bart-large-finetuned-Samsum-DH

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+datasets:
+- samsum
+metrics:
+- rouge
+model-index:
+- name: mode_tuned_peft
+  results: []
+library_name: peft
+---
+
+<!-- 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. -->
+
+# mode_tuned_peft
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5220
+- Rouge1: 40.6099
+- Rouge2: 20.4138
+- Rougel: 31.1095
+- Rougelsum: 37.6804
+- Gen Len: 58.11
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 0.5144        | 1.0   | 14732 | 0.5494          | 39.171  | 19.3682 | 29.7493 | 36.2965   | 58.6773 |
+| 0.5694        | 2.0   | 29464 | 0.5357          | 40.1584 | 20.0293 | 30.5791 | 37.1361   | 58.0648 |
+| 0.3497        | 3.0   | 44196 | 0.5277          | 41.0391 | 20.7891 | 31.5244 | 38.1502   | 58.0086 |
+| 0.3444        | 4.0   | 58928 | 0.5255          | 40.6698 | 20.543  | 31.2399 | 37.8126   | 58.3716 |
+| 0.3495        | 5.0   | 73660 | 0.5220          | 40.6099 | 20.4138 | 31.1095 | 37.6804   | 58.11   |
+
+
+### Framework versions
+
+- PEFT 0.4.0
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/bart-large-cnn",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87812fa1d58c6348a9d71c38eb28c4838fb8ec68014707fe76dcf873440480d3
+size 4738744

runs/Jul11_13-00-22_informally-glorious-horse/events.out.tfevents.1720702823.informally-glorious-horse

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fab16b2343b9255efcf3ad63f2cddcaead525e879586d4058e7c94d0d18ba02
+size 36751

runs/Jul11_13-12-26_informally-glorious-horse/events.out.tfevents.1720703547.informally-glorious-horse

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c859d61ca6d06be45a983d5748cefd72df76c612bddcb91919a730be519666
+size 37785

runs/Jul11_13-12-26_informally-glorious-horse/events.out.tfevents.1720703919.informally-glorious-horse

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901563bc96b9c2a97198dfd48bb094818f7d1041ce49ff79fed7a16b2ef1208f
+size 40

runs/Jul11_13-19-32_informally-glorious-horse/events.out.tfevents.1720703973.informally-glorious-horse

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377062648a06f62c361a084d193a2b9c6dd6c24fad3edead80305b7bd5920f62
+size 1586052

runs/Jul11_13-19-32_informally-glorious-horse/events.out.tfevents.1720715530.informally-glorious-horse

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d073b2785ee985e60af7765879a9787f72df929cd64c34024d5a12b8881bf590
+size 40

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00bbfd79eb361cf31d003733eec46a85b863602eb14c043a700db2a87d5b35f
+size 5304