End of training
Browse files
README.md
CHANGED
|
@@ -6,8 +6,6 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: nlpmodel
|
| 8 |
results: []
|
| 9 |
-
datasets:
|
| 10 |
-
- anon8231489123/ShareGPT_Vicuna_unfiltered
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# nlpmodel
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -34,15 +32,15 @@ More information needed
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate:
|
| 38 |
-
- train_batch_size:
|
| 39 |
- eval_batch_size: 8
|
| 40 |
- seed: 42
|
| 41 |
-
- gradient_accumulation_steps:
|
| 42 |
-
- total_train_batch_size:
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: constant
|
| 45 |
-
- num_epochs: 5
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
@@ -53,4 +51,4 @@ The following hyperparameters were used during training:
|
|
| 53 |
- Transformers 4.35.2
|
| 54 |
- Pytorch 2.1.0+cu118
|
| 55 |
- Datasets 2.15.0
|
| 56 |
-
- Tokenizers 0.15.0
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: nlpmodel
|
| 8 |
results: []
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 13 |
|
| 14 |
# nlpmodel
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0005
|
| 36 |
+
- train_batch_size: 4
|
| 37 |
- eval_batch_size: 8
|
| 38 |
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 4
|
| 40 |
+
- total_train_batch_size: 16
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: constant
|
| 43 |
+
- num_epochs: 0.5
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
| 51 |
- Transformers 4.35.2
|
| 52 |
- Pytorch 2.1.0+cu118
|
| 53 |
- Datasets 2.15.0
|
| 54 |
+
- Tokenizers 0.15.0
|