mistral

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+datasets:
+- generator
+model-index:
+- name: mistral_instruct_generation
+  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_instruct_generation
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8488
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1973        | 0.0305 | 20   | 1.1052          |
+| 1.0347        | 0.0610 | 40   | 0.9958          |
+| 0.9213        | 0.0915 | 60   | 0.9600          |
+| 0.8886        | 0.1220 | 80   | 0.9406          |
+| 0.9314        | 0.1524 | 100  | 0.9281          |
+| 0.9668        | 0.1829 | 120  | 0.9197          |
+| 0.887         | 0.2134 | 140  | 0.9128          |
+| 0.8727        | 0.2439 | 160  | 0.9066          |
+| 0.8571        | 0.2744 | 180  | 0.9005          |
+| 0.8833        | 0.3049 | 200  | 0.8963          |
+| 0.8466        | 0.3354 | 220  | 0.8912          |
+| 0.9015        | 0.3659 | 240  | 0.8865          |
+| 0.8602        | 0.3963 | 260  | 0.8822          |
+| 0.8989        | 0.4268 | 280  | 0.8788          |
+| 0.8452        | 0.4573 | 300  | 0.8758          |
+| 0.8764        | 0.4878 | 320  | 0.8730          |
+| 0.8702        | 0.5183 | 340  | 0.8708          |
+| 0.8758        | 0.5488 | 360  | 0.8676          |
+| 0.8071        | 0.5793 | 380  | 0.8638          |
+| 0.8473        | 0.6098 | 400  | 0.8618          |
+| 0.8822        | 0.6402 | 420  | 0.8586          |
+| 0.8742        | 0.6707 | 440  | 0.8560          |
+| 0.8526        | 0.7012 | 460  | 0.8533          |
+| 0.8116        | 0.7317 | 480  | 0.8511          |
+| 0.8593        | 0.7622 | 500  | 0.8488          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- 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-v0.1",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:7a4aa942f48fe19334df4762e441341f93a95535c64d66af94cadbc8c0c053cc
+size 109069176

runs/Apr28_18-37-54_1cdde9d44bc6/events.out.tfevents.1714329481.1cdde9d44bc6.352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700772558c9e74c97080a97e1c1d4cae11cc86bcb46dff9b21c4e476dadf3760
+size 22797

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 +1,42 @@
+{
+  "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>",
+  "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 sha256:429ffc72cf8a2e9794f479a3ee523ab775d1474d15df35a4be71eddd76c023c2
+size 5048