alieddine commited on
Commit
bcf23f1
·
verified ·
1 Parent(s): e0bdb22

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +61 -0
  2. all_results.json +15 -0
  3. checkpoint-1000/config.json +61 -0
  4. checkpoint-1000/generation_config.json +16 -0
  5. checkpoint-1000/model.safetensors +3 -0
  6. checkpoint-1000/optimizer.pt +3 -0
  7. checkpoint-1000/rng_state.pth +3 -0
  8. checkpoint-1000/scheduler.pt +3 -0
  9. checkpoint-1000/source.spm +0 -0
  10. checkpoint-1000/special_tokens_map.json +5 -0
  11. checkpoint-1000/target.spm +0 -0
  12. checkpoint-1000/tokenizer_config.json +38 -0
  13. checkpoint-1000/trainer_state.json +35 -0
  14. checkpoint-1000/training_args.bin +3 -0
  15. checkpoint-1000/vocab.json +0 -0
  16. checkpoint-1500/config.json +61 -0
  17. checkpoint-1500/generation_config.json +16 -0
  18. checkpoint-1500/model.safetensors +3 -0
  19. checkpoint-1500/optimizer.pt +3 -0
  20. checkpoint-1500/rng_state.pth +3 -0
  21. checkpoint-1500/scheduler.pt +3 -0
  22. checkpoint-1500/source.spm +0 -0
  23. checkpoint-1500/special_tokens_map.json +5 -0
  24. checkpoint-1500/target.spm +0 -0
  25. checkpoint-1500/tokenizer_config.json +38 -0
  26. checkpoint-1500/trainer_state.json +42 -0
  27. checkpoint-1500/training_args.bin +3 -0
  28. checkpoint-1500/vocab.json +0 -0
  29. checkpoint-2000/config.json +61 -0
  30. checkpoint-2000/generation_config.json +16 -0
  31. checkpoint-2000/model.safetensors +3 -0
  32. checkpoint-2000/optimizer.pt +3 -0
  33. checkpoint-2000/rng_state.pth +3 -0
  34. checkpoint-2000/scheduler.pt +3 -0
  35. checkpoint-2000/source.spm +0 -0
  36. checkpoint-2000/special_tokens_map.json +5 -0
  37. checkpoint-2000/target.spm +0 -0
  38. checkpoint-2000/tokenizer_config.json +38 -0
  39. checkpoint-2000/trainer_state.json +49 -0
  40. checkpoint-2000/training_args.bin +3 -0
  41. checkpoint-2000/vocab.json +0 -0
  42. checkpoint-2500/config.json +61 -0
  43. checkpoint-2500/generation_config.json +16 -0
  44. checkpoint-2500/model.safetensors +3 -0
  45. checkpoint-2500/optimizer.pt +3 -0
  46. checkpoint-2500/rng_state.pth +3 -0
  47. checkpoint-2500/scheduler.pt +3 -0
  48. checkpoint-2500/source.spm +0 -0
  49. checkpoint-2500/special_tokens_map.json +5 -0
  50. checkpoint-2500/target.spm +0 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ar
4
+ - en
5
+ license: apache-2.0
6
+ base_model: Helsinki-NLP/opus-mt-ar-en
7
+ tags:
8
+ - generated_from_trainer
9
+ metrics:
10
+ - bleu
11
+ model-index:
12
+ - name: opus_1
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_1
20
+
21
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0000
24
+ - Bleu: 0.0
25
+ - Gen Len: 4.7759
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": 0.0,
4
+ "eval_gen_len": 4.7759,
5
+ "eval_loss": 2.7647881779557792e-06,
6
+ "eval_runtime": 134.857,
7
+ "eval_samples": 5510,
8
+ "eval_samples_per_second": 40.858,
9
+ "eval_steps_per_second": 10.218,
10
+ "train_loss": 0.01952261976593809,
11
+ "train_runtime": 337.4673,
12
+ "train_samples": 5510,
13
+ "train_samples_per_second": 48.983,
14
+ "train_steps_per_second": 12.25
15
+ }
checkpoint-1000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ar-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
+ 62833
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": 62833,
26
+ "decoder_vocab_size": 62834,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
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": 62834
61
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62833
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62833,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62833,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.0.dev0"
16
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117d3fd22412b3b60ca685018644c07af891ad8bb73e9df828edd3bf54038048
3
+ size 305518408
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfaa3b315bdf2463c24302d45eea3f65310777a1ea401bc2bcfc0c29d33d85a3
3
+ size 610687610
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d53f870b7f4c68bebc19c8ac3212d4d2f47f06bd17d63e48a1d75c6159fcab
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea60b690083f16b9f09c4f62e6eb61034f348049f77023c57b6b2e46f7f914b
3
+ size 1064
checkpoint-1000/source.spm ADDED
Binary file (917 kB). View file
 
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-1000/target.spm ADDED
Binary file (802 kB). View file
 
checkpoint-1000/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
+ "62833": {
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": "ar",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7256894049346879,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.36,
13
+ "grad_norm": 0.018075617030262947,
14
+ "learning_rate": 4.3952588292210934e-05,
15
+ "loss": 0.1598,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.73,
20
+ "grad_norm": 0.014405773021280766,
21
+ "learning_rate": 3.790517658442187e-05,
22
+ "loss": 0.0001,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 4134,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 3,
30
+ "save_steps": 500,
31
+ "total_flos": 5070983528448.0,
32
+ "train_batch_size": 4,
33
+ "trial_name": null,
34
+ "trial_params": null
35
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f8dbfcd7b24536ad0c909260b785b5237dfcf76eb289c82c05b69e0e17f21f
3
+ size 5048
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ar-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
+ 62833
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": 62833,
26
+ "decoder_vocab_size": 62834,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
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": 62834
61
+ }
checkpoint-1500/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62833
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62833,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62833,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.0.dev0"
16
+ }
checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade38aa5a0050bb702f1984f29a8c2969b38298c0285267de229e9c720c7623d
3
+ size 305518408
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c325411190a13b1290e1aab931ff5319f84c8bd1752ce866b6e5453a86c3e86c
3
+ size 610687610
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1183dd122c36a2d53e93796f3c2d309338f2c4884a4d80a3f1707dcfda4e7300
3
+ size 14244
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da21cb7f8aacc77576f36ede47f1b3463ace4f4e1395211722250cdd26e48e28
3
+ size 1064
checkpoint-1500/source.spm ADDED
Binary file (917 kB). View file
 
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-1500/target.spm ADDED
Binary file (802 kB). View file
 
checkpoint-1500/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
+ "62833": {
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": "ar",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0885341074020318,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.36,
13
+ "grad_norm": 0.018075617030262947,
14
+ "learning_rate": 4.3952588292210934e-05,
15
+ "loss": 0.1598,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.73,
20
+ "grad_norm": 0.014405773021280766,
21
+ "learning_rate": 3.790517658442187e-05,
22
+ "loss": 0.0001,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.09,
27
+ "grad_norm": 0.0018536851275712252,
28
+ "learning_rate": 3.18577648766328e-05,
29
+ "loss": 0.0001,
30
+ "step": 1500
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 4134,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 3,
37
+ "save_steps": 500,
38
+ "total_flos": 7598530363392.0,
39
+ "train_batch_size": 4,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f8dbfcd7b24536ad0c909260b785b5237dfcf76eb289c82c05b69e0e17f21f
3
+ size 5048
checkpoint-1500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ar-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
+ 62833
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": 62833,
26
+ "decoder_vocab_size": 62834,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
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": 62834
61
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62833
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62833,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62833,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.0.dev0"
16
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ae252dd125f62353275fcb2cf991730e8d4093016df754f4a863f7d1ec436d
3
+ size 305518408
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02110c4aab51794e2d83733f09d77830b775aab137633497a09b26d3ed44c4d
3
+ size 610687610
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b497f140733a3c8a4d0f2c02c5b02853642b68bf37f2eca6e43ecddc29478bde
3
+ size 14244
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d84c8d75bdc39d955eb23c56ac15092d3391d367de17bc7a971044cc72961a6
3
+ size 1064
checkpoint-2000/source.spm ADDED
Binary file (917 kB). View file
 
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-2000/target.spm ADDED
Binary file (802 kB). View file
 
checkpoint-2000/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
+ "62833": {
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": "ar",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "en",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.4513788098693758,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.36,
13
+ "grad_norm": 0.018075617030262947,
14
+ "learning_rate": 4.3952588292210934e-05,
15
+ "loss": 0.1598,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.73,
20
+ "grad_norm": 0.014405773021280766,
21
+ "learning_rate": 3.790517658442187e-05,
22
+ "loss": 0.0001,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.09,
27
+ "grad_norm": 0.0018536851275712252,
28
+ "learning_rate": 3.18577648766328e-05,
29
+ "loss": 0.0001,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.45,
34
+ "grad_norm": 0.0023344324436038733,
35
+ "learning_rate": 2.5810353168843737e-05,
36
+ "loss": 0.0,
37
+ "step": 2000
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 4134,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 3,
44
+ "save_steps": 500,
45
+ "total_flos": 10130314493952.0,
46
+ "train_batch_size": 4,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f8dbfcd7b24536ad0c909260b785b5237dfcf76eb289c82c05b69e0e17f21f
3
+ size 5048
checkpoint-2000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ar-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
+ 62833
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": 62833,
26
+ "decoder_vocab_size": 62834,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
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": 62834
61
+ }
checkpoint-2500/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 62833
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 62833,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 62833,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.0.dev0"
16
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716280ba77572de88a30006479a4447308c193e4285e118e4cad74e23eb47a46
3
+ size 305518408
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2140e14651d31ba018edc781f400c5f140ab7a5b7fab806209145d9638866ead
3
+ size 610687610
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4501890e522d5d366a210914693c7bfda4872b10e63152694fe239bb8d897d2c
3
+ size 14244
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f50f2256dfc7ddefea1d1b75bf4201b27d9d4300614bd65ad8210c1053aeaa
3
+ size 1064
checkpoint-2500/source.spm ADDED
Binary file (917 kB). View file
 
checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-2500/target.spm ADDED
Binary file (802 kB). View file