anoopsinghal/mistralai/Mistral-7B-Instruct-v0.1-sql-create-context

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral-viggo-finetune
+ 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-viggo-finetune
+
+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 None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4072
+
+## 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: 2.5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4563 | 0.01 | 50 | 0.7277 |
+| 0.5873 | 0.01 | 100 | 0.5276 |
+| 0.4951 | 0.02 | 150 | 0.4817 |
+| 0.4645 | 0.02 | 200 | 0.4664 |
+| 0.4682 | 0.03 | 250 | 0.4541 |
+| 0.4569 | 0.03 | 300 | 0.4447 |
+| 0.4428 | 0.04 | 350 | 0.4362 |
+| 0.4184 | 0.04 | 400 | 0.4326 |
+| 0.4174 | 0.05 | 450 | 0.4280 |
+| 0.4122 | 0.05 | 500 | 0.4242 |
+| 0.4176 | 0.06 | 550 | 0.4228 |
+| 0.4105 | 0.06 | 600 | 0.4175 |
+| 0.4103 | 0.07 | 650 | 0.4154 |
+| 0.4113 | 0.07 | 700 | 0.4133 |
+| 0.3979 | 0.08 | 750 | 0.4118 |
+| 0.3895 | 0.08 | 800 | 0.4109 |
+| 0.4088 | 0.09 | 850 | 0.4092 |
+| 0.399 | 0.09 | 900 | 0.4082 |
+| 0.4001 | 0.1 | 950 | 0.4075 |
+| 0.4067 | 0.1 | 1000 | 0.4072 |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

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,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 16,
+ "lora_dropout": 0.05,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "down_proj",
+ "lm_head",
+ "q_proj",
+ "k_proj",
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1361a6163c7a7c586531b71e9c5dbe0e23dc7c2977d897685d98de57c8a4153d
+size 85203090

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4864f320960a397e2661f7504c189c460c2f009879305158fcae7041bfa38d0
+size 4472