hdupouy/distilbert-base-uncased-lora-financial-sentiment-analysis

README.md

@@ -0,0 +1,66 @@
+---
+base_model: distilbert-base-uncased
+datasets:
+- financial_phrasebank
+library_name: peft
+license: apache-2.0
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-base-uncased-lora-financial-sentiment-analysis
+  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. -->
+
+# distilbert-base-uncased-lora-financial-sentiment-analysis
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0787
+- Accuracy: {'accuracy': 0.9823788546255506}
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy                         |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|
+| 0.1615        | 1.0   | 510  | 0.0830          | {'accuracy': 0.973568281938326}  |
+| 0.1076        | 2.0   | 1020 | 0.0787          | {'accuracy': 0.9823788546255506} |
+| 0.0558        | 3.0   | 1530 | 0.1102          | {'accuracy': 0.9647577092511013} |
+
+
+### 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert-base-uncased",
+  "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": 16,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_lin"
+  ],
+  "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 sha256:0aa5973b4ab2db1a92201e62cf5a8a0f5093d7228da1b3ea149fb3d019cb5e98
+size 2521180

runs/Jun23_21-44-09_5d1b3c65064f/events.out.tfevents.1719179515.5d1b3c65064f.1699.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6db7f94d2f213087cf7511560fa9a2c6defdaa20fb37db46d23807720010a0
+size 5804

runs/Jun23_21-52-45_5d1b3c65064f/events.out.tfevents.1719179615.5d1b3c65064f.1699.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fac4af68e97c986497f65bd499fb715bfd1dfdf5fc883ddcfb2a675b695dea
+size 6817

runs/Jun23_21-52-45_5d1b3c65064f/events.out.tfevents.1719179794.5d1b3c65064f.1699.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205abaf7527a0e4e466ae3ca7fef468f034b4224f979f3a223c7f57cac83dc31
+size 359

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4853e827671ecc0aceeb040803993ae3059791b890c0b2b5c5d6a0f5a1cd68
+size 5176