Advaith1612/bart-convo-summarizer-peft

README.md

@@ -0,0 +1,65 @@
+---
+base_model: Advaith1612/bart_convo-summarizer
+datasets:
+- samsum
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-convo-summarizer-peft
+  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. -->
+
+# bart-convo-summarizer-peft
+
+This model is a fine-tuned version of [Advaith1612/bart_convo-summarizer](https://huggingface.co/Advaith1612/bart_convo-summarizer) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1007
+
+## 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: 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.2141        | 1.0   | 37   | 1.5593          |
+| 1.0508        | 2.0   | 74   | 0.5395          |
+| 0.3323        | 3.0   | 111  | 0.1873          |
+| 0.1741        | 4.0   | 148  | 0.1134          |
+| 0.1335        | 5.0   | 185  | 0.1007          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Advaith1612/bart_convo-summarizer",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f6747bf87f9a6d9044772c07545c6ff460f41016ec7a9ee90c163bc701d2e0
+size 18894856

runs/Jun24_11-49-40_75f9e1ef602f/events.out.tfevents.1719229814.75f9e1ef602f.574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc2b05a9b67f74b374024f811d1dc72ff2d8b64c9b4f1910d76f5be00bacc61
+size 17082

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8056f0914429b81b2c4fc1951452091128e8e373ccf64caf5cee8edd2bb5c3
+size 5112