Hugging Face's logo

vargha
/
Hubert-fine-tuned-persian

Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
vargha commited on
Commit
a4c41dd
·
verified ·
1 Parent(s): f3641f2

vargha/Hubert-fine-tuned-persian

Browse files
Files changed (9) hide show
  1. README.md +15 -10
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec26_00-11-42_v-lab/events.out.tfevents.1735159302.v-lab.1505744.0 +3 -0
  5. runs/Dec26_00-13-33_v-lab/events.out.tfevents.1735159413.v-lab.1511684.0 +3 -0
  6. runs/Dec26_00-14-50_v-lab/events.out.tfevents.1735159490.v-lab.1512776.0 +3 -0
  7. runs/Dec26_00-15-30_v-lab/events.out.tfevents.1735159530.v-lab.1513514.0 +3 -0
  8. runs/Dec26_00-15-30_v-lab/events.out.tfevents.1735160656.v-lab.1513514.1 +3 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: apache-2.0
4
  base_model: m3hrdadfi/hubert-base-persian-speech-emotion-recognition
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: Hubert-fine-tuned-persian
9
  results: []
@@ -16,13 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [m3hrdadfi/hubert-base-persian-speech-emotion-recognition](https://huggingface.co/m3hrdadfi/hubert-base-persian-speech-emotion-recognition) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - eval_loss: 0.6998
20
- - eval_accuracy: 0.5442
21
- - eval_runtime: 38.5612
22
- - eval_samples_per_second: 7.624
23
- - eval_steps_per_second: 1.919
24
- - epoch: 2.0
25
- - step: 196
26
 
27
  ## Model description
28
 
@@ -41,16 +38,24 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 0.001
45
  - train_batch_size: 4
46
  - eval_batch_size: 4
47
  - seed: 42
48
- - gradient_accumulation_steps: 3
49
- - total_train_batch_size: 12
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
 
52
  - num_epochs: 3
53
 
 
 
 
 
 
 
 
 
 
54
  ### Framework versions
55
 
56
  - Transformers 4.47.1
 
4
  base_model: m3hrdadfi/hubert-base-persian-speech-emotion-recognition
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
  model-index:
10
  - name: Hubert-fine-tuned-persian
11
  results: []
 
18
 
19
  This model is a fine-tuned version of [m3hrdadfi/hubert-base-persian-speech-emotion-recognition](https://huggingface.co/m3hrdadfi/hubert-base-persian-speech-emotion-recognition) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7682
22
+ - Accuracy: 0.6327
 
 
 
 
 
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
  - train_batch_size: 4
43
  - eval_batch_size: 4
44
  - seed: 42
 
 
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 3
49
 
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.5913 | 1.0 | 294 | 0.6427 | 0.6259 |
55
+ | 1.0411 | 2.0 | 588 | 0.6766 | 0.6190 |
56
+ | 0.615 | 3.0 | 882 | 0.7682 | 0.6327 |
57
+
58
+
59
  ### Framework versions
60
 
61
  - Transformers 4.47.1
config.json CHANGED
@@ -77,7 +77,7 @@
77
  "num_feat_extract_layers": 7,
78
  "num_hidden_layers": 12,
79
  "pad_token_id": 0,
80
- "pooling_mode": "mean",
81
  "problem_type": "single_label_classification",
82
  "torch_dtype": "float32",
83
  "transformers_version": "4.47.1",
 
77
  "num_feat_extract_layers": 7,
78
  "num_hidden_layers": 12,
79
  "pad_token_id": 0,
80
+ "pooling_mode": "max",
81
  "problem_type": "single_label_classification",
82
  "torch_dtype": "float32",
83
  "transformers_version": "4.47.1",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad2eeef8048f6f86d4b69078f47fb4cfd9fd457674ac15d67f62421f7d5b2c3d
3
  size 379881088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b072fe0a2bef88c61cff5a70c1530d9cd7b5594fdbc4f28deebceb286ad54df
3
  size 379881088
runs/Dec26_00-11-42_v-lab/events.out.tfevents.1735159302.v-lab.1505744.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35dbe4c9884afe92936defc0e63fd1064cb4608a5bfa1e8d8ac49ac0b21d023
3
+ size 6173
runs/Dec26_00-13-33_v-lab/events.out.tfevents.1735159413.v-lab.1511684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbdf35e7992c97ed7ab3ed6661ef5afe55c64ef92c3181a5d6d3eaa47acba
3
+ size 6176
runs/Dec26_00-14-50_v-lab/events.out.tfevents.1735159490.v-lab.1512776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76bc7777dd49d398a13e0d46f0d35b2b9a3183bd4d5c2dbeb95561ecdbe36d4
3
+ size 6176
runs/Dec26_00-15-30_v-lab/events.out.tfevents.1735159530.v-lab.1513514.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbf2875d4d26d889634b050766e65b937f1287c34b489e0993304bf30766244
3
+ size 26019
runs/Dec26_00-15-30_v-lab/events.out.tfevents.1735160656.v-lab.1513514.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b262b0afd30ef7b0dd465a33b569b447a70f117281dc315c58f5404f055edd39
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3913eb038e914767cd75bcae957ccf37f72f67d6c37d621a1dcf71592cfcad92
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec4e353f722cb488d6da982372baffab19b7e4fdf158f25212cae869c6cc9a0
3
  size 5368