checkpoint-42 | step 42 | loss 0.5525 | 0.1% complete

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-42/README.md

@@ -0,0 +1,80 @@
+# 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-42/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": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_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-42/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce17ca8008ffb1ed1d0cc497c54038ef77792dac1212e4cd16b8443ae1a550f2
+size 645975704

checkpoint-42/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-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93bfc634f201a9fd425a1007f5c7f96538afe06795e6abb2afc19e999a84e64e
+size 329492499

checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03c2a998d70d4985257c1d453213a9f6370518bd080e81345911b743c20b4d6
+size 14645

checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4deb6569d5c23d884449c04303963357ac2b50c41eaf05a3009247ad73d2be22
+size 1465

checkpoint-42/tokenizer.json

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

checkpoint-42/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-42/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.00017536776996132774,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002922796166022129,
+      "grad_norm": 0.3604201674461365,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6163836479187011,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005845592332044258,
+      "grad_norm": 0.307494193315506,
+      "learning_rate": 3.8e-06,
+      "loss": 0.6056640148162842,
+      "step": 20
+    },
+    {
+      "epoch": 0.00014613980830110646,
+      "grad_norm": 0.1861964464187622,
+      "learning_rate": 5.8e-06,
+      "loss": 0.5507771968841553,
+      "step": 30
+    },
+    {
+      "epoch": 0.00011691184664088517,
+      "grad_norm": 0.18063770234584808,
+      "learning_rate": 7.8e-06,
+      "loss": 0.5524736642837524,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 40000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.478949358829568e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-42/training_args.bin

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