vnktrmnb commited on
Commit
35e7bdb
1 Parent(s): 3d117f6

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 2.4795
18
- - Train End Logits Accuracy: 0.3625
19
- - Train Start Logits Accuracy: 0.4065
20
- - Validation Loss: 1.8676
21
- - Validation End Logits Accuracy: 0.4746
22
- - Validation Start Logits Accuracy: 0.5254
23
  - Epoch: 0
24
 
25
  ## Model description
@@ -39,14 +39,14 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 21993, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
43
  - training_precision: float32
44
 
45
  ### Training results
46
 
47
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
48
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
49
- | 2.4795 | 0.3625 | 0.4065 | 1.8676 | 0.4746 | 0.5254 | 0 |
50
 
51
 
52
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 5.8944
18
+ - Train End Logits Accuracy: 0.0091
19
+ - Train Start Logits Accuracy: 0.0097
20
+ - Validation Loss: 5.9506
21
+ - Validation End Logits Accuracy: 0.3902
22
+ - Validation Start Logits Accuracy: 0.3902
23
  - Epoch: 0
24
 
25
  ## Model description
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 7331, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
43
  - training_precision: float32
44
 
45
  ### Training results
46
 
47
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
48
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
49
+ | 5.8944 | 0.0091 | 0.0097 | 5.9506 | 0.3902 | 0.3902 | 0 |
50
 
51
 
52
  ### Framework versions
logs/train/events.out.tfevents.1688995158.ed5d106294bd.607.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e92b0453eaae07f6f190874b21f48e3340a7992240c5e06f03e53a5e3bb03f2
3
+ size 78
logs/train/events.out.tfevents.1688995890.ed5d106294bd.607.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1a3a53fde9ef27e7385cd605123b6391431fd0f4ba2633ce5352116c2ac442
3
+ size 78
logs/train/events.out.tfevents.1688996253.ed5d106294bd.10611.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb271a23eb868799d9457d687f19b3b77b71b74e501bfe390086f21679ad4bd
3
+ size 78
logs/train/events.out.tfevents.1688996537.ed5d106294bd.10611.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f85cd96e532554baa7636a9925d41537cf59c40035d2e861fe3478ef53a22d
3
+ size 78
logs/train/events.out.tfevents.1688997101.ed5d106294bd.10611.2.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847f0dd54bfe492522d3bcecd5ad566b1de9e174642c2d12f0c3ae69a9de5dea
3
+ size 78
logs/train/events.out.tfevents.1688999759.ed5d106294bd.16276.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a218eaaf3cc130294434f7978ad5f65b5a4cde22ff577855d32f026e117daf14
3
+ size 2645337
logs/validation/events.out.tfevents.1689008738.ed5d106294bd.16276.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe6c4be9bbaa470b8de13a6e32ceb184c9602ecef291dd7ec36019a6318dbbe
3
+ size 604
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fef9414f3a544d57661b6aee89ae3242333d5d7dc42a7ed39f9364c1dce23656
3
  size 709326800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293f05245acba620d6e5b4ed35815b816541663ee619278173328585fa61d045
3
  size 709326800