badokorach commited on
Commit
8c0dd18
1 Parent(s): 19f2b32

Training in progress epoch 0

Browse files
Files changed (5) hide show
  1. README.md +6 -26
  2. config.json +1 -2
  3. tf_model.h5 +1 -1
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +0 -7
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: badokorach/roberta-base-squad2-agric-060124
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,17 +13,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # badokorach/roberta-base-agric-trans-290124
15
 
16
- This model is a fine-tuned version of [badokorach/roberta-base-squad2-agric-060124](https://huggingface.co/badokorach/roberta-base-squad2-agric-060124) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0007
19
  - Validation Loss: 0.0
20
- - Epoch: 14
21
-
22
- ## Model Performance
23
- The model's performance in various metrics is as follows:
24
-
25
- - Exact Match: 81.60%
26
- - F1 Score: 81.88%
27
 
28
  ## Model description
29
 
@@ -42,28 +36,14 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 2280, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
46
  - training_precision: mixed_float16
47
 
48
  ### Training results
49
 
50
  | Train Loss | Validation Loss | Epoch |
51
  |:----------:|:---------------:|:-----:|
52
- | 0.1894 | 0.0 | 0 |
53
- | 0.0200 | 0.0 | 1 |
54
- | 0.0106 | 0.0 | 2 |
55
- | 0.0094 | 0.0 | 3 |
56
- | 0.0060 | 0.0 | 4 |
57
- | 0.0050 | 0.0 | 5 |
58
- | 0.0048 | 0.0 | 6 |
59
- | 0.0043 | 0.0 | 7 |
60
- | 0.0013 | 0.0 | 8 |
61
- | 0.0013 | 0.0 | 9 |
62
- | 0.0009 | 0.0 | 10 |
63
- | 0.0013 | 0.0 | 11 |
64
- | 0.0008 | 0.0 | 12 |
65
- | 0.0035 | 0.0 | 13 |
66
- | 0.0007 | 0.0 | 14 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: badokorach/xlm-roberta-base-finetuned-mlqa
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # badokorach/roberta-base-agric-trans-290124
15
 
16
+ This model is a fine-tuned version of [badokorach/xlm-roberta-base-finetuned-mlqa](https://huggingface.co/badokorach/xlm-roberta-base-finetuned-mlqa) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 2.5938
19
  - Validation Loss: 0.0
20
+ - Epoch: 0
 
 
 
 
 
 
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 460, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
40
  - training_precision: mixed_float16
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 2.5938 | 0.0 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "badokorach/roberta-base-squad2-agric-060124",
3
  "architectures": [
4
  "XLMRobertaForQuestionAnswering"
5
  ],
@@ -20,7 +20,6 @@
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
- "torch_dtype": "float32",
24
  "transformers_version": "4.35.2",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "badokorach/xlm-roberta-base-finetuned-mlqa",
3
  "architectures": [
4
  "XLMRobertaForQuestionAnswering"
5
  ],
 
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
 
23
  "transformers_version": "4.35.2",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38d1236d10bf5847b818f34b843f1c32edc3c04adca7a561132eb5d1148cd618
3
  size 1110105320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e6a58ab7bead15abe52b79e63d5362fb5f6f62a4201cca844bbd002b805f83
3
  size 1110105320
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a64ee085e5e14dbc9894857e29a8ac501e74d9842aeb174e22474a30360a64
3
- size 17083021
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json CHANGED
@@ -46,16 +46,9 @@
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
49
- "max_length": 384,
50
  "model_max_length": 512,
51
- "pad_to_multiple_of": null,
52
  "pad_token": "<pad>",
53
- "pad_token_type_id": 0,
54
- "padding_side": "right",
55
  "sep_token": "</s>",
56
- "stride": 128,
57
  "tokenizer_class": "XLMRobertaTokenizer",
58
- "truncation_side": "right",
59
- "truncation_strategy": "only_second",
60
  "unk_token": "<unk>"
61
  }
 
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "mask_token": "<mask>",
 
49
  "model_max_length": 512,
 
50
  "pad_token": "<pad>",
 
 
51
  "sep_token": "</s>",
 
52
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
53
  "unk_token": "<unk>"
54
  }