End of training
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ model-index:
|
|
24 |
args: default
|
25 |
metrics:
|
26 |
- type: wer
|
27 |
-
value:
|
28 |
name: Wer
|
29 |
---
|
30 |
|
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the miosipof/asr_en dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss:
|
39 |
-
- Wer:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -55,26 +55,38 @@ More information needed
|
|
55 |
### Training hyperparameters
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
-
- learning_rate:
|
59 |
-
- train_batch_size:
|
60 |
-
- eval_batch_size:
|
61 |
- seed: 42
|
62 |
-
- gradient_accumulation_steps:
|
63 |
- total_train_batch_size: 64
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
-
- lr_scheduler_warmup_steps:
|
67 |
-
- training_steps:
|
68 |
- mixed_precision_training: Native AMP
|
69 |
|
70 |
### Training results
|
71 |
|
72 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
73 |
-
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
24 |
args: default
|
25 |
metrics:
|
26 |
- type: wer
|
27 |
+
value: 106.7911714770798
|
28 |
name: Wer
|
29 |
---
|
30 |
|
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the miosipof/asr_en dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 3.9473
|
39 |
+
- Wer: 106.7912
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
55 |
### Training hyperparameters
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 1e-05
|
59 |
+
- train_batch_size: 32
|
60 |
+
- eval_batch_size: 16
|
61 |
- seed: 42
|
62 |
+
- gradient_accumulation_steps: 2
|
63 |
- total_train_batch_size: 64
|
64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
- lr_scheduler_type: linear
|
66 |
+
- lr_scheduler_warmup_steps: 128
|
67 |
+
- training_steps: 1024
|
68 |
- mixed_precision_training: Native AMP
|
69 |
|
70 |
### Training results
|
71 |
|
72 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
73 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
74 |
+
| 7.4432 | 4.2667 | 64 | 7.9570 | 167.9117 |
|
75 |
+
| 6.9871 | 8.5333 | 128 | 7.0858 | 167.5722 |
|
76 |
+
| 6.1972 | 12.8 | 192 | 6.3333 | 205.2632 |
|
77 |
+
| 5.9006 | 17.0667 | 256 | 6.0843 | 203.5654 |
|
78 |
+
| 5.61 | 21.3333 | 320 | 5.8153 | 168.7606 |
|
79 |
+
| 5.2344 | 25.6 | 384 | 5.4746 | 168.0815 |
|
80 |
+
| 4.8067 | 29.8667 | 448 | 5.0913 | 168.2513 |
|
81 |
+
| 4.3927 | 34.1333 | 512 | 4.7586 | 201.5280 |
|
82 |
+
| 4.1103 | 38.4 | 576 | 4.5158 | 164.5161 |
|
83 |
+
| 3.8975 | 42.6667 | 640 | 4.3460 | 108.4890 |
|
84 |
+
| 3.7471 | 46.9333 | 704 | 4.2178 | 109.1681 |
|
85 |
+
| 3.6146 | 51.2 | 768 | 4.1226 | 108.3192 |
|
86 |
+
| 3.53 | 55.4667 | 832 | 4.0471 | 107.9796 |
|
87 |
+
| 3.4579 | 59.7333 | 896 | 3.9927 | 107.4703 |
|
88 |
+
| 3.4061 | 64.0 | 960 | 3.9594 | 106.9610 |
|
89 |
+
| 3.3577 | 68.2667 | 1024 | 3.9473 | 106.7912 |
|
90 |
|
91 |
|
92 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -13,18 +13,18 @@
|
|
13 |
"layers_pattern": null,
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
-
"lora_alpha":
|
17 |
"lora_dropout": 0.01,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": null,
|
21 |
"peft_type": "LORA",
|
22 |
-
"r":
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
|
|
13 |
"layers_pattern": null,
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
"lora_dropout": 0.01,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": null,
|
21 |
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"v_proj"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aeb882533eba03b542ed0bb46eb9db32b7dc782bd6fee502cc8a8fc6d583cf9
|
3 |
+
size 18915424
|
runs/Sep29_17-51-50_fd95e0b5707e/events.out.tfevents.1727632327.fd95e0b5707e
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08c07be74b2b9347e57ab046e69868c46923f5f70d0acad1ba266d8a6057649e
|
3 |
+
size 9734
|
runs/Sep29_20-39-23_fd95e0b5707e/events.out.tfevents.1727642388.fd95e0b5707e
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf26f2074ae09da0a2c8c8c3c4984101bde1cd1b514e6ac1ecfae1ed113f61d
|
3 |
+
size 14637
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23815f753814c6fa06c941b85aa50078574dca65e331b33048cc31379b12fea2
|
3 |
size 5304
|