorBoard
Safetensors
Swahili
English
marian
swahili
english
opus-mt
openchs
Model card Files
xet
 Metrics Community
brendaogutu commited on
Commit
2477520
·
verified ·
1 Parent(s): 697bf81

Upload fine-tuned model - BLEU: 0.1327

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. README.md +4 -4
  3. checkpoint-48000/config.json +54 -0
  4. checkpoint-48000/generation_config.json +17 -0
  5. checkpoint-48000/model.safetensors +3 -0
  6. checkpoint-48000/optimizer.pt +3 -0
  7. checkpoint-48000/rng_state.pth +3 -0
  8. checkpoint-48000/scaler.pt +3 -0
  9. checkpoint-48000/scheduler.pt +3 -0
  10. checkpoint-48000/source.spm +3 -0
  11. checkpoint-48000/special_tokens_map.json +23 -0
  12. checkpoint-48000/target.spm +3 -0
  13. checkpoint-48000/tokenizer_config.json +39 -0
  14. checkpoint-48000/trainer_state.json +0 -0
  15. checkpoint-48000/training_args.bin +3 -0
  16. checkpoint-48000/training_metrics_snapshot.json +0 -0
  17. checkpoint-48000/vocab.json +0 -0
  18. checkpoint-76000/config.json +54 -0
  19. checkpoint-76000/generation_config.json +17 -0
  20. checkpoint-76000/model.safetensors +3 -0
  21. checkpoint-76000/optimizer.pt +3 -0
  22. checkpoint-76000/rng_state.pth +3 -0
  23. checkpoint-76000/scaler.pt +3 -0
  24. checkpoint-76000/scheduler.pt +3 -0
  25. checkpoint-76000/source.spm +3 -0
  26. checkpoint-76000/special_tokens_map.json +23 -0
  27. checkpoint-76000/target.spm +3 -0
  28. checkpoint-76000/tokenizer_config.json +39 -0
  29. checkpoint-76000/trainer_state.json +0 -0
  30. checkpoint-76000/training_args.bin +3 -0
  31. checkpoint-76000/training_metrics_snapshot.json +0 -0
  32. checkpoint-76000/vocab.json +0 -0
  33. checkpoint-78000/config.json +54 -0
  34. checkpoint-78000/generation_config.json +17 -0
  35. checkpoint-78000/model.safetensors +3 -0
  36. checkpoint-78000/optimizer.pt +3 -0
  37. checkpoint-78000/rng_state.pth +3 -0
  38. checkpoint-78000/scaler.pt +3 -0
  39. checkpoint-78000/scheduler.pt +3 -0
  40. checkpoint-78000/source.spm +3 -0
  41. checkpoint-78000/special_tokens_map.json +23 -0
  42. checkpoint-78000/target.spm +3 -0
  43. checkpoint-78000/tokenizer_config.json +39 -0
  44. checkpoint-78000/trainer_state.json +0 -0
  45. checkpoint-78000/training_args.bin +3 -0
  46. checkpoint-78000/training_metrics_snapshot.json +0 -0
  47. checkpoint-78000/vocab.json +0 -0
  48. logs/events.out.tfevents.1763880503.558d7902982f.33610.0 +2 -2
  49. logs/events.out.tfevents.1763904673.558d7902982f.33610.1 +3 -0
  50. logs/events.out.tfevents.1763904694.558d7902982f.33610.2 +3 -0
.gitattributes CHANGED
@@ -119,3 +119,9 @@ checkpoints/checkpoint-76000/source.spm filter=lfs diff=lfs merge=lfs -text
119
  checkpoints/checkpoint-76000/target.spm filter=lfs diff=lfs merge=lfs -text
120
  checkpoints/checkpoint-78000/source.spm filter=lfs diff=lfs merge=lfs -text
121
  checkpoints/checkpoint-78000/target.spm filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
119
  checkpoints/checkpoint-76000/target.spm filter=lfs diff=lfs merge=lfs -text
120
  checkpoints/checkpoint-78000/source.spm filter=lfs diff=lfs merge=lfs -text
121
  checkpoints/checkpoint-78000/target.spm filter=lfs diff=lfs merge=lfs -text
122
+ checkpoint-48000/source.spm filter=lfs diff=lfs merge=lfs -text
123
+ checkpoint-48000/target.spm filter=lfs diff=lfs merge=lfs -text
124
+ checkpoint-76000/source.spm filter=lfs diff=lfs merge=lfs -text
125
+ checkpoint-76000/target.spm filter=lfs diff=lfs merge=lfs -text
126
+ checkpoint-78000/source.spm filter=lfs diff=lfs merge=lfs -text
127
+ checkpoint-78000/target.spm filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -32,14 +32,14 @@ This model is a fine-tuned version of `brendaogutu/mul-sw-en-translation-phase1`
32
  ## Performance
33
 
34
  ### Test Set (General Translation)
35
- - **BLEU:** 0.1289
36
- - **chrF:** 32.25
37
  - **Improvement over baseline:** +0.0%
38
 
39
  ### Domain Evaluation (Call Transcriptions)
40
  - **Domain BLEU:** 0.0000
41
- - **Domain chrF:** 1.18
42
- - **Domain COMET-QE:** 0.0000
43
 
44
  ## Intended Use
45
 
 
32
  ## Performance
33
 
34
  ### Test Set (General Translation)
35
+ - **BLEU:** 0.1327
36
+ - **chrF:** 32.59
37
  - **Improvement over baseline:** +0.0%
38
 
39
  ### Domain Evaluation (Call Transcriptions)
40
  - **Domain BLEU:** 0.0000
41
+ - **Domain chrF:** 1.12
42
+ - **Domain COMET-QE:** 0.0001
43
 
44
  ## Intended Use
45
 
checkpoint-48000/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "swish",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MarianMTModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "classif_dropout": 0.0,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 512,
13
+ "decoder_attention_heads": 8,
14
+ "decoder_ffn_dim": 2048,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 6,
17
+ "decoder_start_token_id": 64171,
18
+ "decoder_vocab_size": 64172,
19
+ "dropout": 0.1,
20
+ "dtype": "float32",
21
+ "encoder_attention_heads": 8,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 0,
26
+ "extra_pos_embeddings": 64172,
27
+ "forced_eos_token_id": 0,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_length": null,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "marian",
43
+ "normalize_before": false,
44
+ "normalize_embedding": false,
45
+ "num_beams": null,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 64171,
48
+ "scale_embedding": true,
49
+ "share_encoder_decoder_embeddings": true,
50
+ "static_position_embeddings": true,
51
+ "transformers_version": "4.57.1",
52
+ "use_cache": true,
53
+ "vocab_size": 64172
54
+ }
checkpoint-48000/generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 64171
5
+ ]
6
+ ],
7
+ "decoder_start_token_id": 64171,
8
+ "eos_token_id": [
9
+ 0
10
+ ],
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 64171,
15
+ "renormalize_logits": true,
16
+ "transformers_version": "4.57.1"
17
+ }
checkpoint-48000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb33b01fd0b2b8140f991e1eba97d767518f0915a957e9b4d607b5fab5eff92
3
+ size 308263984
checkpoint-48000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68b0d8243790ae0fe82f756e5d2292f604545b2ff25f23ca7d041bfaaa1e879
3
+ size 616171979
checkpoint-48000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24af04b3d6ee8244789634414b2afc88b68b21ee8f88783742128c981d80e0b
3
+ size 14645
checkpoint-48000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e813dad333d919afed5366be369784bf51f322710d5a555473f0df56b6f2cdbe
3
+ size 1383
checkpoint-48000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833d72c7e9ff233b15c73ddf470fdf94935810f3140ef1d313da474608626a7f
3
+ size 1465
checkpoint-48000/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
3
+ size 706917
checkpoint-48000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-48000/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
3
+ size 791194
checkpoint-48000/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
+ "64171": {
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
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "mul",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-48000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-48000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d57bc67b52fab2e986e6601c38187c6c1f5438f07426ccb4a39e1f5364676b
3
+ size 5969
checkpoint-48000/training_metrics_snapshot.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-48000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-76000/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "swish",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MarianMTModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "classif_dropout": 0.0,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 512,
13
+ "decoder_attention_heads": 8,
14
+ "decoder_ffn_dim": 2048,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 6,
17
+ "decoder_start_token_id": 64171,
18
+ "decoder_vocab_size": 64172,
19
+ "dropout": 0.1,
20
+ "dtype": "float32",
21
+ "encoder_attention_heads": 8,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 0,
26
+ "extra_pos_embeddings": 64172,
27
+ "forced_eos_token_id": 0,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_length": null,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "marian",
43
+ "normalize_before": false,
44
+ "normalize_embedding": false,
45
+ "num_beams": null,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 64171,
48
+ "scale_embedding": true,
49
+ "share_encoder_decoder_embeddings": true,
50
+ "static_position_embeddings": true,
51
+ "transformers_version": "4.57.1",
52
+ "use_cache": true,
53
+ "vocab_size": 64172
54
+ }
checkpoint-76000/generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 64171
5
+ ]
6
+ ],
7
+ "decoder_start_token_id": 64171,
8
+ "eos_token_id": [
9
+ 0
10
+ ],
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 64171,
15
+ "renormalize_logits": true,
16
+ "transformers_version": "4.57.1"
17
+ }
checkpoint-76000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb90f6d89f560989280d57a17764709507e2d286c09a231754dd5e8e76df373
3
+ size 308263984
checkpoint-76000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444cdacea59ee583007428fbc152b1f29ac7967ddcfe6f4b8e469ca103d98ab7
3
+ size 616171979
checkpoint-76000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee069f90c34f2379c2b3c6d7ae77f9b45b3e87f12e190c9117544447e3710878
3
+ size 14645
checkpoint-76000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3481e6ddaacd5f6e9a82f1204b321f872d3bb9c3976477b0b5d1806ba86e30f2
3
+ size 1383
checkpoint-76000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610e93d4093cc2d2317a65f27e42bc40e0736f9a3caa2c5d1ba80c02dd0eda62
3
+ size 1465
checkpoint-76000/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
3
+ size 706917
checkpoint-76000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-76000/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
3
+ size 791194
checkpoint-76000/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
+ "64171": {
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
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "mul",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-76000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-76000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d57bc67b52fab2e986e6601c38187c6c1f5438f07426ccb4a39e1f5364676b
3
+ size 5969
checkpoint-76000/training_metrics_snapshot.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-76000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-78000/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "swish",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MarianMTModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "classif_dropout": 0.0,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 512,
13
+ "decoder_attention_heads": 8,
14
+ "decoder_ffn_dim": 2048,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 6,
17
+ "decoder_start_token_id": 64171,
18
+ "decoder_vocab_size": 64172,
19
+ "dropout": 0.1,
20
+ "dtype": "float32",
21
+ "encoder_attention_heads": 8,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 0,
26
+ "extra_pos_embeddings": 64172,
27
+ "forced_eos_token_id": 0,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_length": null,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "marian",
43
+ "normalize_before": false,
44
+ "normalize_embedding": false,
45
+ "num_beams": null,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 64171,
48
+ "scale_embedding": true,
49
+ "share_encoder_decoder_embeddings": true,
50
+ "static_position_embeddings": true,
51
+ "transformers_version": "4.57.1",
52
+ "use_cache": true,
53
+ "vocab_size": 64172
54
+ }
checkpoint-78000/generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 64171
5
+ ]
6
+ ],
7
+ "decoder_start_token_id": 64171,
8
+ "eos_token_id": [
9
+ 0
10
+ ],
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 64171,
15
+ "renormalize_logits": true,
16
+ "transformers_version": "4.57.1"
17
+ }
checkpoint-78000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640f79f4411d6121292f934aa9de91eb972c4188e0162c8eb3c46b80bfefd577
3
+ size 308263984
checkpoint-78000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff0726be2377af46f1196a2fff799e3f5034ec8e790943a931798d18ee3981d
3
+ size 616171979
checkpoint-78000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d025db7a5cc057439a79b47d21c1f59d8a4eebb6b080f085e1f5e745389efe
3
+ size 14645
checkpoint-78000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2b006771893674adf04ed4ce37cedcfbc819f3454202741dd508da76be01a0
3
+ size 1383
checkpoint-78000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3876a5862eda1457b4c6b7f858b4f699484c85c15c81773fa469ad13f9235a69
3
+ size 1465
checkpoint-78000/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
3
+ size 706917
checkpoint-78000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-78000/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
3
+ size 791194
checkpoint-78000/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
+ "64171": {
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
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "mul",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "eng",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
checkpoint-78000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-78000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d57bc67b52fab2e986e6601c38187c6c1f5438f07426ccb4a39e1f5364676b
3
+ size 5969
checkpoint-78000/training_metrics_snapshot.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-78000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
logs/events.out.tfevents.1763880503.558d7902982f.33610.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e14710a8bfdc1b34a9e124c387b6afbdc458e81ba11339b46a44eacf18cdc77
3
- size 60267
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:877da18a588e9c8090cd9a7c12e34fcc2cb35a635bdaebe4218d09f8b720c34c
3
+ size 357772
logs/events.out.tfevents.1763904673.558d7902982f.33610.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a359afe2bcbd4cf6d63c6e3a5f28a08e7ba22e13fff3830f7c616fc7fd0e3f0
3
+ size 529
logs/events.out.tfevents.1763904694.558d7902982f.33610.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6ac21245cd1b3c1a10ea2a003f88a15c4f02044bcf269264c9ffa6c825f903
3
+ size 1776