Training in progress, step 1250

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: stabilityai/stable-code-instruct-3b
 library_name: transformers
-model_name: StableCode-text2SQL-alias-indentacao
+model_name: StableCode-text2SQL-withoutquantization
 tags:
 - generated_from_trainer
 - trl
@@ -9,7 +9,7 @@ tags:
 licence: license
 ---
 
-# Model Card for StableCode-text2SQL-alias-indentacao
+# Model Card for StableCode-text2SQL-withoutquantization
 
 This model is a fine-tuned version of [stabilityai/stable-code-instruct-3b](https://huggingface.co/stabilityai/stable-code-instruct-3b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,24 +20,25 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="lleticiasilvaa/StableCode-text2SQL-alias-indentacao", device="cuda")
+generator = pipeline("text-generation", model="lleticiasilvaa/StableCode-text2SQL-withoutquantization", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.0
-- Transformers: 4.46.2
-- Pytorch: 2.5.0+cu121
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- TRL: 0.13.0
+- Transformers: 4.47.1
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -6,6 +6,8 @@
   },
   "base_model_name_or_path": "stabilityai/stable-code-instruct-3b",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -14,6 +16,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "down_proj"
+    "q_proj",
+    "up_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab32c23cca063b93ae2b88c96355b5cc260795d91ee4cf1b08c5f5bb776b507
+oid sha256:0f9c750d51f6519dc289b70fa45af7dd6c73dd07f65d521798ef808e1ef90c24
 size 400616360

logs/events.out.tfevents.1735923028.1356149f6382.358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f024c1e2d4631c2b2cba7a7cd69bf12510b023147029fc09c0bd2b4d298bd5c
+size 10670

logs/events.out.tfevents.1736189043.154f07f7b0d9.1770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:411d2371102f8c8e78ffb5b7931c855affd4e6ceb77b4226bf5ed42c248f1da0
+size 10325

logs/events.out.tfevents.1736193007.154f07f7b0d9.1770.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9c14789027d905f61df5a045ef15dceff49a4a059ff1afaf2251bf2fb8dc73
+size 6341

logs/events.out.tfevents.1736193779.154f07f7b0d9.1770.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fe71fc6491fcac0f506994f9ac674e695e3ac8e16942355319b76cd060841f
+size 6467

tokenizer_config.json

@@ -384,6 +384,7 @@
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "map_device": "auto",
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3dedd34988f1200d6dd0bdca9a10b85e9fdb9d16cf44025625c8ff185de71a
+oid sha256:37d85e10062490083f3df78142b22b936ee4c10ad7bb1c35d68c6a9743be03a9
 size 5560