chandrasekhar319/QA_Finetune_BioMistral

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: BioMistral/BioMistral-7B
+model-index:
+- name: QA_Finetune_BioMistral
+  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. -->
+
+# QA_Finetune_BioMistral
+
+This model is a fine-tuned version of [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8514
+
+## 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: 0.00025
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9391        | 0.0619 | 200  | 0.9290          |
+| 0.9056        | 0.1238 | 400  | 0.9171          |
+| 0.8717        | 0.1858 | 600  | 0.9138          |
+| 0.822         | 0.2477 | 800  | 0.9174          |
+| 0.8539        | 0.3096 | 1000 | 0.9075          |
+| 0.8902        | 0.3715 | 1200 | 0.9061          |
+| 0.936         | 0.4334 | 1400 | 0.9088          |
+| 0.8572        | 0.4954 | 1600 | 0.8990          |
+| 0.8669        | 0.5573 | 1800 | 0.8933          |
+| 0.875         | 0.6192 | 2000 | 0.8868          |
+| 0.8369        | 0.6811 | 2200 | 0.8801          |
+| 0.8445        | 0.7430 | 2400 | 0.8772          |
+| 0.8316        | 0.8050 | 2600 | 0.8692          |
+| 0.8573        | 0.8669 | 2800 | 0.8614          |
+| 0.8104        | 0.9288 | 3000 | 0.8542          |
+| 0.8182        | 0.9907 | 3200 | 0.8488          |
+| 0.5912        | 1.0526 | 3400 | 0.8659          |
+| 0.5579        | 1.1146 | 3600 | 0.8557          |
+| 0.5834        | 1.1765 | 3800 | 0.8608          |
+| 0.547         | 1.2384 | 4000 | 0.8514          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "BioMistral/BioMistral-7B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "lm_head",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0174ebb41b90f874699b4b4b25f08cd6fb2daff4670b565e741dac1dc797355
+size 346667168

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "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:aa1ce4e7da30320668d2d79ac468a41ecd3a6ad11463ef7ee76e320e6ecb2e56
+size 5048