End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: deepseek-ai/deepseek-coder-1.3b-base
-library_name: peft
+library_name: transformers
 license: other
+base_model: deepseek-ai/deepseek-coder-1.3b-base
 tags:
 - trl
 - kto
@@ -14,10 +14,17 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/stojchets/huggingface/runs/kto2)
 # kto2
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5
+- Eval/rewards/chosen: -1151.2938
+- Eval/logps/chosen: -11550.3197
+- Eval/rewards/rejected: -1115.2082
+- Eval/logps/rejected: -11226.5358
+- Eval/rewards/margins: -36.0856
+- Eval/kl: 0.0
 
 ## Model description
 
@@ -36,25 +43,32 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.41e-05
+- learning_rate: 0.07
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |     |
+|:-------------:|:------:|:----:|:---------------:|:---:|
+| 0.498         | 1.1552 | 100  | 0.5             | 0.0 |
+| 0.4992        | 2.3105 | 200  | 0.5             | 0.0 |
+| 0.4982        | 3.4657 | 300  | 0.5             | 0.0 |
+| 0.5001        | 4.6209 | 400  | 0.5             | 0.0 |
 
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.43.0.dev0
-- Pytorch 2.2.2+cu121
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
 - Datasets 2.19.2
-- Tokenizers 0.19.1
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.45.0"
+}