mnlp-nsoai/mistral-7b-scientific-mcq

README.md

@@ -0,0 +1,114 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: mistral-7b-scientific-mcq
+  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. -->
+
+# mistral-7b-scientific-mcq
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7480
+
+## 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-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9911        | 0.0581 | 100  | 0.8124          |
+| 0.879         | 0.1162 | 200  | 0.7703          |
+| 0.9359        | 0.1743 | 300  | 0.7576          |
+| 0.7608        | 0.2325 | 400  | 0.7523          |
+| 0.8144        | 0.2906 | 500  | 0.7469          |
+| 0.8655        | 0.3487 | 600  | 0.7435          |
+| 0.6748        | 0.4068 | 700  | 0.7390          |
+| 0.7004        | 0.4649 | 800  | 0.7369          |
+| 0.7561        | 0.5230 | 900  | 0.7351          |
+| 0.7053        | 0.5811 | 1000 | 0.7317          |
+| 0.7122        | 0.6393 | 1100 | 0.7294          |
+| 0.7431        | 0.6974 | 1200 | 0.7279          |
+| 0.6102        | 0.7555 | 1300 | 0.7255          |
+| 0.7041        | 0.8136 | 1400 | 0.7244          |
+| 0.7339        | 0.8717 | 1500 | 0.7227          |
+| 0.6648        | 0.9298 | 1600 | 0.7207          |
+| 0.5682        | 0.9879 | 1700 | 0.7192          |
+| 0.6745        | 1.0461 | 1800 | 0.7242          |
+| 0.6003        | 1.1042 | 1900 | 0.7258          |
+| 0.6755        | 1.1623 | 2000 | 0.7273          |
+| 0.6815        | 1.2204 | 2100 | 0.7265          |
+| 0.5531        | 1.2785 | 2200 | 0.7253          |
+| 0.5           | 1.3366 | 2300 | 0.7250          |
+| 0.666         | 1.3947 | 2400 | 0.7236          |
+| 0.518         | 1.4529 | 2500 | 0.7247          |
+| 0.6223        | 1.5110 | 2600 | 0.7240          |
+| 0.565         | 1.5691 | 2700 | 0.7234          |
+| 0.5541        | 1.6272 | 2800 | 0.7220          |
+| 0.7622        | 1.6853 | 2900 | 0.7220          |
+| 0.5212        | 1.7434 | 3000 | 0.7223          |
+| 0.6089        | 1.8015 | 3100 | 0.7205          |
+| 0.6908        | 1.8597 | 3200 | 0.7210          |
+| 0.6138        | 1.9178 | 3300 | 0.7204          |
+| 0.6425        | 1.9759 | 3400 | 0.7199          |
+| 0.4918        | 2.0340 | 3500 | 0.7416          |
+| 0.5432        | 2.0921 | 3600 | 0.7468          |
+| 0.6497        | 2.1502 | 3700 | 0.7463          |
+| 0.5068        | 2.2083 | 3800 | 0.7448          |
+| 0.5502        | 2.2665 | 3900 | 0.7475          |
+| 0.4795        | 2.3246 | 4000 | 0.7482          |
+| 0.5718        | 2.3827 | 4100 | 0.7486          |
+| 0.5154        | 2.4408 | 4200 | 0.7474          |
+| 0.6959        | 2.4989 | 4300 | 0.7479          |
+| 0.5848        | 2.5570 | 4400 | 0.7473          |
+| 0.5662        | 2.6151 | 4500 | 0.7479          |
+| 0.4357        | 2.6733 | 4600 | 0.7482          |
+| 0.5318        | 2.7314 | 4700 | 0.7476          |
+| 0.4631        | 2.7895 | 4800 | 0.7480          |
+| 0.5852        | 2.8476 | 4900 | 0.7481          |
+| 0.5633        | 2.9057 | 5000 | 0.7480          |
+| 0.5831        | 2.9638 | 5100 | 0.7480          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_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:b71591490cf44b865cc1aeb07a4a00396980de99aafcad1b6da61d5e4b37bb17
+size 167832240

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 +1,43 @@
+{
+  "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
+    }
+  },
+  "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>",
+  "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:c6c4553b8cdc1874e0ee64b1cf628de61bacf498d7810c4a91c35390a727ae97
+size 5432