mistral-org_aug_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_modelorg_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_modelorg_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: 1.0772
+- F1 Micro: 0.5885
+- F1 Macro: 0.5884
+- F1 Weighted: 0.5884
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
+| 1.6909        | 0.0064 | 25   | 1.5440          | 0.5095   | 0.5089   | 0.5089      |
+| 1.4631        | 0.0127 | 50   | 1.4130          | 0.5483   | 0.5458   | 0.5458      |
+| 1.3764        | 0.0191 | 75   | 1.2988          | 0.5543   | 0.5543   | 0.5543      |
+| 1.2402        | 0.0255 | 100  | 1.2464          | 0.5623   | 0.5621   | 0.5621      |
+| 1.1982        | 0.0318 | 125  | 1.2415          | 0.5580   | 0.5544   | 0.5544      |
+| 1.1759        | 0.0382 | 150  | 1.1822          | 0.5732   | 0.5728   | 0.5728      |
+| 1.0769        | 0.0446 | 175  | 1.1590          | 0.5788   | 0.5787   | 0.5787      |
+| 1.0388        | 0.0510 | 200  | 1.1416          | 0.5821   | 0.5820   | 0.5820      |
+| 1.1786        | 0.0573 | 225  | 1.1273          | 0.5815   | 0.5806   | 0.5806      |
+| 1.2269        | 0.0637 | 250  | 1.1233          | 0.5823   | 0.5798   | 0.5798      |
+| 1.1746        | 0.0701 | 275  | 1.1105          | 0.5833   | 0.5819   | 0.5819      |
+| 1.1455        | 0.0764 | 300  | 1.0927          | 0.5868   | 0.5864   | 0.5864      |
+| 1.0494        | 0.0828 | 325  | 1.0905          | 0.5873   | 0.5867   | 0.5867      |
+| 1.0199        | 0.0892 | 350  | 1.0853          | 0.5845   | 0.5836   | 0.5836      |
+| 1.1086        | 0.0955 | 375  | 1.0789          | 0.5852   | 0.5849   | 0.5849      |
+| 1.0726        | 0.1019 | 400  | 1.0772          | 0.5885   | 0.5884   | 0.5884      |
+
+
+### 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",
+    "o_proj",
+    "q_proj",
+    "v_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:c7e9e1fb8e1abe63fe0d987d382ffdc272daebad148deafa2db923fe3c642e17
+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 sha256:754f4c483dbac6a0e1edca0ee68f789e73c61f1a22d13e77f87efdab0e3f4411
+size 4984