mistral-lp2-org_aug_b

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: org_model
+  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. -->
+
+# org_model
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9527
+- F1 Micro: 0.8011
+- F1 Macro: 0.7779
+- F1 Weighted: 0.8108
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 400
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
+| 1.5515        | 0.0064 | 25   | 1.3111          | 0.7801   | 0.7504   | 0.7890      |
+| 1.2983        | 0.0127 | 50   | 1.2188          | 0.7748   | 0.7572   | 0.7891      |
+| 1.2193        | 0.0191 | 75   | 1.1271          | 0.7855   | 0.7583   | 0.7937      |
+| 1.1269        | 0.0255 | 100  | 1.0890          | 0.7952   | 0.7639   | 0.8015      |
+| 1.0734        | 0.0318 | 125  | 1.0594          | 0.7949   | 0.7635   | 0.8008      |
+| 1.0384        | 0.0382 | 150  | 1.0389          | 0.7857   | 0.7614   | 0.7937      |
+| 1.0168        | 0.0446 | 175  | 1.0126          | 0.8045   | 0.7794   | 0.8133      |
+| 1.0043        | 0.0510 | 200  | 0.9998          | 0.8034   | 0.7786   | 0.8123      |
+| 1.0406        | 0.0573 | 225  | 0.9874          | 0.8074   | 0.7803   | 0.8153      |
+| 1.0488        | 0.0637 | 250  | 0.9838          | 0.7922   | 0.7664   | 0.8000      |
+| 0.9894        | 0.0701 | 275  | 0.9673          | 0.8034   | 0.7780   | 0.8122      |
+| 0.9969        | 0.0764 | 300  | 0.9629          | 0.7992   | 0.7720   | 0.8069      |
+| 1.0047        | 0.0828 | 325  | 0.9655          | 0.8000   | 0.7689   | 0.8058      |
+| 0.9812        | 0.0892 | 350  | 0.9623          | 0.8049   | 0.7839   | 0.8159      |
+| 0.9681        | 0.0955 | 375  | 0.9551          | 0.8016   | 0.7794   | 0.8118      |
+| 1.0594        | 0.1019 | 400  | 0.9527          | 0.8011   | 0.7779   | 0.8108      |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu118
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 8,
+  "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": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_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 sha256:5b85215f09cdaa6df88c3cc47626b89e43c3e757c0812dfd8eb6bf5146d5812a
+size 578898352

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_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[LP2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "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 sha256:30e08f5be53f4133530eaeb78ee7110f2419649486cf505c3734bc1d9de5378e
+size 4920