Model save
Browse files- README.md +77 -0
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HKUSTAudio/Llasa-1B
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: A10-Llasa-1B
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# A10-Llasa-1B
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [HKUSTAudio/Llasa-1B](https://huggingface.co/HKUSTAudio/Llasa-1B) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 7.4506
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
+
- total_train_batch_size: 2
|
| 45 |
+
- total_eval_batch_size: 2
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 55 |
+
| No log | 0 | 0 | 7.8569 |
|
| 56 |
+
| 7.1218 | 0.0751 | 1000 | 7.5281 |
|
| 57 |
+
| 7.2827 | 0.1503 | 2000 | 7.4962 |
|
| 58 |
+
| 7.2238 | 0.2254 | 3000 | 7.4882 |
|
| 59 |
+
| 7.3725 | 0.3006 | 4000 | 7.4697 |
|
| 60 |
+
| 7.2284 | 0.3757 | 5000 | 7.4629 |
|
| 61 |
+
| 6.9178 | 0.4509 | 6000 | 7.4605 |
|
| 62 |
+
| 7.2347 | 0.5260 | 7000 | 7.4566 |
|
| 63 |
+
| 7.0272 | 0.6012 | 8000 | 7.4574 |
|
| 64 |
+
| 7.0231 | 0.6763 | 9000 | 7.4564 |
|
| 65 |
+
| 7.1072 | 0.7515 | 10000 | 7.4533 |
|
| 66 |
+
| 7.0091 | 0.8266 | 11000 | 7.4523 |
|
| 67 |
+
| 7.1567 | 0.9018 | 12000 | 7.4519 |
|
| 68 |
+
| 7.0096 | 0.9769 | 13000 | 7.4506 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- PEFT 0.15.2
|
| 74 |
+
- Transformers 4.45.2
|
| 75 |
+
- Pytorch 2.4.1+cu121
|
| 76 |
+
- Datasets 3.0.1
|
| 77 |
+
- Tokenizers 0.20.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3416264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7930a19a6a420f43626226b5cd09796a1b745b90cd301189d18393036cdcefb0
|
| 3 |
size 3416264
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2745385306
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8c28577c7d37045e7a5cce3df36918e370eda14790d06640370cd97d9fb153
|
| 3 |
size 2745385306
|