mistral-lp2-org_org_a

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_aug_a
+  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_aug_a
+
+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: 0.8808
+- F1 Micro: 0.6615
+- F1 Macro: 0.6476
+- F1 Weighted: 0.6615
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
+| 2.2195        | 0.0154 | 25   | 1.5207          | 0.5691   | 0.5521   | 0.5694      |
+| 1.4371        | 0.0308 | 50   | 1.2747          | 0.6089   | 0.5857   | 0.6052      |
+| 1.2556        | 0.0462 | 75   | 1.1545          | 0.6304   | 0.6036   | 0.6240      |
+| 1.2415        | 0.0615 | 100  | 1.0691          | 0.6320   | 0.6132   | 0.6301      |
+| 0.9864        | 0.0769 | 125  | 1.0264          | 0.6399   | 0.6278   | 0.6411      |
+| 1.0647        | 0.0923 | 150  | 0.9918          | 0.6510   | 0.6266   | 0.6455      |
+| 0.9849        | 0.1077 | 175  | 0.9679          | 0.6576   | 0.6317   | 0.6511      |
+| 1.0067        | 0.1231 | 200  | 0.9383          | 0.6501   | 0.6384   | 0.6513      |
+| 0.8928        | 0.1385 | 225  | 0.9243          | 0.6620   | 0.6405   | 0.6579      |
+| 0.9858        | 0.1538 | 250  | 0.9132          | 0.6627   | 0.6405   | 0.6582      |
+| 0.9085        | 0.1692 | 275  | 0.9011          | 0.6575   | 0.6446   | 0.6581      |
+| 1.0059        | 0.1846 | 300  | 0.9018          | 0.6686   | 0.6436   | 0.6623      |
+| 0.8939        | 0.2    | 325  | 0.8928          | 0.6682   | 0.6448   | 0.6629      |
+| 0.864         | 0.2154 | 350  | 0.8833          | 0.6622   | 0.6478   | 0.6619      |
+| 0.9499        | 0.2308 | 375  | 0.8837          | 0.6585   | 0.6463   | 0.6593      |
+| 0.9721        | 0.2462 | 400  | 0.8808          | 0.6615   | 0.6476   | 0.6615      |
+
+
+### 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": [
+    "k_proj",
+    "q_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 sha256:64aab3f65d05a4875ea0dc29ce6bc0722b691a1b1218bfafa65ff540434e1d9a
+size 578881968

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 sha256:9cb00ce32d29829d7c54d851b6bafbf5cdb2ddcfbf2d94672533df521abb7582
+size 4920