Training in progress, step 1080
Browse files- README.md +6 -14
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,8 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: facebook/wav2vec2-xls-r-300m
|
| 3 |
license: apache-2.0
|
| 4 |
-
|
| 5 |
-
- wer
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
|
@@ -13,13 +11,11 @@ model-index:
|
|
| 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 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/danakal/xls_300m_french_data/runs/cf8f5rsv)
|
| 17 |
# xls_1b_decoding_fr_decoding_test
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on
|
| 20 |
-
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 14.6705
|
| 22 |
-
- Wer: 1.0
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -39,21 +35,17 @@ More information needed
|
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
- learning_rate: 0.0001
|
| 42 |
-
- train_batch_size:
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
| 45 |
- gradient_accumulation_steps: 2
|
| 46 |
-
- total_train_batch_size:
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
-
- lr_scheduler_warmup_steps:
|
| 50 |
- num_epochs: 30
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
-
### Training results
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.43.0.dev0
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
|
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/danakal/xls_300m_french_data/runs/cf8f5rsv)
|
| 15 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/danakal/xls_300m_french_data/runs/cf8f5rsv)
|
| 16 |
# xls_1b_decoding_fr_decoding_test
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
| 41 |
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 4
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 40
|
| 46 |
- num_epochs: 30
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.43.0.dev0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262000180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7fb31004f3ad0211a964788e27320e78f0805e5b97dbd8da031b5f97c38d027
|
| 3 |
size 1262000180
|