Update README.md
Browse files
README.md
CHANGED
@@ -14,6 +14,7 @@ This text generator is based on OpenAI GPT2 model from HuggingFace
|
|
14 |
Base model went through two step of learning
|
15 |
## First - Finetining of base model
|
16 |
On this step model is finetuned on dataset of single sentence from the texts of Dostovesky F.M.
|
|
|
17 |
Training parameters:
|
18 |
* Epoch = 10
|
19 |
* Learning Rate = 1e-3
|
@@ -27,6 +28,7 @@ Training parameters:
|
|
27 |
|
28 |
## Second - RL
|
29 |
On this step finetuned model went trough reinforcement learning pipline with TRL library.
|
|
|
30 |
Training parameters:
|
31 |
* Epoch = 30
|
32 |
* Trainer = PPO
|
|
|
14 |
Base model went through two step of learning
|
15 |
## First - Finetining of base model
|
16 |
On this step model is finetuned on dataset of single sentence from the texts of Dostovesky F.M.
|
17 |
+
|
18 |
Training parameters:
|
19 |
* Epoch = 10
|
20 |
* Learning Rate = 1e-3
|
|
|
28 |
|
29 |
## Second - RL
|
30 |
On this step finetuned model went trough reinforcement learning pipline with TRL library.
|
31 |
+
|
32 |
Training parameters:
|
33 |
* Epoch = 30
|
34 |
* Trainer = PPO
|