Model save
Browse files- README.md +69 -0
- generation_config.json +6 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: qgyd2021/chinese_chitchat
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: chinese_chitchat
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# chinese_chitchat
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [qgyd2021/chinese_chitchat](https://huggingface.co/qgyd2021/chinese_chitchat) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.0956
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0002
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 2
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 128
|
| 44 |
+
- total_eval_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 10000
|
| 48 |
+
- num_epochs: 40.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 1.6078 | 0.29 | 1000 | 2.0697 |
|
| 55 |
+
| 1.5713 | 0.58 | 2000 | 2.0622 |
|
| 56 |
+
| 1.5576 | 0.86 | 3000 | 2.0544 |
|
| 57 |
+
| 1.5351 | 1.15 | 4000 | 2.0736 |
|
| 58 |
+
| 1.5371 | 1.44 | 5000 | 2.0742 |
|
| 59 |
+
| 1.5663 | 1.73 | 6000 | 2.0582 |
|
| 60 |
+
| 1.576 | 2.02 | 7000 | 2.1065 |
|
| 61 |
+
| 1.5178 | 2.3 | 8000 | 2.0956 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.33.0
|
| 67 |
+
- Pytorch 2.0.0
|
| 68 |
+
- Datasets 2.1.0
|
| 69 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.33.0"
|
| 6 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 408322909
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca218ce89f8c232e5c491baf109934dbf890dc80542e7e50518f57c94ab71d7
|
| 3 |
size 408322909
|