checkpoint-6739 | step 6739 | loss 0.1934 | 16.8% complete

.gitattributes

@@ -43,3 +43,4 @@ checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-6326/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6739/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-6739/README.md

@@ -0,0 +1,201 @@
+# ScriptSwiftAI v12 (Dikshan)
+
+> QLoRA fine-tuned full-stack code generation model by **Dikshan** (India).
+> Covers Python, Django, Flask, FastAPI, React, Next.js, TypeScript, SQL, Docker.
+
+---
+
+## License
+
+**CC BY-NC 4.0** — Non-commercial use only. Must credit Dikshan / ScriptSwiftAI.
+https://creativecommons.org/licenses/by-nc/4.0/
+
+**Copyright © 2026 Dikshan. All rights reserved.**
+
+---
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| **Base Model** | Qwen2.5-Coder-7B-Instruct |
+| **Method** | QLoRA (4-bit, r=64) |
+| **Hardware** | NVIDIA RTX 5070 Ti 16GB |
+| **Target Steps** | 40,000 |
+| **Dataset** | ~450-500k samples (17 datasets) |
+| **Max Length** | 1536 tokens |
+| **Developer** | Dikshan (India) |
+| **Training Started** | June 2026 |
+
+---
+
+## Changelog / Training Timeline
+
+*Auto-updated by train_v12.py on every checkpoint save.*
+*Append-only — entries never overwritten. HuggingFace commit history provides timestamps.*
+
+
+---
+
+### 🔵 Checkpoint — Step 13
+**Date:** June 22, 2026 at 18:44 IST
+**Checkpoint:** checkpoint-13
+**Step:** 13 / 40,000 (0.0% complete)
+**Loss:** 0.6164
+**Epoch:** 0.000
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 25
+**Date:** June 22, 2026 at 18:50 IST
+**Checkpoint:** checkpoint-25
+**Step:** 25 / 40,000 (0.1% complete)
+**Loss:** 0.6057
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 36
+**Date:** June 22, 2026 at 18:58 IST
+**Checkpoint:** checkpoint-36
+**Step:** 36 / 40,000 (0.1% complete)
+**Loss:** 0.5508
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 42
+**Date:** June 22, 2026 at 19:08 IST
+**Checkpoint:** checkpoint-42
+**Step:** 42 / 40,000 (0.1% complete)
+**Loss:** 0.5525
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 538
+**Date:** June 22, 2026 at 23:38 IST
+**Checkpoint:** checkpoint-538
+**Step:** 538 / 40,000 (1.3% complete)
+**Loss:** 0.4087
+**Epoch:** 0.015
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 1,000
+**Date:** June 23, 2026 at 03:05 IST
+**Checkpoint:** checkpoint-1000
+**Step:** 1,000 / 40,000 (2.5% complete)
+**Loss:** 0.4174
+**Epoch:** 0.029
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 1,797
+**Date:** June 23, 2026 at 08:26 IST
+**Checkpoint:** checkpoint-1797
+**Step:** 1,797 / 40,000 (4.5% complete)
+**Loss:** 0.3927
+**Epoch:** 0.052
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 2,000
+**Date:** June 23, 2026 at 09:52 IST
+**Checkpoint:** checkpoint-2000
+**Step:** 2,000 / 40,000 (5.0% complete)
+**Loss:** 0.4383
+**Epoch:** 0.058
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 3,000
+**Date:** June 23, 2026 at 17:35 IST
+**Checkpoint:** checkpoint-3000
+**Step:** 3,000 / 40,000 (7.5% complete)
+**Loss:** 0.4153
+**Epoch:** 0.088
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 3,876
+**Date:** June 23, 2026 at 23:40 IST
+**Checkpoint:** checkpoint-3876
+**Step:** 3,876 / 40,000 (9.7% complete)
+**Loss:** 0.3439
+**Epoch:** 0.113
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 4,000
+**Date:** June 24, 2026 at 00:54 IST
+**Checkpoint:** checkpoint-4000
+**Step:** 4,000 / 40,000 (10.0% complete)
+**Loss:** 0.3980
+**Epoch:** 0.117
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 5,000
+**Date:** June 24, 2026 at 07:38 IST
+**Checkpoint:** checkpoint-5000
+**Step:** 5,000 / 40,000 (12.5% complete)
+**Loss:** 0.2748
+**Epoch:** 0.146
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 6,000
+**Date:** June 24, 2026 at 14:22 IST
+**Checkpoint:** checkpoint-6000
+**Step:** 6,000 / 40,000 (15.0% complete)
+**Loss:** 0.2319
+**Epoch:** 0.175
+**Zone:** 🎯 Sweet Spot
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 6,326
+**Date:** June 24, 2026 at 19:59 IST
+**Checkpoint:** checkpoint-6326
+**Step:** 6,326 / 40,000 (15.8% complete)
+**Loss:** 0.2695
+**Epoch:** 0.185
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 6,739
+**Date:** June 24, 2026 at 23:37 IST
+**Checkpoint:** checkpoint-6739
+**Step:** 6,739 / 40,000 (16.8% complete)
+**Loss:** 0.1934
+**Epoch:** 0.197
+**Zone:** 🎯 Sweet Spot
+**Status:** Training ongoing — auto-uploaded via train_v12.py

checkpoint-6739/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-6739/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b33310d0d3715a41f2ebb5f4d43e98f71839a66a7c5b6d0d70666bd85f99811
+size 645975704

checkpoint-6739/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-6739/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e54d1c23b4cfd9e22d24230985f5cf591cddbef351c75c1a300e40d9a6aab7c
+size 329492947

checkpoint-6739/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cdc1633346b195cb35e1ae4153bf8b3f2c224eb90002d6d6e9408b02031948
+size 14645

checkpoint-6739/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77af194d1b98aa515991fd89bdf4593d8dd82b0add9a169de9d8685f2fda0443
+size 1465

checkpoint-6739/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-6739/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-6739/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ab51bd599651344f26a67a1d940a2b6432da90051bdf388dcef2423ea1342d
+size 5329