Remove superseded v2.0 paths for 10k DoRA+ experiment

reports/v2.0/doraplus/reports_training/qwen3-0.6b_D_10k_20260827_213058.json

@@ -1,164 +0,0 @@
-{
-  "model_key": "qwen3-0.6b",
-  "model_id": "Qwen/Qwen3-0.6B",
-  "lora_config": "D",
-  "lora_config_desc": "Heavy — full attention + MLP, rank 32",
-  "dataset_size": "10k",
-  "technique": "DoRA+",
-  "device": "cuda",
-  "dtype": "bfloat16",
-  "timestamp": "20260827_213058",
-  "prompt_format": "tool_id_v1",
-  "tool_id_scheme": "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
-  "no_tool_id": "-",
-  "gradient_checkpointing": true,
-  "trainable_params": 20529152,
-  "total_params": 616579072,
-  "trainable_pct": 3.3295,
-  "steps_per_epoch": 500,
-  "total_steps_trained": 1250,
-  "early_stopped": true,
-  "early_stopping_patience": 2,
-  "early_stopping_threshold": 0.001,
-  "peak_memory_mb": 4593.3,
-  "total_training_time_s": 9873.2,
-  "final_train_loss": 0.03305,
-  "final_eval_loss": 0.002246,
-  "final_val_accuracy": 1.0,
-  "final_train_accuracy": 1.0,
-  "hf_repo": "kon172verma/intent-classifier-experiments",
-  "hf_subfolder": "v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047",
-  "version": "v2.0",
-  "log_history": [
-    {
-      "loss": 0.12966786193847657,
-      "grad_norm": 2.364213466644287,
-      "learning_rate": 4.9245121086159674e-05,
-      "entropy": 0.05329545314458665,
-      "num_tokens": 1516296.0,
-      "mean_token_accuracy": 0.9799166703224182,
-      "epoch": 0.5,
-      "step": 250
-    },
-    {
-      "eval_loss": 0.04242685064673424,
-      "eval_model_preparation_time": 0.0208,
-      "eval_runtime": 83.6812,
-      "eval_samples_per_second": 11.95,
-      "eval_steps_per_second": 1.494,
-      "eval_entropy": 0.02787096245959401,
-      "eval_num_tokens": 1516296.0,
-      "eval_mean_token_accuracy": 0.9943333320617675,
-      "epoch": 0.5,
-      "step": 250,
-      "train_accuracy": 1.0,
-      "eval_accuracy": 0.97
-    },
-    {
-      "loss": 0.014683025360107422,
-      "grad_norm": 3.3569235801696777,
-      "learning_rate": 4.4753875309392266e-05,
-      "entropy": 0.007536330722155981,
-      "num_tokens": 3035617.0,
-      "mean_token_accuracy": 0.9975833353996277,
-      "epoch": 1.0,
-      "step": 500
-    },
-    {
-      "eval_loss": 0.012298869900405407,
-      "eval_model_preparation_time": 0.0208,
-      "eval_runtime": 83.5578,
-      "eval_samples_per_second": 11.968,
-      "eval_steps_per_second": 1.496,
-      "eval_entropy": 0.011986315403133632,
-      "eval_num_tokens": 3035617.0,
-      "eval_mean_token_accuracy": 0.9966666650772095,
-      "epoch": 1.0,
-      "step": 500,
-      "train_accuracy": 1.0,
-      "eval_accuracy": 0.99
-    },
-    {
-      "loss": 0.016262353897094725,
-      "grad_norm": 0.004455740563571453,
-      "learning_rate": 3.693502312666304e-05,
-      "entropy": 0.007805552490521222,
-      "num_tokens": 4550488.0,
-      "mean_token_accuracy": 0.99775000166893,
-      "epoch": 1.5,
-      "step": 750
-    },
-    {
-      "eval_loss": 0.0012079532025381923,
-      "eval_model_preparation_time": 0.0208,
-      "eval_runtime": 83.6801,
-      "eval_samples_per_second": 11.95,
-      "eval_steps_per_second": 1.494,
-      "eval_entropy": 0.0037327693440020082,
-      "eval_num_tokens": 4550488.0,
-      "eval_mean_token_accuracy": 0.999666666507721,
-      "epoch": 1.5,
-      "step": 750,
-      "train_accuracy": 1.0,
-      "eval_accuracy": 1.0
-    },
-    {
-      "loss": 0.003704591512680054,
-      "grad_norm": 0.0007531999726779759,
-      "learning_rate": 2.7105676355426248e-05,
-      "entropy": 0.003422930711181834,
-      "num_tokens": 6071234.0,
-      "mean_token_accuracy": 0.9995000004768372,
-      "epoch": 2.0,
-      "step": 1000
-    },
-    {
-      "eval_loss": 0.0042778607457876205,
-      "eval_model_preparation_time": 0.0208,
-      "eval_runtime": 83.828,
-      "eval_samples_per_second": 11.929,
-      "eval_steps_per_second": 1.491,
-      "eval_entropy": 0.0005781573285348713,
-      "eval_num_tokens": 6071234.0,
-      "eval_mean_token_accuracy": 0.999666666507721,
-      "epoch": 2.0,
-      "step": 1000,
-      "train_accuracy": 1.0,
-      "eval_accuracy": 1.0
-    },
-    {
-      "loss": 0.00093178790807724,
-      "grad_norm": 0.000455356523161754,
-      "learning_rate": 1.6921621355072144e-05,
-      "entropy": 0.0006047176675638184,
-      "num_tokens": 7586814.0,
-      "mean_token_accuracy": 0.9999166667461395,
-      "epoch": 2.5,
-      "step": 1250
-    },
-    {
-      "eval_loss": 0.002245673444122076,
-      "eval_model_preparation_time": 0.0208,
-      "eval_runtime": 83.7139,
-      "eval_samples_per_second": 11.945,
-      "eval_steps_per_second": 1.493,
-      "eval_entropy": 0.000366206516395323,
-      "eval_num_tokens": 7586814.0,
-      "eval_mean_token_accuracy": 0.999666666507721,
-      "epoch": 2.5,
-      "step": 1250,
-      "train_accuracy": 1.0,
-      "eval_accuracy": 1.0
-    },
-    {
-      "train_runtime": 9872.6045,
-      "train_samples_per_second": 3.241,
-      "train_steps_per_second": 0.203,
-      "total_flos": 3.82456210218025e+16,
-      "train_loss": 0.0330499241232872,
-      "epoch": 2.5,
-      "step": 1250
-    }
-  ],
-  "hf_report_path": "reports/v2.0/doraplus/reports_training/qwen3-0.6b_D_10k_20260827_213058.json"
-}

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3-0.6B
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3-0.6B
-- lora
-- sft
-- transformers
-- trl
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.20.0

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/adapter_config.json

@@ -1,50 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
-  "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": 64,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.20.0",
-  "qalora_group_size": 16,
-  "r": 32,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "q_proj",
-    "gate_proj",
-    "down_proj",
-    "o_proj",
-    "k_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": true,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52ae0d59cc9b17cdbbbb726537c1900f1d00852c1f4e1e58309c8a9287c7263c
-size 82195720

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/chat_template.jinja

@@ -1,89 +0,0 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
-    {%- endif %}
-    {{- "# 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' }}
-    {%- endif %}
-{%- endif %}
-{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
-    {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
-        {%- set ns.multi_step_tool = false %}
-        {%- set ns.last_query_index = index %}
-    {%- endif %}
-{%- endfor %}
-{%- for message in messages %}
-    {%- if message.content is string %}
-        {%- set content = message.content %}
-    {%- else %}
-        {%- set content = '' %}
-    {%- endif %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
-        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is string %}
-            {%- set reasoning_content = message.reasoning_content %}
-        {%- else %}
-            {%- if '</think>' in content %}
-                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-            {%- endif %}
-        {%- endif %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {%- if loop.last or (not loop.last and reasoning_content) %}
-                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
-            {%- else %}
-                {{- '<|im_start|>' + message.role + '\n' + content }}
-            {%- endif %}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if (loop.first and content) or (not loop.first) %}
-                    {{- '\n' }}
-                {%- endif %}
-                {%- if tool_call.function %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {{- '<tool_call>\n{"name": "' }}
-                {{- tool_call.name }}
-                {{- '", "arguments": ' }}
-                {%- if tool_call.arguments is string %}
-                    {{- tool_call.arguments }}
-                {%- else %}
-                    {{- tool_call.arguments | tojson }}
-                {%- endif %}
-                {{- '}\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- 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' }}
-    {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
-size 11422650

v2.0/qwen3-0.6b_DoRA+_D_10k_20260827-213047/tokenizer_config.json

@@ -1,30 +0,0 @@
-{
-  "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": 131072,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}