deadcode99/mistral-billm-token-classification

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: mistral-7b-32k-billm-finetuned-token-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. -->
+
+# mistral-7b-32k-billm-finetuned-token-classification
+
+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: 0.6070
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.7473
+
+## 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: 0.0005
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
+- 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 | Precision | Recall | F1  | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 0.9957 | 73   | 1.0053          | 0.0       | 0.0    | 0.0 | 0.7275   |
+| No log        | 1.9915 | 146  | 0.8578          | 0.0       | 0.0    | 0.0 | 0.7426   |
+| No log        | 2.9872 | 219  | 0.7958          | 0.0       | 0.0    | 0.0 | 0.7195   |
+| No log        | 3.9966 | 293  | 0.6437          | 0.0       | 0.0    | 0.0 | 0.7144   |
+| No log        | 4.9923 | 366  | 0.6283          | 0.0       | 0.0    | 0.0 | 0.7318   |
+| No log        | 5.9881 | 439  | 0.6543          | 0.0       | 0.0    | 0.0 | 0.7553   |
+| 0.9335        | 6.9974 | 513  | 0.6112          | 0.0       | 0.0    | 0.0 | 0.7037   |
+| 0.9335        | 7.9932 | 586  | 0.6053          | 0.0       | 0.0    | 0.0 | 0.7373   |
+| 0.9335        | 8.9889 | 659  | 0.6208          | 0.0       | 0.0    | 0.0 | 0.7518   |
+| 0.9335        | 9.9574 | 730  | 0.6070          | 0.0       | 0.0    | 0.0 | 0.7473   |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.2.2
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "TOKEN_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c9abfbce7f47a9948f7ba8a6dd6edb9901291df3d52eb5cef5c39f3f7dccce
+size 27296852

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": "<unk>",
+  "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:ffe5610538f307cef74506cff6a3097cd6ccd3c3dcf3accae5aa213fb75949f1
+size 5176