Model save

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: bsd-3-clause
+base_model: Salesforce/codet5p-220m
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: constrative_faiss_v2
+  results: []
+---
+
+<!-- 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. -->
+
+# constrative_faiss_v2
+
+This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3539
+- Rouge1: 21.4629
+- Rouge2: 8.781
+- Rougel: 19.3981
+- Rougelsum: 20.0634
+- Gen Len: 14.8
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 384
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 1    | 4.0805          | 2.9231  | 0.0    | 2.6635  | 2.6442    | 20.0    |
+| No log        | 2.0   | 2    | 3.7128          | 12.6859 | 4.5992 | 11.8258 | 12.5583   | 19.35   |
+| No log        | 3.0   | 3    | 3.4877          | 16.8517 | 8.4744 | 16.038  | 16.5316   | 18.35   |
+| No log        | 4.0   | 4    | 3.3881          | 18.7157 | 7.4343 | 16.8165 | 17.7776   | 16.9    |
+| No log        | 5.0   | 5    | 3.3881          | 18.7157 | 7.4343 | 16.8165 | 17.7776   | 16.9    |
+| No log        | 6.0   | 6    | 3.3675          | 20.9949 | 8.5536 | 19.7058 | 20.0583   | 15.1    |
+| No log        | 7.0   | 7    | 3.3574          | 20.5585 | 8.5854 | 18.6151 | 19.2469   | 15.25   |
+| No log        | 8.0   | 8    | 3.3539          | 21.4629 | 8.781  | 19.3981 | 20.0634   | 14.8    |
+
+
+### Framework versions
+
+- Transformers 4.55.4
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.55.4"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ba54499b2630c2e0977902b86c7a61c267da87fb9ed82a50622836a4f294bd
+oid sha256:0a9659e6320ae32be35dabab5b751f25956dc4a8235a04b3b77eceacad1dd28f
 size 893924392