Clean up old checkpoints in substitutivity_original_Estonian before re-upload

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/README.md

@@ -1,58 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: transformers
-model_name: Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1
-tags:
-- generated_from_trainer
-- sft
-- trl
-licence: license
----
-
-# Model Card for Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1
-
-This model is a fine-tuned version of [Qwen/Qwen3.5-2B-Base](https://huggingface.co/Qwen/Qwen3.5-2B-Base).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-
-## Quick start
-
-```python
-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="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
-
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/katriin-kukk/Cross_lingual_morphological_generalization/runs/x2lpl94k) 
-
-
-
-This model was trained with SFT.
-
-### Framework versions
-
-- TRL: 0.29.0
-- Transformers: 5.5.4
-- Pytorch: 2.10.0
-- Datasets: 4.6.1
-- Tokenizers: 0.22.2
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@software{vonwerra2020trl,
-  title   = {{TRL: Transformers Reinforcement Learning}},
-  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
-  license = {Apache-2.0},
-  url     = {https://github.com/huggingface/trl},
-  year    = {2020}
-}
-```

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9cafaedfbb8f3542e770b5e614799acc29b354bf5a88410c70c9298fdd7e383a
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/trainer_state.json

@@ -1,340 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 1245,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 6.34152082269024e+16,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1245/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83d8bc1e85309f49a0aa7ffc2f3abfdb68bfe02366a8bcb68a350ceeb1adc7e2
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/trainer_state.json

@@ -1,452 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 4.0,
-  "eval_steps": 500,
-  "global_step": 1660,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    },
-    {
-      "entropy": 0.6077835421369533,
-      "epoch": 3.012062726176116,
-      "grad_norm": 1.124720573425293,
-      "learning_rate": 0.00011713897584164003,
-      "loss": 0.5557136917114258,
-      "mean_token_accuracy": 0.8203362726201915,
-      "num_tokens": 2994602.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.507642827630043,
-      "epoch": 3.132689987937274,
-      "grad_norm": 0.9039916396141052,
-      "learning_rate": 0.00011529219281884579,
-      "loss": 0.4467372512817383,
-      "mean_token_accuracy": 0.8464260965585708,
-      "num_tokens": 3121094.0,
-      "step": 1300
-    },
-    {
-      "entropy": 0.5137191081047058,
-      "epoch": 3.2533172496984317,
-      "grad_norm": 0.8580691814422607,
-      "learning_rate": 0.00011335896360860367,
-      "loss": 0.4538694763183594,
-      "mean_token_accuracy": 0.8448719161748887,
-      "num_tokens": 3248038.0,
-      "step": 1350
-    },
-    {
-      "entropy": 0.5293738862872124,
-      "epoch": 3.37394451145959,
-      "grad_norm": 1.0177273750305176,
-      "learning_rate": 0.00011134270704383492,
-      "loss": 0.4639348220825195,
-      "mean_token_accuracy": 0.8428975892066956,
-      "num_tokens": 3363487.0,
-      "step": 1400
-    },
-    {
-      "entropy": 0.5218872320652008,
-      "epoch": 3.494571773220748,
-      "grad_norm": 1.0530673265457153,
-      "learning_rate": 0.00010924698878777538,
-      "loss": 0.4584346389770508,
-      "mean_token_accuracy": 0.8432288640737533,
-      "num_tokens": 3480513.0,
-      "step": 1450
-    },
-    {
-      "entropy": 0.5320372316241264,
-      "epoch": 3.615199034981906,
-      "grad_norm": 1.0291194915771484,
-      "learning_rate": 0.0001070755150282529,
-      "loss": 0.4711898422241211,
-      "mean_token_accuracy": 0.842066935300827,
-      "num_tokens": 3597183.0,
-      "step": 1500
-    },
-    {
-      "entropy": 0.5315000694990158,
-      "epoch": 3.7358262967430638,
-      "grad_norm": 0.9788838624954224,
-      "learning_rate": 0.00010483212592345332,
-      "loss": 0.4729101943969727,
-      "mean_token_accuracy": 0.8404586082696914,
-      "num_tokens": 3714173.0,
-      "step": 1550
-    },
-    {
-      "entropy": 0.5331643190979958,
-      "epoch": 3.856453558504222,
-      "grad_norm": 1.1248903274536133,
-      "learning_rate": 0.00010252078881076532,
-      "loss": 0.47405517578125,
-      "mean_token_accuracy": 0.8397526168823242,
-      "num_tokens": 3832652.0,
-      "step": 1600
-    },
-    {
-      "entropy": 0.5343865439295769,
-      "epoch": 3.97708082026538,
-      "grad_norm": 0.9008272886276245,
-      "learning_rate": 0.00010014559119071452,
-      "loss": 0.47172779083251953,
-      "mean_token_accuracy": 0.8404951041936874,
-      "num_tokens": 3955167.0,
-      "step": 1650
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5736920103598177,
-      "eval_mean_token_accuracy": 0.7981750027517255,
-      "eval_not_syn_loss": 0.707631528377533,
-      "eval_not_syn_runtime": 52.2858,
-      "eval_not_syn_samples_per_second": 27.158,
-      "eval_not_syn_steps_per_second": 3.404,
-      "eval_num_tokens": 3975224.0,
-      "step": 1660
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5363499959198277,
-      "eval_mean_token_accuracy": 0.8063885539435269,
-      "eval_num_tokens": 3975224.0,
-      "eval_syn_loss": 0.6610181331634521,
-      "eval_syn_runtime": 54.2167,
-      "eval_syn_samples_per_second": 26.191,
-      "eval_syn_steps_per_second": 3.283,
-      "step": 1660
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 8.481153412421376e+16,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-1660/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae3992049a09e84745f3e9ff29b6582c4efb1c244af17d72f891cb248b6e4593
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/trainer_state.json

@@ -1,554 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 5.0,
-  "eval_steps": 500,
-  "global_step": 2075,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    },
-    {
-      "entropy": 0.6077835421369533,
-      "epoch": 3.012062726176116,
-      "grad_norm": 1.124720573425293,
-      "learning_rate": 0.00011713897584164003,
-      "loss": 0.5557136917114258,
-      "mean_token_accuracy": 0.8203362726201915,
-      "num_tokens": 2994602.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.507642827630043,
-      "epoch": 3.132689987937274,
-      "grad_norm": 0.9039916396141052,
-      "learning_rate": 0.00011529219281884579,
-      "loss": 0.4467372512817383,
-      "mean_token_accuracy": 0.8464260965585708,
-      "num_tokens": 3121094.0,
-      "step": 1300
-    },
-    {
-      "entropy": 0.5137191081047058,
-      "epoch": 3.2533172496984317,
-      "grad_norm": 0.8580691814422607,
-      "learning_rate": 0.00011335896360860367,
-      "loss": 0.4538694763183594,
-      "mean_token_accuracy": 0.8448719161748887,
-      "num_tokens": 3248038.0,
-      "step": 1350
-    },
-    {
-      "entropy": 0.5293738862872124,
-      "epoch": 3.37394451145959,
-      "grad_norm": 1.0177273750305176,
-      "learning_rate": 0.00011134270704383492,
-      "loss": 0.4639348220825195,
-      "mean_token_accuracy": 0.8428975892066956,
-      "num_tokens": 3363487.0,
-      "step": 1400
-    },
-    {
-      "entropy": 0.5218872320652008,
-      "epoch": 3.494571773220748,
-      "grad_norm": 1.0530673265457153,
-      "learning_rate": 0.00010924698878777538,
-      "loss": 0.4584346389770508,
-      "mean_token_accuracy": 0.8432288640737533,
-      "num_tokens": 3480513.0,
-      "step": 1450
-    },
-    {
-      "entropy": 0.5320372316241264,
-      "epoch": 3.615199034981906,
-      "grad_norm": 1.0291194915771484,
-      "learning_rate": 0.0001070755150282529,
-      "loss": 0.4711898422241211,
-      "mean_token_accuracy": 0.842066935300827,
-      "num_tokens": 3597183.0,
-      "step": 1500
-    },
-    {
-      "entropy": 0.5315000694990158,
-      "epoch": 3.7358262967430638,
-      "grad_norm": 0.9788838624954224,
-      "learning_rate": 0.00010483212592345332,
-      "loss": 0.4729101943969727,
-      "mean_token_accuracy": 0.8404586082696914,
-      "num_tokens": 3714173.0,
-      "step": 1550
-    },
-    {
-      "entropy": 0.5331643190979958,
-      "epoch": 3.856453558504222,
-      "grad_norm": 1.1248903274536133,
-      "learning_rate": 0.00010252078881076532,
-      "loss": 0.47405517578125,
-      "mean_token_accuracy": 0.8397526168823242,
-      "num_tokens": 3832652.0,
-      "step": 1600
-    },
-    {
-      "entropy": 0.5343865439295769,
-      "epoch": 3.97708082026538,
-      "grad_norm": 0.9008272886276245,
-      "learning_rate": 0.00010014559119071452,
-      "loss": 0.47172779083251953,
-      "mean_token_accuracy": 0.8404951041936874,
-      "num_tokens": 3955167.0,
-      "step": 1650
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5736920103598177,
-      "eval_mean_token_accuracy": 0.7981750027517255,
-      "eval_not_syn_loss": 0.707631528377533,
-      "eval_not_syn_runtime": 52.2858,
-      "eval_not_syn_samples_per_second": 27.158,
-      "eval_not_syn_steps_per_second": 3.404,
-      "eval_num_tokens": 3975224.0,
-      "step": 1660
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5363499959198277,
-      "eval_mean_token_accuracy": 0.8063885539435269,
-      "eval_num_tokens": 3975224.0,
-      "eval_syn_loss": 0.6610181331634521,
-      "eval_syn_runtime": 54.2167,
-      "eval_syn_samples_per_second": 26.191,
-      "eval_syn_steps_per_second": 3.283,
-      "step": 1660
-    },
-    {
-      "entropy": 0.4512602482179199,
-      "epoch": 4.0965018094089265,
-      "grad_norm": 0.8079906105995178,
-      "learning_rate": 9.771073349839416e-05,
-      "loss": 0.3778452682495117,
-      "mean_token_accuracy": 0.8684436221315404,
-      "num_tokens": 4072361.0,
-      "step": 1700
-    },
-    {
-      "entropy": 0.4228873434662819,
-      "epoch": 4.217129071170085,
-      "grad_norm": 1.1206746101379395,
-      "learning_rate": 9.52205216751758e-05,
-      "loss": 0.34671127319335937,
-      "mean_token_accuracy": 0.8763950079679489,
-      "num_tokens": 4194978.0,
-      "step": 1750
-    },
-    {
-      "entropy": 0.42808119297027586,
-      "epoch": 4.337756332931242,
-      "grad_norm": 1.1268125772476196,
-      "learning_rate": 9.26793595538368e-05,
-      "loss": 0.3484600830078125,
-      "mean_token_accuracy": 0.8753323918581009,
-      "num_tokens": 4315548.0,
-      "step": 1800
-    },
-    {
-      "entropy": 0.42506767451763156,
-      "epoch": 4.458383594692401,
-      "grad_norm": 1.1051807403564453,
-      "learning_rate": 9.009174107057088e-05,
-      "loss": 0.35434780120849607,
-      "mean_token_accuracy": 0.8734411865472793,
-      "num_tokens": 4431469.0,
-      "step": 1850
-    },
-    {
-      "entropy": 0.43314908266067503,
-      "epoch": 4.579010856453559,
-      "grad_norm": 0.9782640337944031,
-      "learning_rate": 8.746224231765484e-05,
-      "loss": 0.36225860595703124,
-      "mean_token_accuracy": 0.8715140378475189,
-      "num_tokens": 4551803.0,
-      "step": 1900
-    },
-    {
-      "entropy": 0.42984022706747055,
-      "epoch": 4.699638118214716,
-      "grad_norm": 0.9772566556930542,
-      "learning_rate": 8.479551345082568e-05,
-      "loss": 0.356609001159668,
-      "mean_token_accuracy": 0.8717925781011582,
-      "num_tokens": 4674468.0,
-      "step": 1950
-    },
-    {
-      "entropy": 0.4474307084083557,
-      "epoch": 4.820265379975875,
-      "grad_norm": 0.9547265768051147,
-      "learning_rate": 8.209627046567966e-05,
-      "loss": 0.3654902267456055,
-      "mean_token_accuracy": 0.8724055212736129,
-      "num_tokens": 4788027.0,
-      "step": 2000
-    },
-    {
-      "entropy": 0.4377285006642342,
-      "epoch": 4.940892641737032,
-      "grad_norm": 1.0390652418136597,
-      "learning_rate": 7.936928685763635e-05,
-      "loss": 0.3645761871337891,
-      "mean_token_accuracy": 0.8707609891891479,
-      "num_tokens": 4907561.0,
-      "step": 2050
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.5173388388049737,
-      "eval_mean_token_accuracy": 0.7918405432379647,
-      "eval_not_syn_loss": 0.7532826662063599,
-      "eval_not_syn_runtime": 53.0766,
-      "eval_not_syn_samples_per_second": 26.754,
-      "eval_not_syn_steps_per_second": 3.354,
-      "eval_num_tokens": 4969030.0,
-      "step": 2075
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.4831916272975086,
-      "eval_mean_token_accuracy": 0.8204237202580056,
-      "eval_num_tokens": 4969030.0,
-      "eval_syn_loss": 0.6971890330314636,
-      "eval_syn_runtime": 54.8755,
-      "eval_syn_samples_per_second": 25.877,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 2075
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.0572192305263104e+17,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2075/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:275a7bde3ab6e98ce13f2b9e139f10d35926ca663e5d15c5533c4b1e5cf007af
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/trainer_state.json

@@ -1,656 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 6.0,
-  "eval_steps": 500,
-  "global_step": 2490,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    },
-    {
-      "entropy": 0.6077835421369533,
-      "epoch": 3.012062726176116,
-      "grad_norm": 1.124720573425293,
-      "learning_rate": 0.00011713897584164003,
-      "loss": 0.5557136917114258,
-      "mean_token_accuracy": 0.8203362726201915,
-      "num_tokens": 2994602.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.507642827630043,
-      "epoch": 3.132689987937274,
-      "grad_norm": 0.9039916396141052,
-      "learning_rate": 0.00011529219281884579,
-      "loss": 0.4467372512817383,
-      "mean_token_accuracy": 0.8464260965585708,
-      "num_tokens": 3121094.0,
-      "step": 1300
-    },
-    {
-      "entropy": 0.5137191081047058,
-      "epoch": 3.2533172496984317,
-      "grad_norm": 0.8580691814422607,
-      "learning_rate": 0.00011335896360860367,
-      "loss": 0.4538694763183594,
-      "mean_token_accuracy": 0.8448719161748887,
-      "num_tokens": 3248038.0,
-      "step": 1350
-    },
-    {
-      "entropy": 0.5293738862872124,
-      "epoch": 3.37394451145959,
-      "grad_norm": 1.0177273750305176,
-      "learning_rate": 0.00011134270704383492,
-      "loss": 0.4639348220825195,
-      "mean_token_accuracy": 0.8428975892066956,
-      "num_tokens": 3363487.0,
-      "step": 1400
-    },
-    {
-      "entropy": 0.5218872320652008,
-      "epoch": 3.494571773220748,
-      "grad_norm": 1.0530673265457153,
-      "learning_rate": 0.00010924698878777538,
-      "loss": 0.4584346389770508,
-      "mean_token_accuracy": 0.8432288640737533,
-      "num_tokens": 3480513.0,
-      "step": 1450
-    },
-    {
-      "entropy": 0.5320372316241264,
-      "epoch": 3.615199034981906,
-      "grad_norm": 1.0291194915771484,
-      "learning_rate": 0.0001070755150282529,
-      "loss": 0.4711898422241211,
-      "mean_token_accuracy": 0.842066935300827,
-      "num_tokens": 3597183.0,
-      "step": 1500
-    },
-    {
-      "entropy": 0.5315000694990158,
-      "epoch": 3.7358262967430638,
-      "grad_norm": 0.9788838624954224,
-      "learning_rate": 0.00010483212592345332,
-      "loss": 0.4729101943969727,
-      "mean_token_accuracy": 0.8404586082696914,
-      "num_tokens": 3714173.0,
-      "step": 1550
-    },
-    {
-      "entropy": 0.5331643190979958,
-      "epoch": 3.856453558504222,
-      "grad_norm": 1.1248903274536133,
-      "learning_rate": 0.00010252078881076532,
-      "loss": 0.47405517578125,
-      "mean_token_accuracy": 0.8397526168823242,
-      "num_tokens": 3832652.0,
-      "step": 1600
-    },
-    {
-      "entropy": 0.5343865439295769,
-      "epoch": 3.97708082026538,
-      "grad_norm": 0.9008272886276245,
-      "learning_rate": 0.00010014559119071452,
-      "loss": 0.47172779083251953,
-      "mean_token_accuracy": 0.8404951041936874,
-      "num_tokens": 3955167.0,
-      "step": 1650
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5736920103598177,
-      "eval_mean_token_accuracy": 0.7981750027517255,
-      "eval_not_syn_loss": 0.707631528377533,
-      "eval_not_syn_runtime": 52.2858,
-      "eval_not_syn_samples_per_second": 27.158,
-      "eval_not_syn_steps_per_second": 3.404,
-      "eval_num_tokens": 3975224.0,
-      "step": 1660
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5363499959198277,
-      "eval_mean_token_accuracy": 0.8063885539435269,
-      "eval_num_tokens": 3975224.0,
-      "eval_syn_loss": 0.6610181331634521,
-      "eval_syn_runtime": 54.2167,
-      "eval_syn_samples_per_second": 26.191,
-      "eval_syn_steps_per_second": 3.283,
-      "step": 1660
-    },
-    {
-      "entropy": 0.4512602482179199,
-      "epoch": 4.0965018094089265,
-      "grad_norm": 0.8079906105995178,
-      "learning_rate": 9.771073349839416e-05,
-      "loss": 0.3778452682495117,
-      "mean_token_accuracy": 0.8684436221315404,
-      "num_tokens": 4072361.0,
-      "step": 1700
-    },
-    {
-      "entropy": 0.4228873434662819,
-      "epoch": 4.217129071170085,
-      "grad_norm": 1.1206746101379395,
-      "learning_rate": 9.52205216751758e-05,
-      "loss": 0.34671127319335937,
-      "mean_token_accuracy": 0.8763950079679489,
-      "num_tokens": 4194978.0,
-      "step": 1750
-    },
-    {
-      "entropy": 0.42808119297027586,
-      "epoch": 4.337756332931242,
-      "grad_norm": 1.1268125772476196,
-      "learning_rate": 9.26793595538368e-05,
-      "loss": 0.3484600830078125,
-      "mean_token_accuracy": 0.8753323918581009,
-      "num_tokens": 4315548.0,
-      "step": 1800
-    },
-    {
-      "entropy": 0.42506767451763156,
-      "epoch": 4.458383594692401,
-      "grad_norm": 1.1051807403564453,
-      "learning_rate": 9.009174107057088e-05,
-      "loss": 0.35434780120849607,
-      "mean_token_accuracy": 0.8734411865472793,
-      "num_tokens": 4431469.0,
-      "step": 1850
-    },
-    {
-      "entropy": 0.43314908266067503,
-      "epoch": 4.579010856453559,
-      "grad_norm": 0.9782640337944031,
-      "learning_rate": 8.746224231765484e-05,
-      "loss": 0.36225860595703124,
-      "mean_token_accuracy": 0.8715140378475189,
-      "num_tokens": 4551803.0,
-      "step": 1900
-    },
-    {
-      "entropy": 0.42984022706747055,
-      "epoch": 4.699638118214716,
-      "grad_norm": 0.9772566556930542,
-      "learning_rate": 8.479551345082568e-05,
-      "loss": 0.356609001159668,
-      "mean_token_accuracy": 0.8717925781011582,
-      "num_tokens": 4674468.0,
-      "step": 1950
-    },
-    {
-      "entropy": 0.4474307084083557,
-      "epoch": 4.820265379975875,
-      "grad_norm": 0.9547265768051147,
-      "learning_rate": 8.209627046567966e-05,
-      "loss": 0.3654902267456055,
-      "mean_token_accuracy": 0.8724055212736129,
-      "num_tokens": 4788027.0,
-      "step": 2000
-    },
-    {
-      "entropy": 0.4377285006642342,
-      "epoch": 4.940892641737032,
-      "grad_norm": 1.0390652418136597,
-      "learning_rate": 7.936928685763635e-05,
-      "loss": 0.3645761871337891,
-      "mean_token_accuracy": 0.8707609891891479,
-      "num_tokens": 4907561.0,
-      "step": 2050
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.5173388388049737,
-      "eval_mean_token_accuracy": 0.7918405432379647,
-      "eval_not_syn_loss": 0.7532826662063599,
-      "eval_not_syn_runtime": 53.0766,
-      "eval_not_syn_samples_per_second": 26.754,
-      "eval_not_syn_steps_per_second": 3.354,
-      "eval_num_tokens": 4969030.0,
-      "step": 2075
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.4831916272975086,
-      "eval_mean_token_accuracy": 0.8204237202580056,
-      "eval_num_tokens": 4969030.0,
-      "eval_syn_loss": 0.6971890330314636,
-      "eval_syn_runtime": 54.8755,
-      "eval_syn_samples_per_second": 25.877,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 2075
-    },
-    {
-      "entropy": 0.3804885711934831,
-      "epoch": 5.060313630880579,
-      "grad_norm": 0.8717736005783081,
-      "learning_rate": 7.661938518021687e-05,
-      "loss": 0.3034685707092285,
-      "mean_token_accuracy": 0.8910005471923135,
-      "num_tokens": 5026625.0,
-      "step": 2100
-    },
-    {
-      "entropy": 0.3174623078107834,
-      "epoch": 5.180940892641737,
-      "grad_norm": 0.9808429479598999,
-      "learning_rate": 7.385142851656478e-05,
-      "loss": 0.23829608917236328,
-      "mean_token_accuracy": 0.9131860065460206,
-      "num_tokens": 5141010.0,
-      "step": 2150
-    },
-    {
-      "entropy": 0.3187542732059956,
-      "epoch": 5.301568154402895,
-      "grad_norm": 1.3739993572235107,
-      "learning_rate": 7.107031187929228e-05,
-      "loss": 0.24024734497070313,
-      "mean_token_accuracy": 0.910272576212883,
-      "num_tokens": 5261240.0,
-      "step": 2200
-    },
-    {
-      "entropy": 0.31624249830842016,
-      "epoch": 5.422195416164053,
-      "grad_norm": 1.1618341207504272,
-      "learning_rate": 6.82809535538603e-05,
-      "loss": 0.24144052505493163,
-      "mean_token_accuracy": 0.9122701978683472,
-      "num_tokens": 5382160.0,
-      "step": 2250
-    },
-    {
-      "entropy": 0.31793304443359377,
-      "epoch": 5.542822677925211,
-      "grad_norm": 1.4960980415344238,
-      "learning_rate": 6.548828640080172e-05,
-      "loss": 0.24051647186279296,
-      "mean_token_accuracy": 0.9116496992111206,
-      "num_tokens": 5502002.0,
-      "step": 2300
-    },
-    {
-      "entropy": 0.3180307722091675,
-      "epoch": 5.66344993968637,
-      "grad_norm": 1.103051781654358,
-      "learning_rate": 6.269724913216913e-05,
-      "loss": 0.24294727325439452,
-      "mean_token_accuracy": 0.9102917027473449,
-      "num_tokens": 5629969.0,
-      "step": 2350
-    },
-    {
-      "entropy": 0.32020670652389527,
-      "epoch": 5.784077201447527,
-      "grad_norm": 1.0690243244171143,
-      "learning_rate": 5.991277757763442e-05,
-      "loss": 0.24328670501708985,
-      "mean_token_accuracy": 0.9101310813426972,
-      "num_tokens": 5750596.0,
-      "step": 2400
-    },
-    {
-      "entropy": 0.31846788004040716,
-      "epoch": 5.904704463208685,
-      "grad_norm": 1.203026294708252,
-      "learning_rate": 5.7139795955685784e-05,
-      "loss": 0.244984130859375,
-      "mean_token_accuracy": 0.9100374561548233,
-      "num_tokens": 5868110.0,
-      "step": 2450
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.45794740654109567,
-      "eval_mean_token_accuracy": 0.7891001142142864,
-      "eval_not_syn_loss": 0.8338615894317627,
-      "eval_not_syn_runtime": 53.3841,
-      "eval_not_syn_samples_per_second": 26.6,
-      "eval_not_syn_steps_per_second": 3.334,
-      "eval_num_tokens": 5962836.0,
-      "step": 2490
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.4288232589370749,
-      "eval_mean_token_accuracy": 0.8114104933953017,
-      "eval_num_tokens": 5962836.0,
-      "eval_syn_loss": 0.7791845798492432,
-      "eval_syn_runtime": 54.7877,
-      "eval_syn_samples_per_second": 25.918,
-      "eval_syn_steps_per_second": 3.249,
-      "step": 2490
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.2673564949952768e+17,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2490/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86d444de5a2715bc79592e7c0468576e52e59a3d77c90640aa14e87a29046869
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/trainer_state.json

@@ -1,768 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 7.0,
-  "eval_steps": 500,
-  "global_step": 2905,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    },
-    {
-      "entropy": 0.6077835421369533,
-      "epoch": 3.012062726176116,
-      "grad_norm": 1.124720573425293,
-      "learning_rate": 0.00011713897584164003,
-      "loss": 0.5557136917114258,
-      "mean_token_accuracy": 0.8203362726201915,
-      "num_tokens": 2994602.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.507642827630043,
-      "epoch": 3.132689987937274,
-      "grad_norm": 0.9039916396141052,
-      "learning_rate": 0.00011529219281884579,
-      "loss": 0.4467372512817383,
-      "mean_token_accuracy": 0.8464260965585708,
-      "num_tokens": 3121094.0,
-      "step": 1300
-    },
-    {
-      "entropy": 0.5137191081047058,
-      "epoch": 3.2533172496984317,
-      "grad_norm": 0.8580691814422607,
-      "learning_rate": 0.00011335896360860367,
-      "loss": 0.4538694763183594,
-      "mean_token_accuracy": 0.8448719161748887,
-      "num_tokens": 3248038.0,
-      "step": 1350
-    },
-    {
-      "entropy": 0.5293738862872124,
-      "epoch": 3.37394451145959,
-      "grad_norm": 1.0177273750305176,
-      "learning_rate": 0.00011134270704383492,
-      "loss": 0.4639348220825195,
-      "mean_token_accuracy": 0.8428975892066956,
-      "num_tokens": 3363487.0,
-      "step": 1400
-    },
-    {
-      "entropy": 0.5218872320652008,
-      "epoch": 3.494571773220748,
-      "grad_norm": 1.0530673265457153,
-      "learning_rate": 0.00010924698878777538,
-      "loss": 0.4584346389770508,
-      "mean_token_accuracy": 0.8432288640737533,
-      "num_tokens": 3480513.0,
-      "step": 1450
-    },
-    {
-      "entropy": 0.5320372316241264,
-      "epoch": 3.615199034981906,
-      "grad_norm": 1.0291194915771484,
-      "learning_rate": 0.0001070755150282529,
-      "loss": 0.4711898422241211,
-      "mean_token_accuracy": 0.842066935300827,
-      "num_tokens": 3597183.0,
-      "step": 1500
-    },
-    {
-      "entropy": 0.5315000694990158,
-      "epoch": 3.7358262967430638,
-      "grad_norm": 0.9788838624954224,
-      "learning_rate": 0.00010483212592345332,
-      "loss": 0.4729101943969727,
-      "mean_token_accuracy": 0.8404586082696914,
-      "num_tokens": 3714173.0,
-      "step": 1550
-    },
-    {
-      "entropy": 0.5331643190979958,
-      "epoch": 3.856453558504222,
-      "grad_norm": 1.1248903274536133,
-      "learning_rate": 0.00010252078881076532,
-      "loss": 0.47405517578125,
-      "mean_token_accuracy": 0.8397526168823242,
-      "num_tokens": 3832652.0,
-      "step": 1600
-    },
-    {
-      "entropy": 0.5343865439295769,
-      "epoch": 3.97708082026538,
-      "grad_norm": 0.9008272886276245,
-      "learning_rate": 0.00010014559119071452,
-      "loss": 0.47172779083251953,
-      "mean_token_accuracy": 0.8404951041936874,
-      "num_tokens": 3955167.0,
-      "step": 1650
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5736920103598177,
-      "eval_mean_token_accuracy": 0.7981750027517255,
-      "eval_not_syn_loss": 0.707631528377533,
-      "eval_not_syn_runtime": 52.2858,
-      "eval_not_syn_samples_per_second": 27.158,
-      "eval_not_syn_steps_per_second": 3.404,
-      "eval_num_tokens": 3975224.0,
-      "step": 1660
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5363499959198277,
-      "eval_mean_token_accuracy": 0.8063885539435269,
-      "eval_num_tokens": 3975224.0,
-      "eval_syn_loss": 0.6610181331634521,
-      "eval_syn_runtime": 54.2167,
-      "eval_syn_samples_per_second": 26.191,
-      "eval_syn_steps_per_second": 3.283,
-      "step": 1660
-    },
-    {
-      "entropy": 0.4512602482179199,
-      "epoch": 4.0965018094089265,
-      "grad_norm": 0.8079906105995178,
-      "learning_rate": 9.771073349839416e-05,
-      "loss": 0.3778452682495117,
-      "mean_token_accuracy": 0.8684436221315404,
-      "num_tokens": 4072361.0,
-      "step": 1700
-    },
-    {
-      "entropy": 0.4228873434662819,
-      "epoch": 4.217129071170085,
-      "grad_norm": 1.1206746101379395,
-      "learning_rate": 9.52205216751758e-05,
-      "loss": 0.34671127319335937,
-      "mean_token_accuracy": 0.8763950079679489,
-      "num_tokens": 4194978.0,
-      "step": 1750
-    },
-    {
-      "entropy": 0.42808119297027586,
-      "epoch": 4.337756332931242,
-      "grad_norm": 1.1268125772476196,
-      "learning_rate": 9.26793595538368e-05,
-      "loss": 0.3484600830078125,
-      "mean_token_accuracy": 0.8753323918581009,
-      "num_tokens": 4315548.0,
-      "step": 1800
-    },
-    {
-      "entropy": 0.42506767451763156,
-      "epoch": 4.458383594692401,
-      "grad_norm": 1.1051807403564453,
-      "learning_rate": 9.009174107057088e-05,
-      "loss": 0.35434780120849607,
-      "mean_token_accuracy": 0.8734411865472793,
-      "num_tokens": 4431469.0,
-      "step": 1850
-    },
-    {
-      "entropy": 0.43314908266067503,
-      "epoch": 4.579010856453559,
-      "grad_norm": 0.9782640337944031,
-      "learning_rate": 8.746224231765484e-05,
-      "loss": 0.36225860595703124,
-      "mean_token_accuracy": 0.8715140378475189,
-      "num_tokens": 4551803.0,
-      "step": 1900
-    },
-    {
-      "entropy": 0.42984022706747055,
-      "epoch": 4.699638118214716,
-      "grad_norm": 0.9772566556930542,
-      "learning_rate": 8.479551345082568e-05,
-      "loss": 0.356609001159668,
-      "mean_token_accuracy": 0.8717925781011582,
-      "num_tokens": 4674468.0,
-      "step": 1950
-    },
-    {
-      "entropy": 0.4474307084083557,
-      "epoch": 4.820265379975875,
-      "grad_norm": 0.9547265768051147,
-      "learning_rate": 8.209627046567966e-05,
-      "loss": 0.3654902267456055,
-      "mean_token_accuracy": 0.8724055212736129,
-      "num_tokens": 4788027.0,
-      "step": 2000
-    },
-    {
-      "entropy": 0.4377285006642342,
-      "epoch": 4.940892641737032,
-      "grad_norm": 1.0390652418136597,
-      "learning_rate": 7.936928685763635e-05,
-      "loss": 0.3645761871337891,
-      "mean_token_accuracy": 0.8707609891891479,
-      "num_tokens": 4907561.0,
-      "step": 2050
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.5173388388049737,
-      "eval_mean_token_accuracy": 0.7918405432379647,
-      "eval_not_syn_loss": 0.7532826662063599,
-      "eval_not_syn_runtime": 53.0766,
-      "eval_not_syn_samples_per_second": 26.754,
-      "eval_not_syn_steps_per_second": 3.354,
-      "eval_num_tokens": 4969030.0,
-      "step": 2075
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.4831916272975086,
-      "eval_mean_token_accuracy": 0.8204237202580056,
-      "eval_num_tokens": 4969030.0,
-      "eval_syn_loss": 0.6971890330314636,
-      "eval_syn_runtime": 54.8755,
-      "eval_syn_samples_per_second": 25.877,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 2075
-    },
-    {
-      "entropy": 0.3804885711934831,
-      "epoch": 5.060313630880579,
-      "grad_norm": 0.8717736005783081,
-      "learning_rate": 7.661938518021687e-05,
-      "loss": 0.3034685707092285,
-      "mean_token_accuracy": 0.8910005471923135,
-      "num_tokens": 5026625.0,
-      "step": 2100
-    },
-    {
-      "entropy": 0.3174623078107834,
-      "epoch": 5.180940892641737,
-      "grad_norm": 0.9808429479598999,
-      "learning_rate": 7.385142851656478e-05,
-      "loss": 0.23829608917236328,
-      "mean_token_accuracy": 0.9131860065460206,
-      "num_tokens": 5141010.0,
-      "step": 2150
-    },
-    {
-      "entropy": 0.3187542732059956,
-      "epoch": 5.301568154402895,
-      "grad_norm": 1.3739993572235107,
-      "learning_rate": 7.107031187929228e-05,
-      "loss": 0.24024734497070313,
-      "mean_token_accuracy": 0.910272576212883,
-      "num_tokens": 5261240.0,
-      "step": 2200
-    },
-    {
-      "entropy": 0.31624249830842016,
-      "epoch": 5.422195416164053,
-      "grad_norm": 1.1618341207504272,
-      "learning_rate": 6.82809535538603e-05,
-      "loss": 0.24144052505493163,
-      "mean_token_accuracy": 0.9122701978683472,
-      "num_tokens": 5382160.0,
-      "step": 2250
-    },
-    {
-      "entropy": 0.31793304443359377,
-      "epoch": 5.542822677925211,
-      "grad_norm": 1.4960980415344238,
-      "learning_rate": 6.548828640080172e-05,
-      "loss": 0.24051647186279296,
-      "mean_token_accuracy": 0.9116496992111206,
-      "num_tokens": 5502002.0,
-      "step": 2300
-    },
-    {
-      "entropy": 0.3180307722091675,
-      "epoch": 5.66344993968637,
-      "grad_norm": 1.103051781654358,
-      "learning_rate": 6.269724913216913e-05,
-      "loss": 0.24294727325439452,
-      "mean_token_accuracy": 0.9102917027473449,
-      "num_tokens": 5629969.0,
-      "step": 2350
-    },
-    {
-      "entropy": 0.32020670652389527,
-      "epoch": 5.784077201447527,
-      "grad_norm": 1.0690243244171143,
-      "learning_rate": 5.991277757763442e-05,
-      "loss": 0.24328670501708985,
-      "mean_token_accuracy": 0.9101310813426972,
-      "num_tokens": 5750596.0,
-      "step": 2400
-    },
-    {
-      "entropy": 0.31846788004040716,
-      "epoch": 5.904704463208685,
-      "grad_norm": 1.203026294708252,
-      "learning_rate": 5.7139795955685784e-05,
-      "loss": 0.244984130859375,
-      "mean_token_accuracy": 0.9100374561548233,
-      "num_tokens": 5868110.0,
-      "step": 2450
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.45794740654109567,
-      "eval_mean_token_accuracy": 0.7891001142142864,
-      "eval_not_syn_loss": 0.8338615894317627,
-      "eval_not_syn_runtime": 53.3841,
-      "eval_not_syn_samples_per_second": 26.6,
-      "eval_not_syn_steps_per_second": 3.334,
-      "eval_num_tokens": 5962836.0,
-      "step": 2490
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.4288232589370749,
-      "eval_mean_token_accuracy": 0.8114104933953017,
-      "eval_num_tokens": 5962836.0,
-      "eval_syn_loss": 0.7791845798492432,
-      "eval_syn_runtime": 54.7877,
-      "eval_syn_samples_per_second": 25.918,
-      "eval_syn_steps_per_second": 3.249,
-      "step": 2490
-    },
-    {
-      "entropy": 0.2972855128423132,
-      "epoch": 6.024125452352232,
-      "grad_norm": 1.1748684644699097,
-      "learning_rate": 5.438320816535859e-05,
-      "loss": 0.22051204681396486,
-      "mean_token_accuracy": 0.9190925630656156,
-      "num_tokens": 5990107.0,
-      "step": 2500
-    },
-    {
-      "entropy": 0.2216818816959858,
-      "epoch": 6.144752714113389,
-      "grad_norm": 1.0899405479431152,
-      "learning_rate": 5.164788911390022e-05,
-      "loss": 0.1487915325164795,
-      "mean_token_accuracy": 0.9462692165374755,
-      "num_tokens": 6104230.0,
-      "step": 2550
-    },
-    {
-      "entropy": 0.22189782992005347,
-      "epoch": 6.265379975874548,
-      "grad_norm": 1.0967661142349243,
-      "learning_rate": 4.8938676095705914e-05,
-      "loss": 0.149844388961792,
-      "mean_token_accuracy": 0.9452104204893113,
-      "num_tokens": 6223548.0,
-      "step": 2600
-    },
-    {
-      "entropy": 0.2155836282670498,
-      "epoch": 6.386007237635706,
-      "grad_norm": 1.1443830728530884,
-      "learning_rate": 4.626036023777093e-05,
-      "loss": 0.1472412109375,
-      "mean_token_accuracy": 0.946697844862938,
-      "num_tokens": 6349102.0,
-      "step": 2650
-    },
-    {
-      "entropy": 0.22189507275819778,
-      "epoch": 6.5066344993968634,
-      "grad_norm": 1.2138874530792236,
-      "learning_rate": 4.3617678026788244e-05,
-      "loss": 0.15155397415161131,
-      "mean_token_accuracy": 0.9441326081752777,
-      "num_tokens": 6468966.0,
-      "step": 2700
-    },
-    {
-      "entropy": 0.22405965447425844,
-      "epoch": 6.627261761158022,
-      "grad_norm": 1.2444716691970825,
-      "learning_rate": 4.10153029328748e-05,
-      "loss": 0.15516298294067382,
-      "mean_token_accuracy": 0.9442053025960923,
-      "num_tokens": 6583296.0,
-      "step": 2750
-    },
-    {
-      "entropy": 0.2216674068570137,
-      "epoch": 6.74788902291918,
-      "grad_norm": 1.0056185722351074,
-      "learning_rate": 3.845783714474033e-05,
-      "loss": 0.15423223495483399,
-      "mean_token_accuracy": 0.9445771616697312,
-      "num_tokens": 6698696.0,
-      "step": 2800
-    },
-    {
-      "entropy": 0.21455578804016112,
-      "epoch": 6.868516284680338,
-      "grad_norm": 1.0748720169067383,
-      "learning_rate": 3.59498034309138e-05,
-      "loss": 0.14870482444763183,
-      "mean_token_accuracy": 0.9457976347208024,
-      "num_tokens": 6819711.0,
-      "step": 2850
-    },
-    {
-      "entropy": 0.21227611482143402,
-      "epoch": 6.989143546441496,
-      "grad_norm": 0.978204607963562,
-      "learning_rate": 3.349563714142155e-05,
-      "loss": 0.14802613258361816,
-      "mean_token_accuracy": 0.9466447854042053,
-      "num_tokens": 6944941.0,
-      "step": 2900
-    },
-    {
-      "epoch": 7.0,
-      "eval_entropy": 0.38817436741978933,
-      "eval_mean_token_accuracy": 0.7801904045463948,
-      "eval_not_syn_loss": 0.9901206493377686,
-      "eval_not_syn_runtime": 53.1137,
-      "eval_not_syn_samples_per_second": 26.735,
-      "eval_not_syn_steps_per_second": 3.351,
-      "eval_num_tokens": 6956642.0,
-      "step": 2905
-    },
-    {
-      "epoch": 7.0,
-      "eval_entropy": 0.3640736076938972,
-      "eval_mean_token_accuracy": 0.8158511425671953,
-      "eval_num_tokens": 6956642.0,
-      "eval_syn_loss": 0.8903024792671204,
-      "eval_syn_runtime": 54.3768,
-      "eval_syn_samples_per_second": 26.114,
-      "eval_syn_steps_per_second": 3.273,
-      "step": 2905
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.4783731624475712e+17,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-2905/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3.5-2B-Base",
-  "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": 256,
-  "lora_bias": false,
-  "lora_dropout": 0.027050353915701653,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 128,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb103a11b545a6a1bfadb00e9f36fe586c11850287cbaf9f1a507a083a379f5a
-size 349201608

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/chat_template.jinja

@@ -1,154 +0,0 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
-    {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + 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" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
-{%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
-        {{- '<|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 %}
-        {%- set reasoning_content = reasoning_content|trim %}
-        {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
-        {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
-        {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
-            {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
-                    {%- set tool_call = tool_call.function %}
-                {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
-                {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
-                {%- endif %}
-                {{- '</function>\n</tool_call>' }}
-            {%- endfor %}
-        {%- endif %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is true %}
-        {{- '<think>\n' }}
-    {%- else %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/tokenizer_config.json

@@ -1,31 +0,0 @@
-{
-  "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
-  "backend": "tokenizers",
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "image_token": "<|image_pad|>",
-  "is_local": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
-  "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/trainer_state.json

@@ -1,870 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 8.0,
-  "eval_steps": 500,
-  "global_step": 3320,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 2.0473356211185454,
-      "epoch": 0.12062726176115803,
-      "grad_norm": 3.0554118156433105,
-      "learning_rate": 1.5682344549790923e-05,
-      "loss": 1.910550079345703,
-      "mean_token_accuracy": 0.6053373458981514,
-      "num_tokens": 121428.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.0371007251739501,
-      "epoch": 0.24125452352231605,
-      "grad_norm": 2.109868049621582,
-      "learning_rate": 3.168473694753677e-05,
-      "loss": 0.9585584259033203,
-      "mean_token_accuracy": 0.7352996730804443,
-      "num_tokens": 243966.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.9105490958690643,
-      "epoch": 0.3618817852834741,
-      "grad_norm": 1.7675701379776,
-      "learning_rate": 4.7687129345282605e-05,
-      "loss": 0.8393524932861328,
-      "mean_token_accuracy": 0.7588736474514007,
-      "num_tokens": 366649.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.8660378754138947,
-      "epoch": 0.4825090470446321,
-      "grad_norm": 1.6502987146377563,
-      "learning_rate": 6.368952174302845e-05,
-      "loss": 0.8005844116210937,
-      "mean_token_accuracy": 0.7663125538825989,
-      "num_tokens": 488367.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.8439123743772506,
-      "epoch": 0.6031363088057901,
-      "grad_norm": 1.538365364074707,
-      "learning_rate": 7.969191414077429e-05,
-      "loss": 0.7773619842529297,
-      "mean_token_accuracy": 0.7718527519702911,
-      "num_tokens": 603131.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.8223806774616241,
-      "epoch": 0.7237635705669482,
-      "grad_norm": 1.1559664011001587,
-      "learning_rate": 9.569430653852014e-05,
-      "loss": 0.7587767791748047,
-      "mean_token_accuracy": 0.7767325991392136,
-      "num_tokens": 726412.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.8256935775279999,
-      "epoch": 0.8443908323281062,
-      "grad_norm": 1.2322715520858765,
-      "learning_rate": 0.00011169669893626597,
-      "loss": 0.769886245727539,
-      "mean_token_accuracy": 0.773840668797493,
-      "num_tokens": 846516.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.8065843790769577,
-      "epoch": 0.9650180940892642,
-      "grad_norm": 0.9908286333084106,
-      "learning_rate": 0.00012769909133401183,
-      "loss": 0.7451084899902344,
-      "mean_token_accuracy": 0.7794792425632476,
-      "num_tokens": 958978.0,
-      "step": 400
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.791056221790528,
-      "eval_mean_token_accuracy": 0.7507295300451557,
-      "eval_not_syn_loss": 0.7860428094863892,
-      "eval_not_syn_runtime": 53.5431,
-      "eval_not_syn_samples_per_second": 26.521,
-      "eval_not_syn_steps_per_second": 3.324,
-      "eval_num_tokens": 993806.0,
-      "step": 415
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.7424047408478983,
-      "eval_mean_token_accuracy": 0.8023804037758474,
-      "eval_num_tokens": 993806.0,
-      "eval_syn_loss": 0.7273509502410889,
-      "eval_syn_runtime": 54.8679,
-      "eval_syn_samples_per_second": 25.88,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 415
-    },
-    {
-      "entropy": 0.7607260761838971,
-      "epoch": 1.0844390832328106,
-      "grad_norm": 1.0653696060180664,
-      "learning_rate": 0.0001327927019027069,
-      "loss": 0.7034613037109375,
-      "mean_token_accuracy": 0.7869195998317063,
-      "num_tokens": 1080301.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.7370894801616669,
-      "epoch": 1.2050663449939687,
-      "grad_norm": 1.763787865638733,
-      "learning_rate": 0.00013265416569994628,
-      "loss": 0.6816973114013671,
-      "mean_token_accuracy": 0.7914507347345352,
-      "num_tokens": 1201215.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.742829909324646,
-      "epoch": 1.3256936067551266,
-      "grad_norm": 0.97663414478302,
-      "learning_rate": 0.00013239847940553975,
-      "loss": 0.6867338562011719,
-      "mean_token_accuracy": 0.790328289270401,
-      "num_tokens": 1322895.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.7312483406066894,
-      "epoch": 1.4463208685162847,
-      "grad_norm": 1.0874731540679932,
-      "learning_rate": 0.00013202609518972978,
-      "loss": 0.676800537109375,
-      "mean_token_accuracy": 0.7921512228250503,
-      "num_tokens": 1436749.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.7178869074583054,
-      "epoch": 1.5669481302774426,
-      "grad_norm": 1.064300298690796,
-      "learning_rate": 0.0001315376715980265,
-      "loss": 0.6635584259033203,
-      "mean_token_accuracy": 0.7944776183366775,
-      "num_tokens": 1555400.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.7198166918754577,
-      "epoch": 1.6875753920386007,
-      "grad_norm": 0.7779315114021301,
-      "learning_rate": 0.00013093407238659802,
-      "loss": 0.6660567474365234,
-      "mean_token_accuracy": 0.7968300533294678,
-      "num_tokens": 1676892.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.7170061504840851,
-      "epoch": 1.8082026537997589,
-      "grad_norm": 1.089854121208191,
-      "learning_rate": 0.00013021636499475496,
-      "loss": 0.6632771301269531,
-      "mean_token_accuracy": 0.7963915091753005,
-      "num_tokens": 1802689.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.6953610718250275,
-      "epoch": 1.9288299155609168,
-      "grad_norm": 0.7996730208396912,
-      "learning_rate": 0.0001293858186572295,
-      "loss": 0.6421419525146485,
-      "mean_token_accuracy": 0.8002577543258667,
-      "num_tokens": 1920804.0,
-      "step": 800
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.7369416523515508,
-      "eval_mean_token_accuracy": 0.7872022366925572,
-      "eval_not_syn_loss": 0.713637113571167,
-      "eval_not_syn_runtime": 53.2265,
-      "eval_not_syn_samples_per_second": 26.678,
-      "eval_not_syn_steps_per_second": 3.344,
-      "eval_num_tokens": 1987612.0,
-      "step": 830
-    },
-    {
-      "epoch": 2.0,
-      "eval_entropy": 0.6877032756135705,
-      "eval_mean_token_accuracy": 0.7997466372639945,
-      "eval_num_tokens": 1987612.0,
-      "eval_syn_loss": 0.6614266633987427,
-      "eval_syn_runtime": 54.5178,
-      "eval_syn_samples_per_second": 26.047,
-      "eval_syn_steps_per_second": 3.265,
-      "step": 830
-    },
-    {
-      "entropy": 0.6644553433765065,
-      "epoch": 2.0482509047044632,
-      "grad_norm": 0.7562468647956848,
-      "learning_rate": 0.00012844390215958852,
-      "loss": 0.6112185287475586,
-      "mean_token_accuracy": 0.806649933559726,
-      "num_tokens": 2039660.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.6146580249071121,
-      "epoch": 2.168878166465621,
-      "grad_norm": 1.098607063293457,
-      "learning_rate": 0.00012739228124074913,
-      "loss": 0.5553749084472657,
-      "mean_token_accuracy": 0.8187588346004486,
-      "num_tokens": 2161772.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.6187627577781677,
-      "epoch": 2.2895054282267795,
-      "grad_norm": 1.0338040590286255,
-      "learning_rate": 0.00012623281564719095,
-      "loss": 0.5596194076538086,
-      "mean_token_accuracy": 0.8182566928863525,
-      "num_tokens": 2280833.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.6232365870475769,
-      "epoch": 2.4101326899879374,
-      "grad_norm": 1.0010799169540405,
-      "learning_rate": 0.00012496755584407422,
-      "loss": 0.5667143249511719,
-      "mean_token_accuracy": 0.8175061982870102,
-      "num_tokens": 2398206.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.6151268655061721,
-      "epoch": 2.5307599517490953,
-      "grad_norm": 1.0065034627914429,
-      "learning_rate": 0.0001235987393890801,
-      "loss": 0.5598890686035156,
-      "mean_token_accuracy": 0.8193449324369431,
-      "num_tokens": 2518888.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.6173626267910004,
-      "epoch": 2.651387213510253,
-      "grad_norm": 0.7958805561065674,
-      "learning_rate": 0.00012212878697538592,
-      "loss": 0.5649292755126953,
-      "mean_token_accuracy": 0.8172902607917786,
-      "num_tokens": 2639763.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.6264930808544159,
-      "epoch": 2.772014475271411,
-      "grad_norm": 0.7718372344970703,
-      "learning_rate": 0.00012056029815077323,
-      "loss": 0.5716455078125,
-      "mean_token_accuracy": 0.8170186239480972,
-      "num_tokens": 2755540.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.6203387409448624,
-      "epoch": 2.8926417370325694,
-      "grad_norm": 0.7914765477180481,
-      "learning_rate": 0.000118896046720439,
-      "loss": 0.5653961944580078,
-      "mean_token_accuracy": 0.8170280295610428,
-      "num_tokens": 2874118.0,
-      "step": 1200
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6751241854737314,
-      "eval_mean_token_accuracy": 0.792226163858778,
-      "eval_not_syn_loss": 0.6902772784233093,
-      "eval_not_syn_runtime": 53.2557,
-      "eval_not_syn_samples_per_second": 26.664,
-      "eval_not_syn_steps_per_second": 3.342,
-      "eval_num_tokens": 2981418.0,
-      "step": 1245
-    },
-    {
-      "epoch": 3.0,
-      "eval_entropy": 0.6308753868837035,
-      "eval_mean_token_accuracy": 0.8131611759073278,
-      "eval_num_tokens": 2981418.0,
-      "eval_syn_loss": 0.6440441012382507,
-      "eval_syn_runtime": 54.7064,
-      "eval_syn_samples_per_second": 25.957,
-      "eval_syn_steps_per_second": 3.254,
-      "step": 1245
-    },
-    {
-      "entropy": 0.6077835421369533,
-      "epoch": 3.012062726176116,
-      "grad_norm": 1.124720573425293,
-      "learning_rate": 0.00011713897584164003,
-      "loss": 0.5557136917114258,
-      "mean_token_accuracy": 0.8203362726201915,
-      "num_tokens": 2994602.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.507642827630043,
-      "epoch": 3.132689987937274,
-      "grad_norm": 0.9039916396141052,
-      "learning_rate": 0.00011529219281884579,
-      "loss": 0.4467372512817383,
-      "mean_token_accuracy": 0.8464260965585708,
-      "num_tokens": 3121094.0,
-      "step": 1300
-    },
-    {
-      "entropy": 0.5137191081047058,
-      "epoch": 3.2533172496984317,
-      "grad_norm": 0.8580691814422607,
-      "learning_rate": 0.00011335896360860367,
-      "loss": 0.4538694763183594,
-      "mean_token_accuracy": 0.8448719161748887,
-      "num_tokens": 3248038.0,
-      "step": 1350
-    },
-    {
-      "entropy": 0.5293738862872124,
-      "epoch": 3.37394451145959,
-      "grad_norm": 1.0177273750305176,
-      "learning_rate": 0.00011134270704383492,
-      "loss": 0.4639348220825195,
-      "mean_token_accuracy": 0.8428975892066956,
-      "num_tokens": 3363487.0,
-      "step": 1400
-    },
-    {
-      "entropy": 0.5218872320652008,
-      "epoch": 3.494571773220748,
-      "grad_norm": 1.0530673265457153,
-      "learning_rate": 0.00010924698878777538,
-      "loss": 0.4584346389770508,
-      "mean_token_accuracy": 0.8432288640737533,
-      "num_tokens": 3480513.0,
-      "step": 1450
-    },
-    {
-      "entropy": 0.5320372316241264,
-      "epoch": 3.615199034981906,
-      "grad_norm": 1.0291194915771484,
-      "learning_rate": 0.0001070755150282529,
-      "loss": 0.4711898422241211,
-      "mean_token_accuracy": 0.842066935300827,
-      "num_tokens": 3597183.0,
-      "step": 1500
-    },
-    {
-      "entropy": 0.5315000694990158,
-      "epoch": 3.7358262967430638,
-      "grad_norm": 0.9788838624954224,
-      "learning_rate": 0.00010483212592345332,
-      "loss": 0.4729101943969727,
-      "mean_token_accuracy": 0.8404586082696914,
-      "num_tokens": 3714173.0,
-      "step": 1550
-    },
-    {
-      "entropy": 0.5331643190979958,
-      "epoch": 3.856453558504222,
-      "grad_norm": 1.1248903274536133,
-      "learning_rate": 0.00010252078881076532,
-      "loss": 0.47405517578125,
-      "mean_token_accuracy": 0.8397526168823242,
-      "num_tokens": 3832652.0,
-      "step": 1600
-    },
-    {
-      "entropy": 0.5343865439295769,
-      "epoch": 3.97708082026538,
-      "grad_norm": 0.9008272886276245,
-      "learning_rate": 0.00010014559119071452,
-      "loss": 0.47172779083251953,
-      "mean_token_accuracy": 0.8404951041936874,
-      "num_tokens": 3955167.0,
-      "step": 1650
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5736920103598177,
-      "eval_mean_token_accuracy": 0.7981750027517255,
-      "eval_not_syn_loss": 0.707631528377533,
-      "eval_not_syn_runtime": 52.2858,
-      "eval_not_syn_samples_per_second": 27.158,
-      "eval_not_syn_steps_per_second": 3.404,
-      "eval_num_tokens": 3975224.0,
-      "step": 1660
-    },
-    {
-      "epoch": 4.0,
-      "eval_entropy": 0.5363499959198277,
-      "eval_mean_token_accuracy": 0.8063885539435269,
-      "eval_num_tokens": 3975224.0,
-      "eval_syn_loss": 0.6610181331634521,
-      "eval_syn_runtime": 54.2167,
-      "eval_syn_samples_per_second": 26.191,
-      "eval_syn_steps_per_second": 3.283,
-      "step": 1660
-    },
-    {
-      "entropy": 0.4512602482179199,
-      "epoch": 4.0965018094089265,
-      "grad_norm": 0.8079906105995178,
-      "learning_rate": 9.771073349839416e-05,
-      "loss": 0.3778452682495117,
-      "mean_token_accuracy": 0.8684436221315404,
-      "num_tokens": 4072361.0,
-      "step": 1700
-    },
-    {
-      "entropy": 0.4228873434662819,
-      "epoch": 4.217129071170085,
-      "grad_norm": 1.1206746101379395,
-      "learning_rate": 9.52205216751758e-05,
-      "loss": 0.34671127319335937,
-      "mean_token_accuracy": 0.8763950079679489,
-      "num_tokens": 4194978.0,
-      "step": 1750
-    },
-    {
-      "entropy": 0.42808119297027586,
-      "epoch": 4.337756332931242,
-      "grad_norm": 1.1268125772476196,
-      "learning_rate": 9.26793595538368e-05,
-      "loss": 0.3484600830078125,
-      "mean_token_accuracy": 0.8753323918581009,
-      "num_tokens": 4315548.0,
-      "step": 1800
-    },
-    {
-      "entropy": 0.42506767451763156,
-      "epoch": 4.458383594692401,
-      "grad_norm": 1.1051807403564453,
-      "learning_rate": 9.009174107057088e-05,
-      "loss": 0.35434780120849607,
-      "mean_token_accuracy": 0.8734411865472793,
-      "num_tokens": 4431469.0,
-      "step": 1850
-    },
-    {
-      "entropy": 0.43314908266067503,
-      "epoch": 4.579010856453559,
-      "grad_norm": 0.9782640337944031,
-      "learning_rate": 8.746224231765484e-05,
-      "loss": 0.36225860595703124,
-      "mean_token_accuracy": 0.8715140378475189,
-      "num_tokens": 4551803.0,
-      "step": 1900
-    },
-    {
-      "entropy": 0.42984022706747055,
-      "epoch": 4.699638118214716,
-      "grad_norm": 0.9772566556930542,
-      "learning_rate": 8.479551345082568e-05,
-      "loss": 0.356609001159668,
-      "mean_token_accuracy": 0.8717925781011582,
-      "num_tokens": 4674468.0,
-      "step": 1950
-    },
-    {
-      "entropy": 0.4474307084083557,
-      "epoch": 4.820265379975875,
-      "grad_norm": 0.9547265768051147,
-      "learning_rate": 8.209627046567966e-05,
-      "loss": 0.3654902267456055,
-      "mean_token_accuracy": 0.8724055212736129,
-      "num_tokens": 4788027.0,
-      "step": 2000
-    },
-    {
-      "entropy": 0.4377285006642342,
-      "epoch": 4.940892641737032,
-      "grad_norm": 1.0390652418136597,
-      "learning_rate": 7.936928685763635e-05,
-      "loss": 0.3645761871337891,
-      "mean_token_accuracy": 0.8707609891891479,
-      "num_tokens": 4907561.0,
-      "step": 2050
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.5173388388049737,
-      "eval_mean_token_accuracy": 0.7918405432379647,
-      "eval_not_syn_loss": 0.7532826662063599,
-      "eval_not_syn_runtime": 53.0766,
-      "eval_not_syn_samples_per_second": 26.754,
-      "eval_not_syn_steps_per_second": 3.354,
-      "eval_num_tokens": 4969030.0,
-      "step": 2075
-    },
-    {
-      "epoch": 5.0,
-      "eval_entropy": 0.4831916272975086,
-      "eval_mean_token_accuracy": 0.8204237202580056,
-      "eval_num_tokens": 4969030.0,
-      "eval_syn_loss": 0.6971890330314636,
-      "eval_syn_runtime": 54.8755,
-      "eval_syn_samples_per_second": 25.877,
-      "eval_syn_steps_per_second": 3.244,
-      "step": 2075
-    },
-    {
-      "entropy": 0.3804885711934831,
-      "epoch": 5.060313630880579,
-      "grad_norm": 0.8717736005783081,
-      "learning_rate": 7.661938518021687e-05,
-      "loss": 0.3034685707092285,
-      "mean_token_accuracy": 0.8910005471923135,
-      "num_tokens": 5026625.0,
-      "step": 2100
-    },
-    {
-      "entropy": 0.3174623078107834,
-      "epoch": 5.180940892641737,
-      "grad_norm": 0.9808429479598999,
-      "learning_rate": 7.385142851656478e-05,
-      "loss": 0.23829608917236328,
-      "mean_token_accuracy": 0.9131860065460206,
-      "num_tokens": 5141010.0,
-      "step": 2150
-    },
-    {
-      "entropy": 0.3187542732059956,
-      "epoch": 5.301568154402895,
-      "grad_norm": 1.3739993572235107,
-      "learning_rate": 7.107031187929228e-05,
-      "loss": 0.24024734497070313,
-      "mean_token_accuracy": 0.910272576212883,
-      "num_tokens": 5261240.0,
-      "step": 2200
-    },
-    {
-      "entropy": 0.31624249830842016,
-      "epoch": 5.422195416164053,
-      "grad_norm": 1.1618341207504272,
-      "learning_rate": 6.82809535538603e-05,
-      "loss": 0.24144052505493163,
-      "mean_token_accuracy": 0.9122701978683472,
-      "num_tokens": 5382160.0,
-      "step": 2250
-    },
-    {
-      "entropy": 0.31793304443359377,
-      "epoch": 5.542822677925211,
-      "grad_norm": 1.4960980415344238,
-      "learning_rate": 6.548828640080172e-05,
-      "loss": 0.24051647186279296,
-      "mean_token_accuracy": 0.9116496992111206,
-      "num_tokens": 5502002.0,
-      "step": 2300
-    },
-    {
-      "entropy": 0.3180307722091675,
-      "epoch": 5.66344993968637,
-      "grad_norm": 1.103051781654358,
-      "learning_rate": 6.269724913216913e-05,
-      "loss": 0.24294727325439452,
-      "mean_token_accuracy": 0.9102917027473449,
-      "num_tokens": 5629969.0,
-      "step": 2350
-    },
-    {
-      "entropy": 0.32020670652389527,
-      "epoch": 5.784077201447527,
-      "grad_norm": 1.0690243244171143,
-      "learning_rate": 5.991277757763442e-05,
-      "loss": 0.24328670501708985,
-      "mean_token_accuracy": 0.9101310813426972,
-      "num_tokens": 5750596.0,
-      "step": 2400
-    },
-    {
-      "entropy": 0.31846788004040716,
-      "epoch": 5.904704463208685,
-      "grad_norm": 1.203026294708252,
-      "learning_rate": 5.7139795955685784e-05,
-      "loss": 0.244984130859375,
-      "mean_token_accuracy": 0.9100374561548233,
-      "num_tokens": 5868110.0,
-      "step": 2450
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.45794740654109567,
-      "eval_mean_token_accuracy": 0.7891001142142864,
-      "eval_not_syn_loss": 0.8338615894317627,
-      "eval_not_syn_runtime": 53.3841,
-      "eval_not_syn_samples_per_second": 26.6,
-      "eval_not_syn_steps_per_second": 3.334,
-      "eval_num_tokens": 5962836.0,
-      "step": 2490
-    },
-    {
-      "epoch": 6.0,
-      "eval_entropy": 0.4288232589370749,
-      "eval_mean_token_accuracy": 0.8114104933953017,
-      "eval_num_tokens": 5962836.0,
-      "eval_syn_loss": 0.7791845798492432,
-      "eval_syn_runtime": 54.7877,
-      "eval_syn_samples_per_second": 25.918,
-      "eval_syn_steps_per_second": 3.249,
-      "step": 2490
-    },
-    {
-      "entropy": 0.2972855128423132,
-      "epoch": 6.024125452352232,
-      "grad_norm": 1.1748684644699097,
-      "learning_rate": 5.438320816535859e-05,
-      "loss": 0.22051204681396486,
-      "mean_token_accuracy": 0.9190925630656156,
-      "num_tokens": 5990107.0,
-      "step": 2500
-    },
-    {
-      "entropy": 0.2216818816959858,
-      "epoch": 6.144752714113389,
-      "grad_norm": 1.0899405479431152,
-      "learning_rate": 5.164788911390022e-05,
-      "loss": 0.1487915325164795,
-      "mean_token_accuracy": 0.9462692165374755,
-      "num_tokens": 6104230.0,
-      "step": 2550
-    },
-    {
-      "entropy": 0.22189782992005347,
-      "epoch": 6.265379975874548,
-      "grad_norm": 1.0967661142349243,
-      "learning_rate": 4.8938676095705914e-05,
-      "loss": 0.149844388961792,
-      "mean_token_accuracy": 0.9452104204893113,
-      "num_tokens": 6223548.0,
-      "step": 2600
-    },
-    {
-      "entropy": 0.2155836282670498,
-      "epoch": 6.386007237635706,
-      "grad_norm": 1.1443830728530884,
-      "learning_rate": 4.626036023777093e-05,
-      "loss": 0.1472412109375,
-      "mean_token_accuracy": 0.946697844862938,
-      "num_tokens": 6349102.0,
-      "step": 2650
-    },
-    {
-      "entropy": 0.22189507275819778,
-      "epoch": 6.5066344993968634,
-      "grad_norm": 1.2138874530792236,
-      "learning_rate": 4.3617678026788244e-05,
-      "loss": 0.15155397415161131,
-      "mean_token_accuracy": 0.9441326081752777,
-      "num_tokens": 6468966.0,
-      "step": 2700
-    },
-    {
-      "entropy": 0.22405965447425844,
-      "epoch": 6.627261761158022,
-      "grad_norm": 1.2444716691970825,
-      "learning_rate": 4.10153029328748e-05,
-      "loss": 0.15516298294067382,
-      "mean_token_accuracy": 0.9442053025960923,
-      "num_tokens": 6583296.0,
-      "step": 2750
-    },
-    {
-      "entropy": 0.2216674068570137,
-      "epoch": 6.74788902291918,
-      "grad_norm": 1.0056185722351074,
-      "learning_rate": 3.845783714474033e-05,
-      "loss": 0.15423223495483399,
-      "mean_token_accuracy": 0.9445771616697312,
-      "num_tokens": 6698696.0,
-      "step": 2800
-    },
-    {
-      "entropy": 0.21455578804016112,
-      "epoch": 6.868516284680338,
-      "grad_norm": 1.0748720169067383,
-      "learning_rate": 3.59498034309138e-05,
-      "loss": 0.14870482444763183,
-      "mean_token_accuracy": 0.9457976347208024,
-      "num_tokens": 6819711.0,
-      "step": 2850
-    },
-    {
-      "entropy": 0.21227611482143402,
-      "epoch": 6.989143546441496,
-      "grad_norm": 0.978204607963562,
-      "learning_rate": 3.349563714142155e-05,
-      "loss": 0.14802613258361816,
-      "mean_token_accuracy": 0.9466447854042053,
-      "num_tokens": 6944941.0,
-      "step": 2900
-    },
-    {
-      "epoch": 7.0,
-      "eval_entropy": 0.38817436741978933,
-      "eval_mean_token_accuracy": 0.7801904045463948,
-      "eval_not_syn_loss": 0.9901206493377686,
-      "eval_not_syn_runtime": 53.1137,
-      "eval_not_syn_samples_per_second": 26.735,
-      "eval_not_syn_steps_per_second": 3.351,
-      "eval_num_tokens": 6956642.0,
-      "step": 2905
-    },
-    {
-      "epoch": 7.0,
-      "eval_entropy": 0.3640736076938972,
-      "eval_mean_token_accuracy": 0.8158511425671953,
-      "eval_num_tokens": 6956642.0,
-      "eval_syn_loss": 0.8903024792671204,
-      "eval_syn_runtime": 54.3768,
-      "eval_syn_samples_per_second": 26.114,
-      "eval_syn_steps_per_second": 3.273,
-      "step": 2905
-    },
-    {
-      "entropy": 0.16986672166321012,
-      "epoch": 7.108564535585042,
-      "grad_norm": 0.7068538069725037,
-      "learning_rate": 3.1099678364060876e-05,
-      "loss": 0.10039780616760254,
-      "mean_token_accuracy": 0.964904587678235,
-      "num_tokens": 7064818.0,
-      "step": 2950
-    },
-    {
-      "entropy": 0.16062987893819808,
-      "epoch": 7.2291917973462,
-      "grad_norm": 0.963703453540802,
-      "learning_rate": 2.8766164249141098e-05,
-      "loss": 0.09831766128540038,
-      "mean_token_accuracy": 0.9666522133350373,
-      "num_tokens": 7183624.0,
-      "step": 3000
-    },
-    {
-      "entropy": 0.15993704989552499,
-      "epoch": 7.349819059107358,
-      "grad_norm": 0.8077407479286194,
-      "learning_rate": 2.6499221516264785e-05,
-      "loss": 0.09768331527709961,
-      "mean_token_accuracy": 0.9664828568696976,
-      "num_tokens": 7304122.0,
-      "step": 3050
-    },
-    {
-      "entropy": 0.16501803942024706,
-      "epoch": 7.470446320868517,
-      "grad_norm": 0.8302854299545288,
-      "learning_rate": 2.4302859156401512e-05,
-      "loss": 0.10022387504577637,
-      "mean_token_accuracy": 0.9645011806488037,
-      "num_tokens": 7422217.0,
-      "step": 3100
-    },
-    {
-      "entropy": 0.1541054170578718,
-      "epoch": 7.591073582629674,
-      "grad_norm": 0.8342278599739075,
-      "learning_rate": 2.218096134215895e-05,
-      "loss": 0.09620431900024413,
-      "mean_token_accuracy": 0.9666509574651718,
-      "num_tokens": 7547071.0,
-      "step": 3150
-    },
-    {
-      "entropy": 0.16526211962103843,
-      "epoch": 7.711700844390832,
-      "grad_norm": 0.9860979914665222,
-      "learning_rate": 2.0137280558790573e-05,
-      "loss": 0.10015854835510254,
-      "mean_token_accuracy": 0.9650658935308456,
-      "num_tokens": 7663184.0,
-      "step": 3200
-    },
-    {
-      "entropy": 0.1566712998598814,
-      "epoch": 7.832328106151991,
-      "grad_norm": 0.6179924011230469,
-      "learning_rate": 1.8175430968086255e-05,
-      "loss": 0.09698445320129395,
-      "mean_token_accuracy": 0.9661821335554123,
-      "num_tokens": 7785293.0,
-      "step": 3250
-    },
-    {
-      "entropy": 0.16459605664014818,
-      "epoch": 7.952955367913148,
-      "grad_norm": 0.7428495287895203,
-      "learning_rate": 1.6298882016882273e-05,
-      "loss": 0.09972883224487304,
-      "mean_token_accuracy": 0.9650641173124314,
-      "num_tokens": 7903616.0,
-      "step": 3300
-    },
-    {
-      "epoch": 8.0,
-      "eval_entropy": 0.339001152455137,
-      "eval_mean_token_accuracy": 0.7834485541568713,
-      "eval_not_syn_loss": 1.1380223035812378,
-      "eval_not_syn_runtime": 52.6766,
-      "eval_not_syn_samples_per_second": 26.957,
-      "eval_not_syn_steps_per_second": 3.379,
-      "eval_num_tokens": 7950448.0,
-      "step": 3320
-    },
-    {
-      "epoch": 8.0,
-      "eval_entropy": 0.3175283433513695,
-      "eval_mean_token_accuracy": 0.8104708164595487,
-      "eval_num_tokens": 7950448.0,
-      "eval_syn_loss": 1.0303504467010498,
-      "eval_syn_runtime": 54.8193,
-      "eval_syn_samples_per_second": 25.903,
-      "eval_syn_steps_per_second": 3.247,
-      "step": 3320
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 4150,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.6904481806551872e+17,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3320/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:770fc15ebc27a54d780af597d32c57ca14b3b528f14788d142bdfce09b555bef
-size 6033

substitutivity_original_Estonian/Qwen3.5-2B-Base_substitutivity_splits_original_features_train_substitutivity_splits_original_features_test1/checkpoint-3735/README.md

@@ -1,209 +0,0 @@
----
-base_model: Qwen/Qwen3.5-2B-Base
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3.5-2B-Base
-- 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 0.18.1