Samandards/uzbek-5k-data
Browse files- README.md +5 -5
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,8 +36,8 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.001
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
|
|
53 |
-
| 0.
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7645
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.001
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.054 | 1.0 | 86 | 0.8908 |
|
53 |
+
| 0.6785 | 2.0 | 172 | 0.7645 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": {
|
4 |
-
"base_model_class": "
|
5 |
-
"parent_library": "
|
6 |
},
|
7 |
-
"base_model_name_or_path":
|
8 |
"bias": "none",
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
@@ -13,13 +13,13 @@
|
|
13 |
"layers_pattern": null,
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
-
"lora_alpha":
|
17 |
"lora_dropout": 0.05,
|
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": [
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": {
|
4 |
+
"base_model_class": "PeftModel",
|
5 |
+
"parent_library": "peft.peft_model"
|
6 |
},
|
7 |
+
"base_model_name_or_path": null,
|
8 |
"bias": "none",
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
|
|
13 |
"layers_pattern": null,
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
+
"lora_alpha": 8,
|
17 |
"lora_dropout": 0.05,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": null,
|
21 |
"peft_type": "LORA",
|
22 |
+
"r": 4,
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
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:dc503d8f32177c5fd85ebef3e2fd033f1843316db0bcadf94b21f0a16894dcbb
|
3 |
+
size 7924808
|
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 sha256:0d9b2f2850856b320102670f687f3b2fe0d3fc81a31e68eea2b73d9d368ba00f
|
3 |
size 5304
|