End of training

README.md

@@ -1,9 +1,8 @@
 ---
 license: bigcode-openrail-m
-library_name: peft
+base_model: bigcode/tiny_starcoder_py
 tags:
 - generated_from_trainer
-base_model: bigcode/tiny_starcoder_py
 model-index:
 - name: peft-lora-starcoder-chat-asst-A100-40GB-colab
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2075
+- Loss: 2.2079
 
 ## Model description
 
@@ -50,7 +49,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.649         | 0.67  | 100  | 2.2075          |
+| 2.6488        | 0.67  | 100  | 2.2079          |
 
 
 ### Framework versions
@@ -59,22 +58,3 @@ The following hyperparameters were used during training:
 - Pytorch 2.0.0
 - Datasets 2.15.0
 - Tokenizers 0.15.0
-## Training procedure
-
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-
-### Framework versions
-
-
-- PEFT 0.6.3.dev0