Promptengineering/text-to-sql-st_geometry

README.md

@@ -0,0 +1,67 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: sid321axn/Mistral-7B-text-to-sql-finetuned
+datasets:
+- generator
+model-index:
+- name: mistral_instruct_generation_st_geometry
+  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_st_geometry
+
+This model is a fine-tuned version of [sid321axn/Mistral-7B-text-to-sql-finetuned](https://huggingface.co/sid321axn/Mistral-7B-text-to-sql-finetuned) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2155
+
+## 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: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2741        | 4.0   | 20   | 0.1555          |
+| 0.0834        | 8.0   | 40   | 0.1331          |
+| 0.0236        | 12.0  | 60   | 0.1771          |
+| 0.0098        | 16.0  | 80   | 0.2101          |
+| 0.0063        | 20.0  | 100  | 0.2155          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.2.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sid321axn/Mistral-7B-text-to-sql-finetuned",
+  "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": [
+    "q_proj",
+    "v_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 sha256:63d0869c3e688366975b2e2f5759a0ac16e681e602cab5702f4169f16d426380
+size 109069176

runs/May24_16-05-02_DESK-HO-74960/events.out.tfevents.1716546908.DESK-HO-74960.10020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618ab14ccc4d13864f454fce3cdcd9077277b08abc0c782536128b6f1839f025
+size 5381

runs/May24_16-06-30_DESK-HO-74960/events.out.tfevents.1716546995.DESK-HO-74960.10020.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f6c41ba974f7607501c9f9c08cc4e832a5b6a51c3208f4972cc2210b213a4f
+size 5588

runs/May24_16-06-30_DESK-HO-74960/events.out.tfevents.1716547172.DESK-HO-74960.10020.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6107261256cd63a39aea215e2f3731d88e4388deae11a9ae3981089cac8bee0
+size 5381

runs/May24_16-13-43_DESK-HO-74960/events.out.tfevents.1716547429.DESK-HO-74960.18204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977de603bba65fa0f234790edcd2bc943905999dedc2233a168c039f3c3e2e6d
+size 5795

runs/May24_16-46-19_DESK-HO-74960/events.out.tfevents.1716549384.DESK-HO-74960.15976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661940a58801a8ed6bb9f063ae5c68b659c06c7908dd0b4ff1bef5e9084ca363
+size 9129

runs/May27_10-31-10_DESK-HO-74960/events.out.tfevents.1716786236.DESK-HO-74960.21048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f5be84ee815ac4f5a248b48be0b59b65cacdac5e5342202e623c1d712ccf78
+size 10674

runs/May27_10-57-42_DESK-HO-74960/events.out.tfevents.1716787667.DESK-HO-74960.19572.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48dace8bbb86456d578a266f2760849d0433c8b122b97623ff8542e565a65b43
+size 9129

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 +1,46 @@
+{
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38191b47b5adae85baedf9a148e4033ea9235eb86eb0c93b4b8a7a2aa188c733
+size 5176