SaiPavanKumarMeruga/roberta-base-lora-sarcasm-classification

README.md

@@ -0,0 +1,66 @@
+---
+base_model: roberta-base
+library_name: peft
+license: mit
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+model-index:
+- name: roberta-base-lora-text-classification
+  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. -->
+
+# roberta-base-lora-text-classification
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7005
+- Accuracy: {'accuracy': 0.858}
+
+## 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: 0.001
+- train_batch_size: 4
+- eval_batch_size: 4
+- 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 | Accuracy            |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
+| No log        | 1.0   | 250  | 0.6210          | {'accuracy': 0.688} |
+| 0.6692        | 2.0   | 500  | 0.5909          | {'accuracy': 0.84}  |
+| 0.6692        | 3.0   | 750  | 0.5707          | {'accuracy': 0.84}  |
+| 0.4899        | 4.0   | 1000 | 0.4900          | {'accuracy': 0.84}  |
+| 0.4899        | 5.0   | 1250 | 0.7005          | {'accuracy': 0.858} |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.3.1
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 2,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb4e7bfba8e9d8460e2a47bf693a562a8c0144f54ee87ecb9575ad2fb7310e0
+size 2670768

runs/Aug04_11-54-50_Sais-MBP-3.attlocal.net/events.out.tfevents.1722786893.Sais-MBP-3.attlocal.net.25797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba64cc1e33bba28b35b60cd06edc98d99387578e32e3787c338dec2959c628ea
+size 9156

runs/Aug04_12-20-00_Sais-MBP-3.attlocal.net/events.out.tfevents.1722788402.Sais-MBP-3.attlocal.net.25797.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e19a937507b30912f427cbf65944ae5d5fbbb8495136d409fc6545ceb3726f7
+size 12970

runs/Aug04_14-04-00_Sais-MBP-3.attlocal.net/events.out.tfevents.1722794641.Sais-MBP-3.attlocal.net.28745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8c243f055d3fe4136dccfb8bbbe32c946d283446f309792eb5fce02f04d715
+size 7167

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "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": false,
+      "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": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6573139d1dd76360590250e19dde8da4fd4f084b5ccfe0658f2e3a25fd07ea3c
+size 5176