Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: mms-meta/mms-zeroshot-300m
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mms-zeroshot-bem-sv-female
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# mms-zeroshot-bem-sv-female
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2722
|
| 22 |
+
- Wer: 0.4382
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 10.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| No log | 0.3992 | 200 | 1.9434 | 1.0 |
|
| 56 |
+
| No log | 0.7984 | 400 | 0.3648 | 0.5411 |
|
| 57 |
+
| 2.5692 | 1.1976 | 600 | 0.3371 | 0.5174 |
|
| 58 |
+
| 2.5692 | 1.5968 | 800 | 0.3229 | 0.5213 |
|
| 59 |
+
| 0.3941 | 1.9960 | 1000 | 0.3183 | 0.4915 |
|
| 60 |
+
| 0.3941 | 2.3952 | 1200 | 0.3068 | 0.5073 |
|
| 61 |
+
| 0.3941 | 2.7944 | 1400 | 0.3057 | 0.4688 |
|
| 62 |
+
| 0.3502 | 3.1936 | 1600 | 0.3017 | 0.4777 |
|
| 63 |
+
| 0.3502 | 3.5928 | 1800 | 0.2905 | 0.4647 |
|
| 64 |
+
| 0.3253 | 3.9920 | 2000 | 0.2857 | 0.4686 |
|
| 65 |
+
| 0.3253 | 4.3912 | 2200 | 0.2892 | 0.4601 |
|
| 66 |
+
| 0.3253 | 4.7904 | 2400 | 0.2848 | 0.4759 |
|
| 67 |
+
| 0.3066 | 5.1896 | 2600 | 0.2801 | 0.4444 |
|
| 68 |
+
| 0.3066 | 5.5888 | 2800 | 0.2752 | 0.4627 |
|
| 69 |
+
| 0.2988 | 5.9880 | 3000 | 0.2818 | 0.4614 |
|
| 70 |
+
| 0.2988 | 6.3872 | 3200 | 0.2759 | 0.4444 |
|
| 71 |
+
| 0.2988 | 6.7864 | 3400 | 0.2751 | 0.4382 |
|
| 72 |
+
| 0.2877 | 7.1856 | 3600 | 0.2726 | 0.4472 |
|
| 73 |
+
| 0.2877 | 7.5848 | 3800 | 0.2722 | 0.4484 |
|
| 74 |
+
| 0.2812 | 7.9840 | 4000 | 0.2710 | 0.4344 |
|
| 75 |
+
| 0.2812 | 8.3832 | 4200 | 0.2734 | 0.4410 |
|
| 76 |
+
| 0.2812 | 8.7824 | 4400 | 0.2734 | 0.4360 |
|
| 77 |
+
| 0.2742 | 9.1816 | 4600 | 0.2759 | 0.4398 |
|
| 78 |
+
| 0.2742 | 9.5808 | 4800 | 0.2740 | 0.4337 |
|
| 79 |
+
| 0.2731 | 9.9800 | 5000 | 0.2722 | 0.4382 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.45.0.dev0
|
| 85 |
+
- Pytorch 2.4.0+cu121
|
| 86 |
+
- Datasets 2.21.0
|
| 87 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1265394748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:136ae8dd41eb050948c702b08c80265598a03ac28f649b07be5cf6d82369037c
|
| 3 |
size 1265394748
|
runs/Aug30_14-04-35_4297e45ecd95/events.out.tfevents.1725027143.4297e45ecd95.3339.0
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 sha256:1d096c83a1a9dc5caf8d5e1196f42f465590832418537044d2220a62cec3b0ec
|
| 3 |
+
size 16806
|