Hugging Face's logo

MarineLives
/
mBert-finetuned-yiddish-experiment-3

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Addaci commited on
Commit
90e0c88
·
verified ·
1 Parent(s): 26472aa

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 +98 -5
  2. checkpoint-100/config.json +31 -0
  3. checkpoint-100/generation_config.json +5 -0
  4. checkpoint-100/model.safetensors +3 -0
  5. checkpoint-100/optimizer.pt +3 -0
  6. checkpoint-100/rng_state.pth +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/special_tokens_map.json +7 -0
  9. checkpoint-100/tokenizer.json +0 -0
  10. checkpoint-100/tokenizer_config.json +56 -0
  11. checkpoint-100/trainer_state.json +48 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. checkpoint-100/vocab.txt +0 -0
  14. checkpoint-1000/config.json +31 -0
  15. checkpoint-1000/generation_config.json +5 -0
  16. checkpoint-1000/model.safetensors +3 -0
  17. checkpoint-1000/optimizer.pt +3 -0
  18. checkpoint-1000/rng_state.pth +3 -0
  19. checkpoint-1000/scheduler.pt +3 -0
  20. checkpoint-1000/special_tokens_map.json +7 -0
  21. checkpoint-1000/tokenizer.json +0 -0
  22. checkpoint-1000/tokenizer_config.json +56 -0
  23. checkpoint-1000/trainer_state.json +183 -0
  24. checkpoint-1000/training_args.bin +3 -0
  25. checkpoint-1000/vocab.txt +0 -0
  26. checkpoint-1060/config.json +31 -0
  27. checkpoint-1060/generation_config.json +5 -0
  28. checkpoint-1060/model.safetensors +3 -0
  29. checkpoint-1060/optimizer.pt +3 -0
  30. checkpoint-1060/rng_state.pth +3 -0
  31. checkpoint-1060/scheduler.pt +3 -0
  32. checkpoint-1060/special_tokens_map.json +7 -0
  33. checkpoint-1060/tokenizer.json +0 -0
  34. checkpoint-1060/tokenizer_config.json +56 -0
  35. checkpoint-1060/trainer_state.json +143 -0
  36. checkpoint-1060/training_args.bin +3 -0
  37. checkpoint-1060/vocab.txt +0 -0
  38. checkpoint-1100/config.json +31 -0
  39. checkpoint-1100/generation_config.json +5 -0
  40. checkpoint-1100/model.safetensors +3 -0
  41. checkpoint-1100/optimizer.pt +3 -0
  42. checkpoint-1100/rng_state.pth +3 -0
  43. checkpoint-1100/scheduler.pt +3 -0
  44. checkpoint-1100/special_tokens_map.json +7 -0
  45. checkpoint-1100/tokenizer.json +0 -0
  46. checkpoint-1100/tokenizer_config.json +56 -0
  47. checkpoint-1100/trainer_state.json +198 -0
  48. checkpoint-1100/training_args.bin +3 -0
  49. checkpoint-1100/vocab.txt +0 -0
  50. checkpoint-1200/config.json +31 -0
README.md CHANGED
@@ -1,7 +1,100 @@
1
  ---
 
2
  license: apache-2.0
3
- language:
4
- - yi
5
- base_model:
6
- - google-bert/bert-base-multilingual-cased
7
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: transformers
3
  license: apache-2.0
4
+ base_model: bert-base-multilingual-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: bert-base-multilingual-cased-finetuned-yiddish-experiment-3
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # bert-base-multilingual-cased-finetuned-yiddish-experiment-3
16
+
17
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.4254
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-06
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 300
45
+ - num_epochs: 10
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:----:|:---------------:|
51
+ | 11.143 | 0.2364 | 100 | 7.6591 |
52
+ | 4.1737 | 0.4728 | 200 | 2.2642 |
53
+ | 2.0579 | 0.7092 | 300 | 1.7710 |
54
+ | 1.6963 | 0.9456 | 400 | 1.6712 |
55
+ | 1.5705 | 1.1820 | 500 | 1.6379 |
56
+ | 1.5353 | 1.4184 | 600 | 1.6003 |
57
+ | 1.5213 | 1.6548 | 700 | 1.5273 |
58
+ | 1.4387 | 1.8913 | 800 | 1.5415 |
59
+ | 1.3973 | 2.1277 | 900 | 1.5530 |
60
+ | 1.4266 | 2.3641 | 1000 | 1.5328 |
61
+ | 1.3365 | 2.6005 | 1100 | 1.5154 |
62
+ | 1.4423 | 2.8369 | 1200 | 1.4662 |
63
+ | 1.3948 | 3.0733 | 1300 | 1.5041 |
64
+ | 1.3244 | 3.3097 | 1400 | 1.4530 |
65
+ | 1.3645 | 3.5461 | 1500 | 1.4656 |
66
+ | 1.329 | 3.7825 | 1600 | 1.4542 |
67
+ | 1.3326 | 4.0189 | 1700 | 1.5293 |
68
+ | 1.2768 | 4.2553 | 1800 | 1.4575 |
69
+ | 1.3125 | 4.4917 | 1900 | 1.4638 |
70
+ | 1.2925 | 4.7281 | 2000 | 1.4867 |
71
+ | 1.281 | 4.9645 | 2100 | 1.4827 |
72
+ | 1.2966 | 5.2009 | 2200 | 1.4359 |
73
+ | 1.28 | 5.4374 | 2300 | 1.4761 |
74
+ | 1.2436 | 5.6738 | 2400 | 1.5006 |
75
+ | 1.2787 | 5.9102 | 2500 | 1.4511 |
76
+ | 1.2344 | 6.1466 | 2600 | 1.4430 |
77
+ | 1.199 | 6.3830 | 2700 | 1.4254 |
78
+ | 1.2899 | 6.6194 | 2800 | 1.4339 |
79
+ | 1.2637 | 6.8558 | 2900 | 1.4609 |
80
+ | 1.2186 | 7.0922 | 3000 | 1.4300 |
81
+ | 1.181 | 7.3286 | 3100 | 1.4407 |
82
+ | 1.2815 | 7.5650 | 3200 | 1.4471 |
83
+ | 1.2161 | 7.8014 | 3300 | 1.4413 |
84
+ | 1.1562 | 8.0378 | 3400 | 1.4695 |
85
+ | 1.1668 | 8.2742 | 3500 | 1.4940 |
86
+ | 1.2557 | 8.5106 | 3600 | 1.4430 |
87
+ | 1.1985 | 8.7470 | 3700 | 1.4562 |
88
+ | 1.2051 | 8.9835 | 3800 | 1.4412 |
89
+ | 1.1588 | 9.2199 | 3900 | 1.4421 |
90
+ | 1.2002 | 9.4563 | 4000 | 1.4477 |
91
+ | 1.2339 | 9.6927 | 4100 | 1.4573 |
92
+ | 1.1918 | 9.9291 | 4200 | 1.4463 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.47.0
98
+ - Pytorch 2.5.1+cu121
99
+ - Datasets 3.1.0
100
+ - Tokenizers 0.21.0
checkpoint-100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.47.0"
5
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619f2d38c080eeb4c0d4e28b0283740927ef788c75713f550e7d4f328813a57b
3
+ size 711921812
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5cfdc5ffa9045d9548ae7ab0fe7738464722ca5b5851c517629798ec2e6551
3
+ size 1423965114
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e56e872d5c43044cc0bbd7ce8db0be7422d3a18e852a63b7e60ce261ebe49b
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373a12f32010632b7a8c57a48ae89c9348649659a96f10493f146583a0e25742
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 7.659108638763428,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-100",
4
+ "epoch": 0.2364066193853428,
5
+ "eval_steps": 100,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2364066193853428,
13
+ "grad_norm": 28.178190231323242,
14
+ "learning_rate": 1.6666666666666667e-06,
15
+ "loss": 11.143,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.2364066193853428,
20
+ "eval_loss": 7.659108638763428,
21
+ "eval_runtime": 0.809,
22
+ "eval_samples_per_second": 260.829,
23
+ "eval_steps_per_second": 65.516,
24
+ "step": 100
25
+ }
26
+ ],
27
+ "logging_steps": 100,
28
+ "max_steps": 4230,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 10,
31
+ "save_steps": 100,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": false
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 13173914880000.0,
45
+ "train_batch_size": 4,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb4a2e10ec0d433a2c1cbe100f4b7b8ddffbf0b7f7be8cb0de207e1d689716
3
+ size 5496
checkpoint-100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.47.0"
5
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21852301d2885847254f3ddc161c45bcc30cdaebd3acfd8f3fde668a58125ae
3
+ size 711921812
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c12fa7767aa9d3497ffebdf77fc0669b9373adecf11f3ac8b1e732af5f385fe
3
+ size 1423965114
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6eacc054a23e1a698e7c258a58f0e80026bbd15fbe76aae1f30aee5abfe7b9
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb73752446a033a44e4f3a15c395c90cd34c0a6799d073fe465a56409455ae2
3
+ size 1064
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.52731454372406,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-700",
4
+ "epoch": 2.3640661938534278,
5
+ "eval_steps": 100,
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": 0.2364066193853428,
13
+ "grad_norm": 28.178190231323242,
14
+ "learning_rate": 1.6666666666666667e-06,
15
+ "loss": 11.143,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.2364066193853428,
20
+ "eval_loss": 7.659108638763428,
21
+ "eval_runtime": 0.809,
22
+ "eval_samples_per_second": 260.829,
23
+ "eval_steps_per_second": 65.516,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.4728132387706856,
28
+ "grad_norm": 15.27036190032959,
29
+ "learning_rate": 3.3333333333333333e-06,
30
+ "loss": 4.1737,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.4728132387706856,
35
+ "eval_loss": 2.2642054557800293,
36
+ "eval_runtime": 0.8681,
37
+ "eval_samples_per_second": 243.069,
38
+ "eval_steps_per_second": 61.055,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 0.7092198581560284,
43
+ "grad_norm": 13.071714401245117,
44
+ "learning_rate": 5e-06,
45
+ "loss": 2.0579,
46
+ "step": 300
47
+ },
48
+ {
49
+ "epoch": 0.7092198581560284,
50
+ "eval_loss": 1.7709782123565674,
51
+ "eval_runtime": 0.8603,
52
+ "eval_samples_per_second": 245.25,
53
+ "eval_steps_per_second": 61.603,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 0.9456264775413712,
58
+ "grad_norm": 8.75770092010498,
59
+ "learning_rate": 4.8727735368956745e-06,
60
+ "loss": 1.6963,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 0.9456264775413712,
65
+ "eval_loss": 1.671216607093811,
66
+ "eval_runtime": 0.9312,
67
+ "eval_samples_per_second": 226.587,
68
+ "eval_steps_per_second": 56.915,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 1.1820330969267139,
73
+ "grad_norm": 11.299208641052246,
74
+ "learning_rate": 4.745547073791349e-06,
75
+ "loss": 1.5705,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 1.1820330969267139,
80
+ "eval_loss": 1.6379029750823975,
81
+ "eval_runtime": 0.872,
82
+ "eval_samples_per_second": 241.979,
83
+ "eval_steps_per_second": 60.782,
84
+ "step": 500
85
+ },
86
+ {
87
+ "epoch": 1.4184397163120568,
88
+ "grad_norm": 7.146368980407715,
89
+ "learning_rate": 4.618320610687023e-06,
90
+ "loss": 1.5353,
91
+ "step": 600
92
+ },
93
+ {
94
+ "epoch": 1.4184397163120568,
95
+ "eval_loss": 1.600274682044983,
96
+ "eval_runtime": 0.9755,
97
+ "eval_samples_per_second": 216.307,
98
+ "eval_steps_per_second": 54.333,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 1.6548463356973995,
103
+ "grad_norm": 7.896175861358643,
104
+ "learning_rate": 4.491094147582698e-06,
105
+ "loss": 1.5213,
106
+ "step": 700
107
+ },
108
+ {
109
+ "epoch": 1.6548463356973995,
110
+ "eval_loss": 1.52731454372406,
111
+ "eval_runtime": 0.9375,
112
+ "eval_samples_per_second": 225.075,
113
+ "eval_steps_per_second": 56.535,
114
+ "step": 700
115
+ },
116
+ {
117
+ "epoch": 1.8912529550827424,
118
+ "grad_norm": 10.965773582458496,
119
+ "learning_rate": 4.363867684478372e-06,
120
+ "loss": 1.4387,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 1.8912529550827424,
125
+ "eval_loss": 1.5414769649505615,
126
+ "eval_runtime": 0.8682,
127
+ "eval_samples_per_second": 243.03,
128
+ "eval_steps_per_second": 61.045,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 2.127659574468085,
133
+ "grad_norm": 10.384049415588379,
134
+ "learning_rate": 4.236641221374046e-06,
135
+ "loss": 1.3973,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 2.127659574468085,
140
+ "eval_loss": 1.5529794692993164,
141
+ "eval_runtime": 0.9033,
142
+ "eval_samples_per_second": 233.6,
143
+ "eval_steps_per_second": 58.677,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 2.3640661938534278,
148
+ "grad_norm": 5.56968879699707,
149
+ "learning_rate": 4.10941475826972e-06,
150
+ "loss": 1.4266,
151
+ "step": 1000
152
+ },
153
+ {
154
+ "epoch": 2.3640661938534278,
155
+ "eval_loss": 1.5328062772750854,
156
+ "eval_runtime": 0.961,
157
+ "eval_samples_per_second": 219.562,
158
+ "eval_steps_per_second": 55.151,
159
+ "step": 1000
160
+ }
161
+ ],
162
+ "logging_steps": 100,
163
+ "max_steps": 4230,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 10,
166
+ "save_steps": 100,
167
+ "stateful_callbacks": {
168
+ "TrainerControl": {
169
+ "args": {
170
+ "should_epoch_stop": false,
171
+ "should_evaluate": false,
172
+ "should_log": false,
173
+ "should_save": true,
174
+ "should_training_stop": false
175
+ },
176
+ "attributes": {}
177
+ }
178
+ },
179
+ "total_flos": 131739148800000.0,
180
+ "train_batch_size": 4,
181
+ "trial_name": null,
182
+ "trial_params": null
183
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb4a2e10ec0d433a2c1cbe100f4b7b8ddffbf0b7f7be8cb0de207e1d689716
3
+ size 5496
checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1060/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-1060/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.47.0"
5
+ }
checkpoint-1060/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38262802145173a78055ee0fe481b395359609c003982d564f96cbcfbc1a2ffc
3
+ size 711921812
checkpoint-1060/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86804f3ec3b8498e476c023d6d7ed146f16c18627c43b43fd29274df11da2c33
3
+ size 1423965114
checkpoint-1060/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3955b51e6aa1c428313cf7f041e204f9c412c4d49b0023ca0016644225562e6
3
+ size 14244
checkpoint-1060/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2351b59295abd51978a8c66c7caf778394a264908afa63f91f830e25fe080da1
3
+ size 1064
checkpoint-1060/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-1060/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1060/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-1060/trainer_state.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.746055543422699,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-1060",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1060,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4716981132075472,
13
+ "grad_norm": 59.220130920410156,
14
+ "learning_rate": 1.6666666666666667e-06,
15
+ "loss": 12.7288,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.9433962264150944,
20
+ "grad_norm": 5.840357303619385,
21
+ "learning_rate": 3.3333333333333333e-06,
22
+ "loss": 2.3607,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 1.0444412231445312,
28
+ "eval_runtime": 1.4447,
29
+ "eval_samples_per_second": 146.047,
30
+ "eval_steps_per_second": 18.688,
31
+ "step": 212
32
+ },
33
+ {
34
+ "epoch": 1.4150943396226414,
35
+ "grad_norm": 4.266133785247803,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.9508,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 1.8867924528301887,
42
+ "grad_norm": 5.5207600593566895,
43
+ "learning_rate": 4.577702702702703e-06,
44
+ "loss": 0.8155,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 0.8413578867912292,
50
+ "eval_runtime": 1.5393,
51
+ "eval_samples_per_second": 137.077,
52
+ "eval_steps_per_second": 17.541,
53
+ "step": 424
54
+ },
55
+ {
56
+ "epoch": 2.358490566037736,
57
+ "grad_norm": 3.453446626663208,
58
+ "learning_rate": 4.155405405405405e-06,
59
+ "loss": 0.7593,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 2.830188679245283,
64
+ "grad_norm": 4.256667613983154,
65
+ "learning_rate": 3.733108108108108e-06,
66
+ "loss": 0.7368,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 3.0,
71
+ "eval_loss": 0.7711948752403259,
72
+ "eval_runtime": 1.5544,
73
+ "eval_samples_per_second": 135.739,
74
+ "eval_steps_per_second": 17.369,
75
+ "step": 636
76
+ },
77
+ {
78
+ "epoch": 3.30188679245283,
79
+ "grad_norm": 3.4198522567749023,
80
+ "learning_rate": 3.310810810810811e-06,
81
+ "loss": 0.7175,
82
+ "step": 700
83
+ },
84
+ {
85
+ "epoch": 3.7735849056603774,
86
+ "grad_norm": 3.9418258666992188,
87
+ "learning_rate": 2.888513513513514e-06,
88
+ "loss": 0.7147,
89
+ "step": 800
90
+ },
91
+ {
92
+ "epoch": 4.0,
93
+ "eval_loss": 0.7569031715393066,
94
+ "eval_runtime": 1.5508,
95
+ "eval_samples_per_second": 136.058,
96
+ "eval_steps_per_second": 17.41,
97
+ "step": 848
98
+ },
99
+ {
100
+ "epoch": 4.245283018867925,
101
+ "grad_norm": 3.400341749191284,
102
+ "learning_rate": 2.4662162162162163e-06,
103
+ "loss": 0.6938,
104
+ "step": 900
105
+ },
106
+ {
107
+ "epoch": 4.716981132075472,
108
+ "grad_norm": 4.095581531524658,
109
+ "learning_rate": 2.043918918918919e-06,
110
+ "loss": 0.692,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 5.0,
115
+ "eval_loss": 0.746055543422699,
116
+ "eval_runtime": 1.5614,
117
+ "eval_samples_per_second": 135.133,
118
+ "eval_steps_per_second": 17.292,
119
+ "step": 1060
120
+ }
121
+ ],
122
+ "logging_steps": 100,
123
+ "max_steps": 1484,
124
+ "num_input_tokens_seen": 0,
125
+ "num_train_epochs": 7,
126
+ "save_steps": 500,
127
+ "stateful_callbacks": {
128
+ "TrainerControl": {
129
+ "args": {
130
+ "should_epoch_stop": false,
131
+ "should_evaluate": false,
132
+ "should_log": false,
133
+ "should_save": true,
134
+ "should_training_stop": false
135
+ },
136
+ "attributes": {}
137
+ }
138
+ },
139
+ "total_flos": 557256599424000.0,
140
+ "train_batch_size": 8,
141
+ "trial_name": null,
142
+ "trial_params": null
143
+ }
checkpoint-1060/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7deb4e1c30b4f93c46b58763b48f9495a07643b3cf2d9b9cc86b10c37f0085
3
+ size 5368
checkpoint-1060/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-1100/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.47.0"
5
+ }
checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65cb507868b2ba475692b28d4988f12f59771abd0a74c46acf83373484e762df
3
+ size 711921812
checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589a0be06395d420ab9df3bee0de83a1068ad61bdedae8cc615f640ce6dad4e2
3
+ size 1423965114
checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de171c08c377eb4f4f598d21ac913fd18285eaec46ad05d13c826d1abe7c847
3
+ size 14244
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4484441034ebe082476fc36576c3a97a217e5d79f53aef00710ad7d51e8a480
3
+ size 1064
checkpoint-1100/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5154240131378174,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-1100",
4
+ "epoch": 2.6004728132387704,
5
+ "eval_steps": 100,
6
+ "global_step": 1100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2364066193853428,
13
+ "grad_norm": 28.178190231323242,
14
+ "learning_rate": 1.6666666666666667e-06,
15
+ "loss": 11.143,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.2364066193853428,
20
+ "eval_loss": 7.659108638763428,
21
+ "eval_runtime": 0.809,
22
+ "eval_samples_per_second": 260.829,
23
+ "eval_steps_per_second": 65.516,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.4728132387706856,
28
+ "grad_norm": 15.27036190032959,
29
+ "learning_rate": 3.3333333333333333e-06,
30
+ "loss": 4.1737,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.4728132387706856,
35
+ "eval_loss": 2.2642054557800293,
36
+ "eval_runtime": 0.8681,
37
+ "eval_samples_per_second": 243.069,
38
+ "eval_steps_per_second": 61.055,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 0.7092198581560284,
43
+ "grad_norm": 13.071714401245117,
44
+ "learning_rate": 5e-06,
45
+ "loss": 2.0579,
46
+ "step": 300
47
+ },
48
+ {
49
+ "epoch": 0.7092198581560284,
50
+ "eval_loss": 1.7709782123565674,
51
+ "eval_runtime": 0.8603,
52
+ "eval_samples_per_second": 245.25,
53
+ "eval_steps_per_second": 61.603,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 0.9456264775413712,
58
+ "grad_norm": 8.75770092010498,
59
+ "learning_rate": 4.8727735368956745e-06,
60
+ "loss": 1.6963,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 0.9456264775413712,
65
+ "eval_loss": 1.671216607093811,
66
+ "eval_runtime": 0.9312,
67
+ "eval_samples_per_second": 226.587,
68
+ "eval_steps_per_second": 56.915,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 1.1820330969267139,
73
+ "grad_norm": 11.299208641052246,
74
+ "learning_rate": 4.745547073791349e-06,
75
+ "loss": 1.5705,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 1.1820330969267139,
80
+ "eval_loss": 1.6379029750823975,
81
+ "eval_runtime": 0.872,
82
+ "eval_samples_per_second": 241.979,
83
+ "eval_steps_per_second": 60.782,
84
+ "step": 500
85
+ },
86
+ {
87
+ "epoch": 1.4184397163120568,
88
+ "grad_norm": 7.146368980407715,
89
+ "learning_rate": 4.618320610687023e-06,
90
+ "loss": 1.5353,
91
+ "step": 600
92
+ },
93
+ {
94
+ "epoch": 1.4184397163120568,
95
+ "eval_loss": 1.600274682044983,
96
+ "eval_runtime": 0.9755,
97
+ "eval_samples_per_second": 216.307,
98
+ "eval_steps_per_second": 54.333,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 1.6548463356973995,
103
+ "grad_norm": 7.896175861358643,
104
+ "learning_rate": 4.491094147582698e-06,
105
+ "loss": 1.5213,
106
+ "step": 700
107
+ },
108
+ {
109
+ "epoch": 1.6548463356973995,
110
+ "eval_loss": 1.52731454372406,
111
+ "eval_runtime": 0.9375,
112
+ "eval_samples_per_second": 225.075,
113
+ "eval_steps_per_second": 56.535,
114
+ "step": 700
115
+ },
116
+ {
117
+ "epoch": 1.8912529550827424,
118
+ "grad_norm": 10.965773582458496,
119
+ "learning_rate": 4.363867684478372e-06,
120
+ "loss": 1.4387,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 1.8912529550827424,
125
+ "eval_loss": 1.5414769649505615,
126
+ "eval_runtime": 0.8682,
127
+ "eval_samples_per_second": 243.03,
128
+ "eval_steps_per_second": 61.045,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 2.127659574468085,
133
+ "grad_norm": 10.384049415588379,
134
+ "learning_rate": 4.236641221374046e-06,
135
+ "loss": 1.3973,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 2.127659574468085,
140
+ "eval_loss": 1.5529794692993164,
141
+ "eval_runtime": 0.9033,
142
+ "eval_samples_per_second": 233.6,
143
+ "eval_steps_per_second": 58.677,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 2.3640661938534278,
148
+ "grad_norm": 5.56968879699707,
149
+ "learning_rate": 4.10941475826972e-06,
150
+ "loss": 1.4266,
151
+ "step": 1000
152
+ },
153
+ {
154
+ "epoch": 2.3640661938534278,
155
+ "eval_loss": 1.5328062772750854,
156
+ "eval_runtime": 0.961,
157
+ "eval_samples_per_second": 219.562,
158
+ "eval_steps_per_second": 55.151,
159
+ "step": 1000
160
+ },
161
+ {
162
+ "epoch": 2.6004728132387704,
163
+ "grad_norm": 10.164349555969238,
164
+ "learning_rate": 3.982188295165394e-06,
165
+ "loss": 1.3365,
166
+ "step": 1100
167
+ },
168
+ {
169
+ "epoch": 2.6004728132387704,
170
+ "eval_loss": 1.5154240131378174,
171
+ "eval_runtime": 0.8705,
172
+ "eval_samples_per_second": 242.391,
173
+ "eval_steps_per_second": 60.885,
174
+ "step": 1100
175
+ }
176
+ ],
177
+ "logging_steps": 100,
178
+ "max_steps": 4230,
179
+ "num_input_tokens_seen": 0,
180
+ "num_train_epochs": 10,
181
+ "save_steps": 100,
182
+ "stateful_callbacks": {
183
+ "TrainerControl": {
184
+ "args": {
185
+ "should_epoch_stop": false,
186
+ "should_evaluate": false,
187
+ "should_log": false,
188
+ "should_save": true,
189
+ "should_training_stop": false
190
+ },
191
+ "attributes": {}
192
+ }
193
+ },
194
+ "total_flos": 144913063680000.0,
195
+ "train_batch_size": 4,
196
+ "trial_name": null,
197
+ "trial_params": null
198
+ }
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb4a2e10ec0d433a2c1cbe100f4b7b8ddffbf0b7f7be8cb0de207e1d689716
3
+ size 5496
checkpoint-1100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.47.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }