Commit
•
d0fd808
1
Parent(s):
5b116cc
End of training
Browse files- README.md +77 -0
- generation_config.json +6 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/DialoGPT-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-stage2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 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 |
+
# DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-stage2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/DialoGPT-large](https://huggingface.co/microsoft/DialoGPT-large) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.4123
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| No log | 1.0 | 40 | 4.2793 |
|
| 51 |
+
| No log | 2.0 | 80 | 3.5752 |
|
| 52 |
+
| No log | 3.0 | 120 | 3.1238 |
|
| 53 |
+
| No log | 4.0 | 160 | 2.8875 |
|
| 54 |
+
| No log | 5.0 | 200 | 2.7358 |
|
| 55 |
+
| No log | 6.0 | 240 | 2.6321 |
|
| 56 |
+
| No log | 7.0 | 280 | 2.5629 |
|
| 57 |
+
| No log | 8.0 | 320 | 2.5147 |
|
| 58 |
+
| No log | 9.0 | 360 | 2.4783 |
|
| 59 |
+
| No log | 10.0 | 400 | 2.4595 |
|
| 60 |
+
| No log | 11.0 | 440 | 2.4370 |
|
| 61 |
+
| No log | 12.0 | 480 | 2.4229 |
|
| 62 |
+
| 2.7646 | 13.0 | 520 | 2.4167 |
|
| 63 |
+
| 2.7646 | 14.0 | 560 | 2.4109 |
|
| 64 |
+
| 2.7646 | 15.0 | 600 | 2.4084 |
|
| 65 |
+
| 2.7646 | 16.0 | 640 | 2.4146 |
|
| 66 |
+
| 2.7646 | 17.0 | 680 | 2.4085 |
|
| 67 |
+
| 2.7646 | 18.0 | 720 | 2.4139 |
|
| 68 |
+
| 2.7646 | 19.0 | 760 | 2.4137 |
|
| 69 |
+
| 2.7646 | 20.0 | 800 | 2.4123 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.33.0.dev0
|
| 75 |
+
- Pytorch 2.0.1+cu118
|
| 76 |
+
- Datasets 2.14.4.dev0
|
| 77 |
+
- 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.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3353572641
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:304c12dc19b231d0527fd08af5e97a5a72bfc8ef924544e18932da019f28799f
|
| 3 |
size 3353572641
|