flan-t5-peft-mixsub

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-large
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: flan-t5-large-peft-mixSub
+  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. -->
+
+# flan-t5-large-peft-mixSub
+
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9408
+- Rouge1: 39.2511
+- Rouge2: 14.4613
+- Rougel: 28.6907
+- Rougelsum: 35.9795
+- Gen Len: 97.8269
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.1134        | 1.0   | 1630 | 1.9559          | 39.0131 | 14.3369 | 28.4611 | 35.7936   | 96.2081 |
+| 2.0783        | 2.0   | 3260 | 1.9438          | 39.0184 | 14.3571 | 28.5375 | 35.7466   | 99.4684 |
+| 2.0722        | 3.0   | 4890 | 1.9408          | 39.2511 | 14.4613 | 28.6907 | 35.9795   | 97.8269 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name_or_path": "google/flan-t5-large",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "SEQ_2_SEQ_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103e6a73b26bc732dacc5417939f6364f1e2ea299b8dff1821d9322572215dcf
+size 18980874

logs/events.out.tfevents.1711684560.ip-10-25-205-144.180196.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927bf293a01d419fd933d3f296d92f1a86902ac74536de1c48c09f09d42ffdc2
+size 8707

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a228df09c5b850027a26ba9be5f6cd962070f70cc01e989945bc894dba065468
+size 5112