VladS159 commited on
Commit
cc8e962
1 Parent(s): e844966

End of training

Browse files
README.md CHANGED
@@ -6,19 +6,19 @@ tags:
6
  metrics:
7
  - wer
8
  model-index:
9
- - name: whisper_small_ro_VladS_02_13_24_4000_steps
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # whisper_small_ro_VladS_02_13_24_4000_steps
17
 
18
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2095
21
- - Wer: 16.1590
22
 
23
  ## Model description
24
 
@@ -38,9 +38,13 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
 
 
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
@@ -51,14 +55,14 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
- | 0.2447 | 0.66 | 500 | 0.2456 | 22.0322 |
55
- | 0.1137 | 1.31 | 1000 | 0.2053 | 19.1230 |
56
- | 0.101 | 1.97 | 1500 | 0.1894 | 17.4706 |
57
- | 0.0387 | 2.62 | 2000 | 0.1922 | 16.7311 |
58
- | 0.0194 | 3.28 | 2500 | 0.2012 | 16.7006 |
59
- | 0.0204 | 3.93 | 3000 | 0.1956 | 16.2990 |
60
- | 0.0079 | 4.59 | 3500 | 0.2060 | 16.2259 |
61
- | 0.0045 | 5.24 | 4000 | 0.2095 | 16.1590 |
62
 
63
 
64
  ### Framework versions
 
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: Whisper_small_ro_VladS_02_14_24_4000_steps
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # Whisper_small_ro_VladS_02_14_24_4000_steps
17
 
18
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2920
21
+ - Wer: 18.6647
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
  - eval_batch_size: 16
43
  - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 3
46
+ - total_train_batch_size: 96
47
+ - total_eval_batch_size: 48
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 500
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
58
+ | 0.1437 | 3.91 | 500 | 0.2167 | 20.5100 |
59
+ | 0.0268 | 7.81 | 1000 | 0.2202 | 18.6557 |
60
+ | 0.008 | 11.72 | 1500 | 0.2478 | 18.6829 |
61
+ | 0.0037 | 15.62 | 2000 | 0.2644 | 18.6708 |
62
+ | 0.0024 | 19.53 | 2500 | 0.2761 | 18.6405 |
63
+ | 0.0018 | 23.44 | 3000 | 0.2844 | 18.6859 |
64
+ | 0.0016 | 27.34 | 3500 | 0.2900 | 18.6799 |
65
+ | 0.0014 | 31.25 | 4000 | 0.2920 | 18.6647 |
66
 
67
 
68
  ### Framework versions
generation_config.json CHANGED
@@ -260,5 +260,6 @@
260
  "transcribe": 50359,
261
  "translate": 50358
262
  },
263
- "transformers_version": "4.37.2"
 
264
  }
 
260
  "transcribe": 50359,
261
  "translate": 50358
262
  },
263
+ "transformers_version": "4.37.2",
264
+ "use_cache": false
265
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a9880b96fb70d065fef11f49ac435e480a29a664c6ae5c4c8529af683d795d
3
  size 563189936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e32dcb913ae37ca615a273f3d4e41440e3871a1b5ca09999c77d6356e70a52d
3
  size 563189936
runs/Feb14_19-40-58_ubuntu-llama/events.out.tfevents.1707932471.ubuntu-llama.201611.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cff0c700cbd345c5609824509933dfa76a0ed4af0c0cab0b2ffaae88eacfc71
3
- size 11917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6123dfc5cdfbab15fac83230e1b0fb2928a75294b91d0da6f136ae8f43238471
3
+ size 14477