kwang123/llama2-7B-ReqORNot

README.md

@@ -0,0 +1,71 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: llama2-7B-ReqORNot
+  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. -->
+
+# llama2-7B-ReqORNot
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2597
+- Accuracy: 0.8970
+- Weighted precision: 0.8971
+- Weighted recall: 0.8970
+- Weighted f1: 0.8971
+- Macro precision: 0.8969
+- Macro recall: 0.8971
+- Macro f1: 0.8970
+
+## 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: 2e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- 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 | Weighted precision | Weighted recall | Weighted f1 | Macro precision | Macro recall | Macro f1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------:|:---------------:|:-----------:|:---------------:|:------------:|:--------:|
+| No log        | 1.0   | 237  | 0.4807          | 0.7896   | 0.7895             | 0.7896          | 0.7895      | 0.7894          | 0.7891       | 0.7892   |
+| No log        | 2.0   | 474  | 0.3167          | 0.8605   | 0.8605             | 0.8605          | 0.8605      | 0.8604          | 0.8604       | 0.8604   |
+| 0.5108        | 3.0   | 711  | 0.2709          | 0.8860   | 0.8869             | 0.8860          | 0.8860      | 0.8862          | 0.8866       | 0.8860   |
+| 0.5108        | 4.0   | 948  | 0.2704          | 0.8880   | 0.8889             | 0.8880          | 0.8879      | 0.8894          | 0.8871       | 0.8876   |
+| 0.1829        | 5.0   | 1185 | 0.2597          | 0.8970   | 0.8971             | 0.8970          | 0.8971      | 0.8969          | 0.8971       | 0.8970   |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "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 sha256:631141c099f92608e937daa0ec9b707ef0281b30f28a02fbd12932d05b06f94c
+size 639724744

runs/Mar05_23-55-36_1be7571c5275/events.out.tfevents.1709682936.1be7571c5275.79128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b19da25ed2aac82a55dc9cb2665663603d13496fd5df7a698f407fb3703c42
+size 9183

runs/Mar05_23-55-36_1be7571c5275/events.out.tfevents.1709692803.1be7571c5275.79128.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810dfcb3e37a290dee09916b215d3174de58e5dce3b61a9ad3321beb9a905fef
+size 754

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f6337d23eebadf061f56dd8fedc68c249382216dc47b4ba6ef045291c79af7
+size 4920