jimypbr commited on
Commit
3c82dff
1 Parent(s): 00c2a0a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the common_language dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.2773
23
- - Accuracy: 0.7301
24
 
25
  ## Model description
26
 
@@ -42,14 +42,14 @@ The following hyperparameters were used during training:
42
  - learning_rate: 0.0001
43
  - train_batch_size: 1
44
  - eval_batch_size: 4
45
- - seed: 1984
46
  - distributed_type: IPU
47
  - gradient_accumulation_steps: 32
48
  - total_train_batch_size: 128
49
  - total_eval_batch_size: 64
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - lr_scheduler_warmup_ratio: 0.2
53
  - num_epochs: 10.0
54
  - training precision: Mixed Precision
55
 
19
 
20
  This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the common_language dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.3477
23
+ - Accuracy: 0.7317
24
 
25
  ## Model description
26
 
42
  - learning_rate: 0.0001
43
  - train_batch_size: 1
44
  - eval_batch_size: 4
45
+ - seed: 0
46
  - distributed_type: IPU
47
  - gradient_accumulation_steps: 32
48
  - total_train_batch_size: 128
49
  - total_eval_batch_size: 64
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.25
53
  - num_epochs: 10.0
54
  - training precision: Mixed Precision
55