Sribhuvan/distilgpt2-Finance

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: distilbert/distilgpt2
+tags:
+- generated_from_trainer
+library_name: peft
+model-index:
+- name: distilgpt2-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. -->
+
+# distilgpt2-lora-text-classification
+
+This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.5596
+- Rougel F1: 0.0
+
+## 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-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rougel F1 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| No log        | 1.0   | 83   | 7.1013          | 0.0       |
+| No log        | 2.0   | 166  | 6.9855          | 0.0       |
+| No log        | 3.0   | 249  | 6.8850          | 0.0       |
+| No log        | 4.0   | 332  | 6.7975          | 0.0       |
+| No log        | 5.0   | 415  | 6.7247          | 0.0       |
+| No log        | 6.0   | 498  | 6.6657          | 0.0       |
+| 7.0748        | 7.0   | 581  | 6.6194          | 0.0       |
+| 7.0748        | 8.0   | 664  | 6.5859          | 0.0       |
+| 7.0748        | 9.0   | 747  | 6.5662          | 0.0       |
+| 7.0748        | 10.0  | 830  | 6.5596          | 0.0       |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.43.4
+- Pytorch 2.6.0
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert/distilgpt2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "qa_outputs"
+  ],
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "QUESTION_ANS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba020e3d4263f580202e7ed79178a9bc18a24b332c87955a47facf435122a19
+size 154695456

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7837828fd1db116bb6900b0eb04edd5a89c31982718f6e81ae2d0c45349af6ea
+size 5240