Add files using upload-large-folder tool

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1284/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1284/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.010622890133962027,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1284/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1284/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1284/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1284,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7805559730529785,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.5128960013389587,
+      "learning_rate": 1.950005322230992e-06,
+      "loss": 1.770846405029297,
+      "mean_token_accuracy": 0.6305050283670426,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.5725344836711883,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.7059135437011719,
+      "learning_rate": 3.93980667144629e-06,
+      "loss": 1.5153414916992187,
+      "mean_token_accuracy": 0.6729821544885636,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0769569373130798,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.6092284321784973,
+      "learning_rate": 5.9296080206615885e-06,
+      "loss": 1.0251461791992187,
+      "mean_token_accuracy": 0.737835128903389,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8583791655302048,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5586332082748413,
+      "learning_rate": 7.919409369876886e-06,
+      "loss": 0.81265869140625,
+      "mean_token_accuracy": 0.7762657129764556,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7744105678796768,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.4821721613407135,
+      "learning_rate": 9.909210719092184e-06,
+      "loss": 0.7364049530029297,
+      "mean_token_accuracy": 0.7918167436122894,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.715560827255249,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.6843860745429993,
+      "learning_rate": 1.1899012068307483e-05,
+      "loss": 0.6826614379882813,
+      "mean_token_accuracy": 0.8043146914243698,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6893886953592301,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.6543110013008118,
+      "learning_rate": 1.3888813417522781e-05,
+      "loss": 0.6608805847167969,
+      "mean_token_accuracy": 0.8083165866136551,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.652973799109459,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7437635660171509,
+      "learning_rate": 1.587861476673808e-05,
+      "loss": 0.6218611907958984,
+      "mean_token_accuracy": 0.8167323243618011,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.8066210185552573,
+      "eval_loss": 0.7281543016433716,
+      "eval_mean_token_accuracy": 0.7858095281309896,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 46.0044,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 3.348,
+      "step": 428
+    },
+    {
+      "entropy": 0.6467276298999787,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.626556396484375,
+      "learning_rate": 1.7031450502641085e-05,
+      "loss": 0.6161280441284179,
+      "mean_token_accuracy": 0.817004052400589,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6262363213300705,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.70875084400177,
+      "learning_rate": 1.7018425538355792e-05,
+      "loss": 0.5963106536865235,
+      "mean_token_accuracy": 0.8221335035562515,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6171189111471176,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.6629440188407898,
+      "learning_rate": 1.6991264396738895e-05,
+      "loss": 0.5875393676757813,
+      "mean_token_accuracy": 0.8245152229070664,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6083133199810982,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.5385038256645203,
+      "learning_rate": 1.6950012237904817e-05,
+      "loss": 0.5768455505371094,
+      "mean_token_accuracy": 0.8271224808692932,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.6011673760414123,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.7062859535217285,
+      "learning_rate": 1.6894737650731013e-05,
+      "loss": 0.5666856384277343,
+      "mean_token_accuracy": 0.829860600233078,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5905318284034728,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.646713137626648,
+      "learning_rate": 1.682553253881702e-05,
+      "loss": 0.560577392578125,
+      "mean_token_accuracy": 0.8313507026433945,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5964298728108406,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.6510505080223083,
+      "learning_rate": 1.674251196767876e-05,
+      "loss": 0.5606492614746094,
+      "mean_token_accuracy": 0.8313686531782151,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5872641482949257,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.6211879849433899,
+      "learning_rate": 1.6645813973432182e-05,
+      "loss": 0.556594352722168,
+      "mean_token_accuracy": 0.8333250796794891,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5889243066310883,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.6804038882255554,
+      "learning_rate": 1.6535599333284194e-05,
+      "loss": 0.5578879928588867,
+      "mean_token_accuracy": 0.831966199874878,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.7079034389613511,
+      "eval_loss": 0.6832069158554077,
+      "eval_mean_token_accuracy": 0.8022074165282311,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 46.0398,
+      "eval_samples_per_second": 26.738,
+      "eval_steps_per_second": 3.345,
+      "step": 856
+    },
+    {
+      "entropy": 0.5462229257822037,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.5834382772445679,
+      "learning_rate": 1.6412051298212675e-05,
+      "loss": 0.5115155029296875,
+      "mean_token_accuracy": 0.8419190347194672,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5501805812120437,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.774409830570221,
+      "learning_rate": 1.627537528827988e-05,
+      "loss": 0.5193024826049805,
+      "mean_token_accuracy": 0.8415862208604813,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5417112326622009,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.8148911595344543,
+      "learning_rate": 1.612579855108594e-05,
+      "loss": 0.5099837875366211,
+      "mean_token_accuracy": 0.8432273292541503,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5426027116179466,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.738017737865448,
+      "learning_rate": 1.596356978393025e-05,
+      "loss": 0.5110509490966797,
+      "mean_token_accuracy": 0.8447510355710983,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.536553855240345,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.6512451767921448,
+      "learning_rate": 1.5788958720309008e-05,
+      "loss": 0.5046747207641602,
+      "mean_token_accuracy": 0.8439748030900955,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5361887359619141,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.7650485038757324,
+      "learning_rate": 1.5602255681436483e-05,
+      "loss": 0.5043494415283203,
+      "mean_token_accuracy": 0.8450696021318436,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.5419432005286217,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.6945335268974304,
+      "learning_rate": 1.5403771093535538e-05,
+      "loss": 0.5108187103271484,
+      "mean_token_accuracy": 0.8431807065010071,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.5400136861205102,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.774668276309967,
+      "learning_rate": 1.5193834971700146e-05,
+      "loss": 0.5082107543945312,
+      "mean_token_accuracy": 0.8444043332338333,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.6524020644364419,
+      "eval_loss": 0.6701120138168335,
+      "eval_mean_token_accuracy": 0.8018650695101007,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 46.004,
+      "eval_samples_per_second": 26.759,
+      "eval_steps_per_second": 3.348,
+      "step": 1284
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 7.917359668463616e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1712/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1712/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.010622890133962027,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1712/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1712/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-1712/trainer_state.json

@@ -0,0 +1,418 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7805559730529785,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.5128960013389587,
+      "learning_rate": 1.950005322230992e-06,
+      "loss": 1.770846405029297,
+      "mean_token_accuracy": 0.6305050283670426,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.5725344836711883,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.7059135437011719,
+      "learning_rate": 3.93980667144629e-06,
+      "loss": 1.5153414916992187,
+      "mean_token_accuracy": 0.6729821544885636,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0769569373130798,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.6092284321784973,
+      "learning_rate": 5.9296080206615885e-06,
+      "loss": 1.0251461791992187,
+      "mean_token_accuracy": 0.737835128903389,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8583791655302048,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5586332082748413,
+      "learning_rate": 7.919409369876886e-06,
+      "loss": 0.81265869140625,
+      "mean_token_accuracy": 0.7762657129764556,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7744105678796768,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.4821721613407135,
+      "learning_rate": 9.909210719092184e-06,
+      "loss": 0.7364049530029297,
+      "mean_token_accuracy": 0.7918167436122894,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.715560827255249,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.6843860745429993,
+      "learning_rate": 1.1899012068307483e-05,
+      "loss": 0.6826614379882813,
+      "mean_token_accuracy": 0.8043146914243698,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6893886953592301,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.6543110013008118,
+      "learning_rate": 1.3888813417522781e-05,
+      "loss": 0.6608805847167969,
+      "mean_token_accuracy": 0.8083165866136551,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.652973799109459,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7437635660171509,
+      "learning_rate": 1.587861476673808e-05,
+      "loss": 0.6218611907958984,
+      "mean_token_accuracy": 0.8167323243618011,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.8066210185552573,
+      "eval_loss": 0.7281543016433716,
+      "eval_mean_token_accuracy": 0.7858095281309896,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 46.0044,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 3.348,
+      "step": 428
+    },
+    {
+      "entropy": 0.6467276298999787,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.626556396484375,
+      "learning_rate": 1.7031450502641085e-05,
+      "loss": 0.6161280441284179,
+      "mean_token_accuracy": 0.817004052400589,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6262363213300705,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.70875084400177,
+      "learning_rate": 1.7018425538355792e-05,
+      "loss": 0.5963106536865235,
+      "mean_token_accuracy": 0.8221335035562515,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6171189111471176,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.6629440188407898,
+      "learning_rate": 1.6991264396738895e-05,
+      "loss": 0.5875393676757813,
+      "mean_token_accuracy": 0.8245152229070664,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6083133199810982,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.5385038256645203,
+      "learning_rate": 1.6950012237904817e-05,
+      "loss": 0.5768455505371094,
+      "mean_token_accuracy": 0.8271224808692932,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.6011673760414123,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.7062859535217285,
+      "learning_rate": 1.6894737650731013e-05,
+      "loss": 0.5666856384277343,
+      "mean_token_accuracy": 0.829860600233078,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5905318284034728,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.646713137626648,
+      "learning_rate": 1.682553253881702e-05,
+      "loss": 0.560577392578125,
+      "mean_token_accuracy": 0.8313507026433945,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5964298728108406,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.6510505080223083,
+      "learning_rate": 1.674251196767876e-05,
+      "loss": 0.5606492614746094,
+      "mean_token_accuracy": 0.8313686531782151,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5872641482949257,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.6211879849433899,
+      "learning_rate": 1.6645813973432182e-05,
+      "loss": 0.556594352722168,
+      "mean_token_accuracy": 0.8333250796794891,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5889243066310883,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.6804038882255554,
+      "learning_rate": 1.6535599333284194e-05,
+      "loss": 0.5578879928588867,
+      "mean_token_accuracy": 0.831966199874878,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.7079034389613511,
+      "eval_loss": 0.6832069158554077,
+      "eval_mean_token_accuracy": 0.8022074165282311,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 46.0398,
+      "eval_samples_per_second": 26.738,
+      "eval_steps_per_second": 3.345,
+      "step": 856
+    },
+    {
+      "entropy": 0.5462229257822037,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.5834382772445679,
+      "learning_rate": 1.6412051298212675e-05,
+      "loss": 0.5115155029296875,
+      "mean_token_accuracy": 0.8419190347194672,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5501805812120437,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.774409830570221,
+      "learning_rate": 1.627537528827988e-05,
+      "loss": 0.5193024826049805,
+      "mean_token_accuracy": 0.8415862208604813,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5417112326622009,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.8148911595344543,
+      "learning_rate": 1.612579855108594e-05,
+      "loss": 0.5099837875366211,
+      "mean_token_accuracy": 0.8432273292541503,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5426027116179466,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.738017737865448,
+      "learning_rate": 1.596356978393025e-05,
+      "loss": 0.5110509490966797,
+      "mean_token_accuracy": 0.8447510355710983,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.536553855240345,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.6512451767921448,
+      "learning_rate": 1.5788958720309008e-05,
+      "loss": 0.5046747207641602,
+      "mean_token_accuracy": 0.8439748030900955,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5361887359619141,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.7650485038757324,
+      "learning_rate": 1.5602255681436483e-05,
+      "loss": 0.5043494415283203,
+      "mean_token_accuracy": 0.8450696021318436,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.5419432005286217,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.6945335268974304,
+      "learning_rate": 1.5403771093535538e-05,
+      "loss": 0.5108187103271484,
+      "mean_token_accuracy": 0.8431807065010071,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.5400136861205102,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.774668276309967,
+      "learning_rate": 1.5193834971700146e-05,
+      "loss": 0.5082107543945312,
+      "mean_token_accuracy": 0.8444043332338333,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.6524020644364419,
+      "eval_loss": 0.6701120138168335,
+      "eval_mean_token_accuracy": 0.8018650695101007,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 46.004,
+      "eval_samples_per_second": 26.759,
+      "eval_steps_per_second": 3.348,
+      "step": 1284
+    },
+    {
+      "entropy": 0.5256310805678368,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.8875723481178284,
+      "learning_rate": 1.4972796371187997e-05,
+      "loss": 0.49435077667236327,
+      "mean_token_accuracy": 0.8473169440031052,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4986111795902252,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.8605287671089172,
+      "learning_rate": 1.4741022807055508e-05,
+      "loss": 0.4662786483764648,
+      "mean_token_accuracy": 0.8552708566188812,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.5061789083480835,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.8101795315742493,
+      "learning_rate": 1.4498899643100226e-05,
+      "loss": 0.47242179870605466,
+      "mean_token_accuracy": 0.8520459419488907,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4939887225627899,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.8013083338737488,
+      "learning_rate": 1.4246829451126602e-05,
+      "loss": 0.4614598846435547,
+      "mean_token_accuracy": 0.8552495676279068,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.4918920609354973,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.7743699550628662,
+      "learning_rate": 1.3985231341600455e-05,
+      "loss": 0.46159915924072265,
+      "mean_token_accuracy": 0.8550176537036895,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.49779762893915175,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.8169922828674316,
+      "learning_rate": 1.3714540266805045e-05,
+      "loss": 0.46558887481689454,
+      "mean_token_accuracy": 0.8540038305521012,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.5015265879034996,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.851017951965332,
+      "learning_rate": 1.343520629765737e-05,
+      "loss": 0.46733531951904295,
+      "mean_token_accuracy": 0.8522392755746842,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.501338247358799,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.8121753334999084,
+      "learning_rate": 1.3147693875387126e-05,
+      "loss": 0.4710521697998047,
+      "mean_token_accuracy": 0.8534136080741882,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.49478380143642425,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.6918302178382874,
+      "learning_rate": 1.2852481039322492e-05,
+      "loss": 0.4646331405639648,
+      "mean_token_accuracy": 0.8551374357938767,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.6295453201640736,
+      "eval_loss": 0.666642427444458,
+      "eval_mean_token_accuracy": 0.8111948270302314,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.8725,
+      "eval_samples_per_second": 26.835,
+      "eval_steps_per_second": 3.357,
+      "step": 1712
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 1.0548186638206157e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2140/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2140/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.010622890133962027,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2140/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2140/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2140/trainer_state.json

@@ -0,0 +1,509 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7805559730529785,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.5128960013389587,
+      "learning_rate": 1.950005322230992e-06,
+      "loss": 1.770846405029297,
+      "mean_token_accuracy": 0.6305050283670426,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.5725344836711883,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.7059135437011719,
+      "learning_rate": 3.93980667144629e-06,
+      "loss": 1.5153414916992187,
+      "mean_token_accuracy": 0.6729821544885636,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0769569373130798,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.6092284321784973,
+      "learning_rate": 5.9296080206615885e-06,
+      "loss": 1.0251461791992187,
+      "mean_token_accuracy": 0.737835128903389,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8583791655302048,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5586332082748413,
+      "learning_rate": 7.919409369876886e-06,
+      "loss": 0.81265869140625,
+      "mean_token_accuracy": 0.7762657129764556,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7744105678796768,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.4821721613407135,
+      "learning_rate": 9.909210719092184e-06,
+      "loss": 0.7364049530029297,
+      "mean_token_accuracy": 0.7918167436122894,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.715560827255249,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.6843860745429993,
+      "learning_rate": 1.1899012068307483e-05,
+      "loss": 0.6826614379882813,
+      "mean_token_accuracy": 0.8043146914243698,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6893886953592301,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.6543110013008118,
+      "learning_rate": 1.3888813417522781e-05,
+      "loss": 0.6608805847167969,
+      "mean_token_accuracy": 0.8083165866136551,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.652973799109459,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7437635660171509,
+      "learning_rate": 1.587861476673808e-05,
+      "loss": 0.6218611907958984,
+      "mean_token_accuracy": 0.8167323243618011,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.8066210185552573,
+      "eval_loss": 0.7281543016433716,
+      "eval_mean_token_accuracy": 0.7858095281309896,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 46.0044,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 3.348,
+      "step": 428
+    },
+    {
+      "entropy": 0.6467276298999787,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.626556396484375,
+      "learning_rate": 1.7031450502641085e-05,
+      "loss": 0.6161280441284179,
+      "mean_token_accuracy": 0.817004052400589,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6262363213300705,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.70875084400177,
+      "learning_rate": 1.7018425538355792e-05,
+      "loss": 0.5963106536865235,
+      "mean_token_accuracy": 0.8221335035562515,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6171189111471176,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.6629440188407898,
+      "learning_rate": 1.6991264396738895e-05,
+      "loss": 0.5875393676757813,
+      "mean_token_accuracy": 0.8245152229070664,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6083133199810982,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.5385038256645203,
+      "learning_rate": 1.6950012237904817e-05,
+      "loss": 0.5768455505371094,
+      "mean_token_accuracy": 0.8271224808692932,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.6011673760414123,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.7062859535217285,
+      "learning_rate": 1.6894737650731013e-05,
+      "loss": 0.5666856384277343,
+      "mean_token_accuracy": 0.829860600233078,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5905318284034728,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.646713137626648,
+      "learning_rate": 1.682553253881702e-05,
+      "loss": 0.560577392578125,
+      "mean_token_accuracy": 0.8313507026433945,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5964298728108406,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.6510505080223083,
+      "learning_rate": 1.674251196767876e-05,
+      "loss": 0.5606492614746094,
+      "mean_token_accuracy": 0.8313686531782151,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5872641482949257,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.6211879849433899,
+      "learning_rate": 1.6645813973432182e-05,
+      "loss": 0.556594352722168,
+      "mean_token_accuracy": 0.8333250796794891,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5889243066310883,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.6804038882255554,
+      "learning_rate": 1.6535599333284194e-05,
+      "loss": 0.5578879928588867,
+      "mean_token_accuracy": 0.831966199874878,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.7079034389613511,
+      "eval_loss": 0.6832069158554077,
+      "eval_mean_token_accuracy": 0.8022074165282311,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 46.0398,
+      "eval_samples_per_second": 26.738,
+      "eval_steps_per_second": 3.345,
+      "step": 856
+    },
+    {
+      "entropy": 0.5462229257822037,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.5834382772445679,
+      "learning_rate": 1.6412051298212675e-05,
+      "loss": 0.5115155029296875,
+      "mean_token_accuracy": 0.8419190347194672,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5501805812120437,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.774409830570221,
+      "learning_rate": 1.627537528827988e-05,
+      "loss": 0.5193024826049805,
+      "mean_token_accuracy": 0.8415862208604813,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5417112326622009,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.8148911595344543,
+      "learning_rate": 1.612579855108594e-05,
+      "loss": 0.5099837875366211,
+      "mean_token_accuracy": 0.8432273292541503,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5426027116179466,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.738017737865448,
+      "learning_rate": 1.596356978393025e-05,
+      "loss": 0.5110509490966797,
+      "mean_token_accuracy": 0.8447510355710983,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.536553855240345,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.6512451767921448,
+      "learning_rate": 1.5788958720309008e-05,
+      "loss": 0.5046747207641602,
+      "mean_token_accuracy": 0.8439748030900955,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5361887359619141,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.7650485038757324,
+      "learning_rate": 1.5602255681436483e-05,
+      "loss": 0.5043494415283203,
+      "mean_token_accuracy": 0.8450696021318436,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.5419432005286217,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.6945335268974304,
+      "learning_rate": 1.5403771093535538e-05,
+      "loss": 0.5108187103271484,
+      "mean_token_accuracy": 0.8431807065010071,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.5400136861205102,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.774668276309967,
+      "learning_rate": 1.5193834971700146e-05,
+      "loss": 0.5082107543945312,
+      "mean_token_accuracy": 0.8444043332338333,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.6524020644364419,
+      "eval_loss": 0.6701120138168335,
+      "eval_mean_token_accuracy": 0.8018650695101007,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 46.004,
+      "eval_samples_per_second": 26.759,
+      "eval_steps_per_second": 3.348,
+      "step": 1284
+    },
+    {
+      "entropy": 0.5256310805678368,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.8875723481178284,
+      "learning_rate": 1.4972796371187997e-05,
+      "loss": 0.49435077667236327,
+      "mean_token_accuracy": 0.8473169440031052,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4986111795902252,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.8605287671089172,
+      "learning_rate": 1.4741022807055508e-05,
+      "loss": 0.4662786483764648,
+      "mean_token_accuracy": 0.8552708566188812,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.5061789083480835,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.8101795315742493,
+      "learning_rate": 1.4498899643100226e-05,
+      "loss": 0.47242179870605466,
+      "mean_token_accuracy": 0.8520459419488907,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4939887225627899,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.8013083338737488,
+      "learning_rate": 1.4246829451126602e-05,
+      "loss": 0.4614598846435547,
+      "mean_token_accuracy": 0.8552495676279068,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.4918920609354973,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.7743699550628662,
+      "learning_rate": 1.3985231341600455e-05,
+      "loss": 0.46159915924072265,
+      "mean_token_accuracy": 0.8550176537036895,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.49779762893915175,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.8169922828674316,
+      "learning_rate": 1.3714540266805045e-05,
+      "loss": 0.46558887481689454,
+      "mean_token_accuracy": 0.8540038305521012,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.5015265879034996,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.851017951965332,
+      "learning_rate": 1.343520629765737e-05,
+      "loss": 0.46733531951904295,
+      "mean_token_accuracy": 0.8522392755746842,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.501338247358799,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.8121753334999084,
+      "learning_rate": 1.3147693875387126e-05,
+      "loss": 0.4710521697998047,
+      "mean_token_accuracy": 0.8534136080741882,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.49478380143642425,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.6918302178382874,
+      "learning_rate": 1.2852481039322492e-05,
+      "loss": 0.4646331405639648,
+      "mean_token_accuracy": 0.8551374357938767,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.6295453201640736,
+      "eval_loss": 0.666642427444458,
+      "eval_mean_token_accuracy": 0.8111948270302314,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.8725,
+      "eval_samples_per_second": 26.835,
+      "eval_steps_per_second": 3.357,
+      "step": 1712
+    },
+    {
+      "entropy": 0.46167980462312697,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.8769540190696716,
+      "learning_rate": 1.2550058632066751e-05,
+      "loss": 0.4263522338867187,
+      "mean_token_accuracy": 0.8653014451265335,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.4534104973077774,
+      "epoch": 4.205607476635514,
+      "grad_norm": 1.1420735120773315,
+      "learning_rate": 1.2240929483387228e-05,
+      "loss": 0.41863834381103515,
+      "mean_token_accuracy": 0.8667230373620987,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.4606948295235634,
+      "epoch": 4.322429906542056,
+      "grad_norm": 1.0596942901611328,
+      "learning_rate": 1.1925607574173476e-05,
+      "loss": 0.42718273162841797,
+      "mean_token_accuracy": 0.8641588741540909,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.45681062549352647,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.9009803533554077,
+      "learning_rate": 1.1604617181854806e-05,
+      "loss": 0.42521621704101564,
+      "mean_token_accuracy": 0.8644315087795258,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.45814105302095415,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.9394752383232117,
+      "learning_rate": 1.127849200869801e-05,
+      "loss": 0.42409008026123046,
+      "mean_token_accuracy": 0.864885100722313,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.4561432495713234,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.8258721828460693,
+      "learning_rate": 1.094777429443468e-05,
+      "loss": 0.42701839447021483,
+      "mean_token_accuracy": 0.8638879442214966,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.4610430991649628,
+      "epoch": 4.789719626168225,
+      "grad_norm": 1.0002802610397339,
+      "learning_rate": 1.0613013914693477e-05,
+      "loss": 0.4286579895019531,
+      "mean_token_accuracy": 0.8643757510185242,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.4558544892072678,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.9755097031593323,
+      "learning_rate": 1.0274767466736426e-05,
+      "loss": 0.4233176803588867,
+      "mean_token_accuracy": 0.8655301338434219,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.6000483314712326,
+      "eval_loss": 0.6985165476799011,
+      "eval_mean_token_accuracy": 0.8045627912143608,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.9034,
+      "eval_samples_per_second": 26.817,
+      "eval_steps_per_second": 3.355,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 1.3194768647028326e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2568/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2568/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.010622890133962027,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2568/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2568/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2568/trainer_state.json

@@ -0,0 +1,610 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2568,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7805559730529785,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.5128960013389587,
+      "learning_rate": 1.950005322230992e-06,
+      "loss": 1.770846405029297,
+      "mean_token_accuracy": 0.6305050283670426,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.5725344836711883,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.7059135437011719,
+      "learning_rate": 3.93980667144629e-06,
+      "loss": 1.5153414916992187,
+      "mean_token_accuracy": 0.6729821544885636,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0769569373130798,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.6092284321784973,
+      "learning_rate": 5.9296080206615885e-06,
+      "loss": 1.0251461791992187,
+      "mean_token_accuracy": 0.737835128903389,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8583791655302048,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5586332082748413,
+      "learning_rate": 7.919409369876886e-06,
+      "loss": 0.81265869140625,
+      "mean_token_accuracy": 0.7762657129764556,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7744105678796768,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.4821721613407135,
+      "learning_rate": 9.909210719092184e-06,
+      "loss": 0.7364049530029297,
+      "mean_token_accuracy": 0.7918167436122894,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.715560827255249,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.6843860745429993,
+      "learning_rate": 1.1899012068307483e-05,
+      "loss": 0.6826614379882813,
+      "mean_token_accuracy": 0.8043146914243698,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6893886953592301,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.6543110013008118,
+      "learning_rate": 1.3888813417522781e-05,
+      "loss": 0.6608805847167969,
+      "mean_token_accuracy": 0.8083165866136551,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.652973799109459,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7437635660171509,
+      "learning_rate": 1.587861476673808e-05,
+      "loss": 0.6218611907958984,
+      "mean_token_accuracy": 0.8167323243618011,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.8066210185552573,
+      "eval_loss": 0.7281543016433716,
+      "eval_mean_token_accuracy": 0.7858095281309896,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 46.0044,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 3.348,
+      "step": 428
+    },
+    {
+      "entropy": 0.6467276298999787,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.626556396484375,
+      "learning_rate": 1.7031450502641085e-05,
+      "loss": 0.6161280441284179,
+      "mean_token_accuracy": 0.817004052400589,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6262363213300705,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.70875084400177,
+      "learning_rate": 1.7018425538355792e-05,
+      "loss": 0.5963106536865235,
+      "mean_token_accuracy": 0.8221335035562515,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6171189111471176,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.6629440188407898,
+      "learning_rate": 1.6991264396738895e-05,
+      "loss": 0.5875393676757813,
+      "mean_token_accuracy": 0.8245152229070664,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6083133199810982,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.5385038256645203,
+      "learning_rate": 1.6950012237904817e-05,
+      "loss": 0.5768455505371094,
+      "mean_token_accuracy": 0.8271224808692932,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.6011673760414123,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.7062859535217285,
+      "learning_rate": 1.6894737650731013e-05,
+      "loss": 0.5666856384277343,
+      "mean_token_accuracy": 0.829860600233078,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5905318284034728,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.646713137626648,
+      "learning_rate": 1.682553253881702e-05,
+      "loss": 0.560577392578125,
+      "mean_token_accuracy": 0.8313507026433945,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5964298728108406,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.6510505080223083,
+      "learning_rate": 1.674251196767876e-05,
+      "loss": 0.5606492614746094,
+      "mean_token_accuracy": 0.8313686531782151,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.5872641482949257,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.6211879849433899,
+      "learning_rate": 1.6645813973432182e-05,
+      "loss": 0.556594352722168,
+      "mean_token_accuracy": 0.8333250796794891,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5889243066310883,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.6804038882255554,
+      "learning_rate": 1.6535599333284194e-05,
+      "loss": 0.5578879928588867,
+      "mean_token_accuracy": 0.831966199874878,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.7079034389613511,
+      "eval_loss": 0.6832069158554077,
+      "eval_mean_token_accuracy": 0.8022074165282311,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 46.0398,
+      "eval_samples_per_second": 26.738,
+      "eval_steps_per_second": 3.345,
+      "step": 856
+    },
+    {
+      "entropy": 0.5462229257822037,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.5834382772445679,
+      "learning_rate": 1.6412051298212675e-05,
+      "loss": 0.5115155029296875,
+      "mean_token_accuracy": 0.8419190347194672,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5501805812120437,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.774409830570221,
+      "learning_rate": 1.627537528827988e-05,
+      "loss": 0.5193024826049805,
+      "mean_token_accuracy": 0.8415862208604813,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5417112326622009,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.8148911595344543,
+      "learning_rate": 1.612579855108594e-05,
+      "loss": 0.5099837875366211,
+      "mean_token_accuracy": 0.8432273292541503,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5426027116179466,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.738017737865448,
+      "learning_rate": 1.596356978393025e-05,
+      "loss": 0.5110509490966797,
+      "mean_token_accuracy": 0.8447510355710983,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.536553855240345,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.6512451767921448,
+      "learning_rate": 1.5788958720309008e-05,
+      "loss": 0.5046747207641602,
+      "mean_token_accuracy": 0.8439748030900955,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5361887359619141,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.7650485038757324,
+      "learning_rate": 1.5602255681436483e-05,
+      "loss": 0.5043494415283203,
+      "mean_token_accuracy": 0.8450696021318436,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.5419432005286217,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.6945335268974304,
+      "learning_rate": 1.5403771093535538e-05,
+      "loss": 0.5108187103271484,
+      "mean_token_accuracy": 0.8431807065010071,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.5400136861205102,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.774668276309967,
+      "learning_rate": 1.5193834971700146e-05,
+      "loss": 0.5082107543945312,
+      "mean_token_accuracy": 0.8444043332338333,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.6524020644364419,
+      "eval_loss": 0.6701120138168335,
+      "eval_mean_token_accuracy": 0.8018650695101007,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 46.004,
+      "eval_samples_per_second": 26.759,
+      "eval_steps_per_second": 3.348,
+      "step": 1284
+    },
+    {
+      "entropy": 0.5256310805678368,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.8875723481178284,
+      "learning_rate": 1.4972796371187997e-05,
+      "loss": 0.49435077667236327,
+      "mean_token_accuracy": 0.8473169440031052,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4986111795902252,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.8605287671089172,
+      "learning_rate": 1.4741022807055508e-05,
+      "loss": 0.4662786483764648,
+      "mean_token_accuracy": 0.8552708566188812,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.5061789083480835,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.8101795315742493,
+      "learning_rate": 1.4498899643100226e-05,
+      "loss": 0.47242179870605466,
+      "mean_token_accuracy": 0.8520459419488907,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4939887225627899,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.8013083338737488,
+      "learning_rate": 1.4246829451126602e-05,
+      "loss": 0.4614598846435547,
+      "mean_token_accuracy": 0.8552495676279068,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.4918920609354973,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.7743699550628662,
+      "learning_rate": 1.3985231341600455e-05,
+      "loss": 0.46159915924072265,
+      "mean_token_accuracy": 0.8550176537036895,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.49779762893915175,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.8169922828674316,
+      "learning_rate": 1.3714540266805045e-05,
+      "loss": 0.46558887481689454,
+      "mean_token_accuracy": 0.8540038305521012,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.5015265879034996,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.851017951965332,
+      "learning_rate": 1.343520629765737e-05,
+      "loss": 0.46733531951904295,
+      "mean_token_accuracy": 0.8522392755746842,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.501338247358799,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.8121753334999084,
+      "learning_rate": 1.3147693875387126e-05,
+      "loss": 0.4710521697998047,
+      "mean_token_accuracy": 0.8534136080741882,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.49478380143642425,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.6918302178382874,
+      "learning_rate": 1.2852481039322492e-05,
+      "loss": 0.4646331405639648,
+      "mean_token_accuracy": 0.8551374357938767,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.6295453201640736,
+      "eval_loss": 0.666642427444458,
+      "eval_mean_token_accuracy": 0.8111948270302314,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.8725,
+      "eval_samples_per_second": 26.835,
+      "eval_steps_per_second": 3.357,
+      "step": 1712
+    },
+    {
+      "entropy": 0.46167980462312697,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.8769540190696716,
+      "learning_rate": 1.2550058632066751e-05,
+      "loss": 0.4263522338867187,
+      "mean_token_accuracy": 0.8653014451265335,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.4534104973077774,
+      "epoch": 4.205607476635514,
+      "grad_norm": 1.1420735120773315,
+      "learning_rate": 1.2240929483387228e-05,
+      "loss": 0.41863834381103515,
+      "mean_token_accuracy": 0.8667230373620987,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.4606948295235634,
+      "epoch": 4.322429906542056,
+      "grad_norm": 1.0596942901611328,
+      "learning_rate": 1.1925607574173476e-05,
+      "loss": 0.42718273162841797,
+      "mean_token_accuracy": 0.8641588741540909,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.45681062549352647,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.9009803533554077,
+      "learning_rate": 1.1604617181854806e-05,
+      "loss": 0.42521621704101564,
+      "mean_token_accuracy": 0.8644315087795258,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.45814105302095415,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.9394752383232117,
+      "learning_rate": 1.127849200869801e-05,
+      "loss": 0.42409008026123046,
+      "mean_token_accuracy": 0.864885100722313,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.4561432495713234,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.8258721828460693,
+      "learning_rate": 1.094777429443468e-05,
+      "loss": 0.42701839447021483,
+      "mean_token_accuracy": 0.8638879442214966,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.4610430991649628,
+      "epoch": 4.789719626168225,
+      "grad_norm": 1.0002802610397339,
+      "learning_rate": 1.0613013914693477e-05,
+      "loss": 0.4286579895019531,
+      "mean_token_accuracy": 0.8643757510185242,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.4558544892072678,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.9755097031593323,
+      "learning_rate": 1.0274767466736426e-05,
+      "loss": 0.4233176803588867,
+      "mean_token_accuracy": 0.8655301338434219,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.6000483314712326,
+      "eval_loss": 0.6985165476799011,
+      "eval_mean_token_accuracy": 0.8045627912143608,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.9034,
+      "eval_samples_per_second": 26.817,
+      "eval_steps_per_second": 3.355,
+      "step": 2140
+    },
+    {
+      "entropy": 0.44992744773626325,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 1.1082366704940796,
+      "learning_rate": 9.933597344019314e-06,
+      "loss": 0.41550483703613283,
+      "mean_token_accuracy": 0.8669036704301835,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.4088956421613693,
+      "epoch": 5.140186915887851,
+      "grad_norm": 1.0101401805877686,
+      "learning_rate": 9.59007080111491e-06,
+      "loss": 0.3716637420654297,
+      "mean_token_accuracy": 0.8802521765232086,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.4127876952290535,
+      "epoch": 5.257009345794392,
+      "grad_norm": 1.1201362609863281,
+      "learning_rate": 9.244759010553727e-06,
+      "loss": 0.37826343536376955,
+      "mean_token_accuracy": 0.8786936563253402,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.4232992666959763,
+      "epoch": 5.373831775700935,
+      "grad_norm": 1.1778150796890259,
+      "learning_rate": 8.898236113150524e-06,
+      "loss": 0.38583309173583985,
+      "mean_token_accuracy": 0.8747973537445068,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.4159915736317635,
+      "epoch": 5.490654205607477,
+      "grad_norm": 1.1592568159103394,
+      "learning_rate": 8.551078263395478e-06,
+      "loss": 0.3784225082397461,
+      "mean_token_accuracy": 0.8779372000694274,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.41662866294384004,
+      "epoch": 5.607476635514018,
+      "grad_norm": 1.254981517791748,
+      "learning_rate": 8.203862671497323e-06,
+      "loss": 0.37995223999023436,
+      "mean_token_accuracy": 0.8772805953025817,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.417872933447361,
+      "epoch": 5.724299065420561,
+      "grad_norm": 1.322206974029541,
+      "learning_rate": 7.857166643671128e-06,
+      "loss": 0.38079578399658204,
+      "mean_token_accuracy": 0.8774149787425994,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.41878397345542906,
+      "epoch": 5.841121495327103,
+      "grad_norm": 1.2948966026306152,
+      "learning_rate": 7.511566622266466e-06,
+      "loss": 0.3861651611328125,
+      "mean_token_accuracy": 0.8755189329385757,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.4128647845983505,
+      "epoch": 5.957943925233645,
+      "grad_norm": 1.190157175064087,
+      "learning_rate": 7.167637227331918e-06,
+      "loss": 0.37860721588134766,
+      "mean_token_accuracy": 0.8772583198547363,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.5655807773401211,
+      "eval_loss": 0.7187017202377319,
+      "eval_mean_token_accuracy": 0.8067006375882533,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.9295,
+      "eval_samples_per_second": 26.802,
+      "eval_steps_per_second": 3.353,
+      "step": 2568
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 1.5831812695824384e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2996/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-2996/trainer_state.json

@@ -0,0 +1,701 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2996,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    },
+    {
+      "entropy": 0.30689359933137894,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 0.6219972372055054,
+      "learning_rate": 9.004661882888355e-05,
+      "loss": 0.27355791091918946,
+      "mean_token_accuracy": 0.9078934907913208,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.23060906335711479,
+      "epoch": 5.140186915887851,
+      "grad_norm": 0.39721137285232544,
+      "learning_rate": 8.69326005538081e-05,
+      "loss": 0.19190786361694337,
+      "mean_token_accuracy": 0.9332777208089829,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.23536642283201217,
+      "epoch": 5.257009345794392,
+      "grad_norm": 0.4206141233444214,
+      "learning_rate": 8.380239926771483e-05,
+      "loss": 0.19819820404052735,
+      "mean_token_accuracy": 0.9311726182699204,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2427162781357765,
+      "epoch": 5.373831775700935,
+      "grad_norm": 0.543883204460144,
+      "learning_rate": 8.066121947379727e-05,
+      "loss": 0.20555742263793944,
+      "mean_token_accuracy": 0.9283805179595948,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.24081297397613524,
+      "epoch": 5.490654205607477,
+      "grad_norm": 0.4346058666706085,
+      "learning_rate": 7.751428392892456e-05,
+      "loss": 0.20357828140258788,
+      "mean_token_accuracy": 0.9291914713382721,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2414954523742199,
+      "epoch": 5.607476635514018,
+      "grad_norm": 0.48998570442199707,
+      "learning_rate": 7.43668249599014e-05,
+      "loss": 0.20533323287963867,
+      "mean_token_accuracy": 0.9290326738357544,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.24239167034626008,
+      "epoch": 5.724299065420561,
+      "grad_norm": 0.5171953439712524,
+      "learning_rate": 7.122407576381592e-05,
+      "loss": 0.20603450775146484,
+      "mean_token_accuracy": 0.9289826327562332,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.24068919852375983,
+      "epoch": 5.841121495327103,
+      "grad_norm": 0.5036585330963135,
+      "learning_rate": 6.809126170694096e-05,
+      "loss": 0.20551023483276368,
+      "mean_token_accuracy": 0.9283198803663254,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.23394863292574883,
+      "epoch": 5.957943925233645,
+      "grad_norm": 0.4463285505771637,
+      "learning_rate": 6.497359163665513e-05,
+      "loss": 0.20060670852661133,
+      "mean_token_accuracy": 0.9296612071990967,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.4407621825283224,
+      "eval_loss": 0.7988200187683105,
+      "eval_mean_token_accuracy": 0.810667238839261,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.6554,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2568
+    },
+    {
+      "entropy": 0.19413772232830526,
+      "epoch": 6.074766355140187,
+      "grad_norm": 0.41453734040260315,
+      "learning_rate": 6.18762492208297e-05,
+      "loss": 0.15272833824157714,
+      "mean_token_accuracy": 0.9470745486021042,
+      "num_tokens": 8502228.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.15578473143279553,
+      "epoch": 6.191588785046729,
+      "grad_norm": 0.43579405546188354,
+      "learning_rate": 5.880438432908041e-05,
+      "loss": 0.11623106002807618,
+      "mean_token_accuracy": 0.959901955127716,
+      "num_tokens": 8670819.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.15948383696377277,
+      "epoch": 6.308411214953271,
+      "grad_norm": 0.48238715529441833,
+      "learning_rate": 5.5763104470215215e-05,
+      "loss": 0.11941349029541015,
+      "mean_token_accuracy": 0.9588177186250687,
+      "num_tokens": 8833691.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.1605475340038538,
+      "epoch": 6.425233644859813,
+      "grad_norm": 0.4522126317024231,
+      "learning_rate": 5.275746630011375e-05,
+      "loss": 0.11946668624877929,
+      "mean_token_accuracy": 0.9586575514078141,
+      "num_tokens": 8991136.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16507557310163976,
+      "epoch": 6.542056074766355,
+      "grad_norm": 0.4999944865703583,
+      "learning_rate": 4.9792467214159004e-05,
+      "loss": 0.12344318389892578,
+      "mean_token_accuracy": 0.9567851454019547,
+      "num_tokens": 9156211.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.16322320364415646,
+      "epoch": 6.658878504672897,
+      "grad_norm": 0.39386141300201416,
+      "learning_rate": 4.6873037038199605e-05,
+      "loss": 0.1236769676208496,
+      "mean_token_accuracy": 0.9565887361764908,
+      "num_tokens": 9320538.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.16041388005018234,
+      "epoch": 6.775700934579439,
+      "grad_norm": 0.4434821307659149,
+      "learning_rate": 4.400402983185835e-05,
+      "loss": 0.12205925941467285,
+      "mean_token_accuracy": 0.9575694715976715,
+      "num_tokens": 9480686.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15794747926294803,
+      "epoch": 6.892523364485982,
+      "grad_norm": 0.46692273020744324,
+      "learning_rate": 4.119021581781515e-05,
+      "loss": 0.11820981025695801,
+      "mean_token_accuracy": 0.959431186914444,
+      "num_tokens": 9644088.0,
+      "step": 2950
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.37710911519341656,
+      "eval_loss": 0.9603754281997681,
+      "eval_mean_token_accuracy": 0.8079396579172704,
+      "eval_num_tokens": 9797690.0,
+      "eval_runtime": 45.655,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2996
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 1.814310055369728e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3424/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3424/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3424/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3424/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3424/trainer_state.json

@@ -0,0 +1,802 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3424,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    },
+    {
+      "entropy": 0.30689359933137894,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 0.6219972372055054,
+      "learning_rate": 9.004661882888355e-05,
+      "loss": 0.27355791091918946,
+      "mean_token_accuracy": 0.9078934907913208,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.23060906335711479,
+      "epoch": 5.140186915887851,
+      "grad_norm": 0.39721137285232544,
+      "learning_rate": 8.69326005538081e-05,
+      "loss": 0.19190786361694337,
+      "mean_token_accuracy": 0.9332777208089829,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.23536642283201217,
+      "epoch": 5.257009345794392,
+      "grad_norm": 0.4206141233444214,
+      "learning_rate": 8.380239926771483e-05,
+      "loss": 0.19819820404052735,
+      "mean_token_accuracy": 0.9311726182699204,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2427162781357765,
+      "epoch": 5.373831775700935,
+      "grad_norm": 0.543883204460144,
+      "learning_rate": 8.066121947379727e-05,
+      "loss": 0.20555742263793944,
+      "mean_token_accuracy": 0.9283805179595948,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.24081297397613524,
+      "epoch": 5.490654205607477,
+      "grad_norm": 0.4346058666706085,
+      "learning_rate": 7.751428392892456e-05,
+      "loss": 0.20357828140258788,
+      "mean_token_accuracy": 0.9291914713382721,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2414954523742199,
+      "epoch": 5.607476635514018,
+      "grad_norm": 0.48998570442199707,
+      "learning_rate": 7.43668249599014e-05,
+      "loss": 0.20533323287963867,
+      "mean_token_accuracy": 0.9290326738357544,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.24239167034626008,
+      "epoch": 5.724299065420561,
+      "grad_norm": 0.5171953439712524,
+      "learning_rate": 7.122407576381592e-05,
+      "loss": 0.20603450775146484,
+      "mean_token_accuracy": 0.9289826327562332,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.24068919852375983,
+      "epoch": 5.841121495327103,
+      "grad_norm": 0.5036585330963135,
+      "learning_rate": 6.809126170694096e-05,
+      "loss": 0.20551023483276368,
+      "mean_token_accuracy": 0.9283198803663254,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.23394863292574883,
+      "epoch": 5.957943925233645,
+      "grad_norm": 0.4463285505771637,
+      "learning_rate": 6.497359163665513e-05,
+      "loss": 0.20060670852661133,
+      "mean_token_accuracy": 0.9296612071990967,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.4407621825283224,
+      "eval_loss": 0.7988200187683105,
+      "eval_mean_token_accuracy": 0.810667238839261,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.6554,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2568
+    },
+    {
+      "entropy": 0.19413772232830526,
+      "epoch": 6.074766355140187,
+      "grad_norm": 0.41453734040260315,
+      "learning_rate": 6.18762492208297e-05,
+      "loss": 0.15272833824157714,
+      "mean_token_accuracy": 0.9470745486021042,
+      "num_tokens": 8502228.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.15578473143279553,
+      "epoch": 6.191588785046729,
+      "grad_norm": 0.43579405546188354,
+      "learning_rate": 5.880438432908041e-05,
+      "loss": 0.11623106002807618,
+      "mean_token_accuracy": 0.959901955127716,
+      "num_tokens": 8670819.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.15948383696377277,
+      "epoch": 6.308411214953271,
+      "grad_norm": 0.48238715529441833,
+      "learning_rate": 5.5763104470215215e-05,
+      "loss": 0.11941349029541015,
+      "mean_token_accuracy": 0.9588177186250687,
+      "num_tokens": 8833691.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.1605475340038538,
+      "epoch": 6.425233644859813,
+      "grad_norm": 0.4522126317024231,
+      "learning_rate": 5.275746630011375e-05,
+      "loss": 0.11946668624877929,
+      "mean_token_accuracy": 0.9586575514078141,
+      "num_tokens": 8991136.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16507557310163976,
+      "epoch": 6.542056074766355,
+      "grad_norm": 0.4999944865703583,
+      "learning_rate": 4.9792467214159004e-05,
+      "loss": 0.12344318389892578,
+      "mean_token_accuracy": 0.9567851454019547,
+      "num_tokens": 9156211.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.16322320364415646,
+      "epoch": 6.658878504672897,
+      "grad_norm": 0.39386141300201416,
+      "learning_rate": 4.6873037038199605e-05,
+      "loss": 0.1236769676208496,
+      "mean_token_accuracy": 0.9565887361764908,
+      "num_tokens": 9320538.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.16041388005018234,
+      "epoch": 6.775700934579439,
+      "grad_norm": 0.4434821307659149,
+      "learning_rate": 4.400402983185835e-05,
+      "loss": 0.12205925941467285,
+      "mean_token_accuracy": 0.9575694715976715,
+      "num_tokens": 9480686.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15794747926294803,
+      "epoch": 6.892523364485982,
+      "grad_norm": 0.46692273020744324,
+      "learning_rate": 4.119021581781515e-05,
+      "loss": 0.11820981025695801,
+      "mean_token_accuracy": 0.959431186914444,
+      "num_tokens": 9644088.0,
+      "step": 2950
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.37710911519341656,
+      "eval_loss": 0.9603754281997681,
+      "eval_mean_token_accuracy": 0.8079396579172704,
+      "eval_num_tokens": 9797690.0,
+      "eval_runtime": 45.655,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2996
+    },
+    {
+      "entropy": 0.15656570471823217,
+      "epoch": 7.009345794392523,
+      "grad_norm": 0.3916987478733063,
+      "learning_rate": 3.843627345048353e-05,
+      "loss": 0.11604588508605956,
+      "mean_token_accuracy": 0.959635105729103,
+      "num_tokens": 9809264.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.11141053996980191,
+      "epoch": 7.126168224299065,
+      "grad_norm": 0.37652429938316345,
+      "learning_rate": 3.5746781637267694e-05,
+      "loss": 0.07014975070953369,
+      "mean_token_accuracy": 0.9768576163053513,
+      "num_tokens": 9972116.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.1082563553750515,
+      "epoch": 7.242990654205608,
+      "grad_norm": 0.5874696969985962,
+      "learning_rate": 3.312621212533388e-05,
+      "loss": 0.06926133155822754,
+      "mean_token_accuracy": 0.9767617470026017,
+      "num_tokens": 10137487.0,
+      "step": 3100
+    },
+    {
+      "entropy": 0.10475032545626163,
+      "epoch": 7.359813084112149,
+      "grad_norm": 0.3031817078590393,
+      "learning_rate": 3.0578922066554204e-05,
+      "loss": 0.06838406085968017,
+      "mean_token_accuracy": 0.9779873842000961,
+      "num_tokens": 10302931.0,
+      "step": 3150
+    },
+    {
+      "entropy": 0.11219218984246254,
+      "epoch": 7.4766355140186915,
+      "grad_norm": 0.37162110209465027,
+      "learning_rate": 2.810914677298496e-05,
+      "loss": 0.07271810531616212,
+      "mean_token_accuracy": 0.9758705735206604,
+      "num_tokens": 10458987.0,
+      "step": 3200
+    },
+    {
+      "entropy": 0.10745158478617668,
+      "epoch": 7.593457943925234,
+      "grad_norm": 0.35573893785476685,
+      "learning_rate": 2.5720992674924995e-05,
+      "loss": 0.06988383769989014,
+      "mean_token_accuracy": 0.9772955650091171,
+      "num_tokens": 10626220.0,
+      "step": 3250
+    },
+    {
+      "entropy": 0.109193622097373,
+      "epoch": 7.710280373831775,
+      "grad_norm": 0.40555712580680847,
+      "learning_rate": 2.3418430493262215e-05,
+      "loss": 0.07179480075836181,
+      "mean_token_accuracy": 0.9755140417814254,
+      "num_tokens": 10791927.0,
+      "step": 3300
+    },
+    {
+      "entropy": 0.10803250230848789,
+      "epoch": 7.827102803738318,
+      "grad_norm": 0.3087987005710602,
+      "learning_rate": 2.1205288637460552e-05,
+      "loss": 0.06999539375305176,
+      "mean_token_accuracy": 0.9768486160039902,
+      "num_tokens": 10959396.0,
+      "step": 3350
+    },
+    {
+      "entropy": 0.10778876394033432,
+      "epoch": 7.94392523364486,
+      "grad_norm": 0.27656036615371704,
+      "learning_rate": 1.908524684016453e-05,
+      "loss": 0.07048747539520264,
+      "mean_token_accuracy": 0.9763320505619049,
+      "num_tokens": 11119550.0,
+      "step": 3400
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.34777289396756655,
+      "eval_loss": 1.0812466144561768,
+      "eval_mean_token_accuracy": 0.806237152257523,
+      "eval_num_tokens": 11197360.0,
+      "eval_runtime": 45.6576,
+      "eval_samples_per_second": 26.962,
+      "eval_steps_per_second": 3.373,
+      "step": 3424
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 2.069744468370432e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3852/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3852/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3852/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3852/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-3852/trainer_state.json

@@ -0,0 +1,903 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 3852,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    },
+    {
+      "entropy": 0.30689359933137894,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 0.6219972372055054,
+      "learning_rate": 9.004661882888355e-05,
+      "loss": 0.27355791091918946,
+      "mean_token_accuracy": 0.9078934907913208,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.23060906335711479,
+      "epoch": 5.140186915887851,
+      "grad_norm": 0.39721137285232544,
+      "learning_rate": 8.69326005538081e-05,
+      "loss": 0.19190786361694337,
+      "mean_token_accuracy": 0.9332777208089829,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.23536642283201217,
+      "epoch": 5.257009345794392,
+      "grad_norm": 0.4206141233444214,
+      "learning_rate": 8.380239926771483e-05,
+      "loss": 0.19819820404052735,
+      "mean_token_accuracy": 0.9311726182699204,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2427162781357765,
+      "epoch": 5.373831775700935,
+      "grad_norm": 0.543883204460144,
+      "learning_rate": 8.066121947379727e-05,
+      "loss": 0.20555742263793944,
+      "mean_token_accuracy": 0.9283805179595948,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.24081297397613524,
+      "epoch": 5.490654205607477,
+      "grad_norm": 0.4346058666706085,
+      "learning_rate": 7.751428392892456e-05,
+      "loss": 0.20357828140258788,
+      "mean_token_accuracy": 0.9291914713382721,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2414954523742199,
+      "epoch": 5.607476635514018,
+      "grad_norm": 0.48998570442199707,
+      "learning_rate": 7.43668249599014e-05,
+      "loss": 0.20533323287963867,
+      "mean_token_accuracy": 0.9290326738357544,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.24239167034626008,
+      "epoch": 5.724299065420561,
+      "grad_norm": 0.5171953439712524,
+      "learning_rate": 7.122407576381592e-05,
+      "loss": 0.20603450775146484,
+      "mean_token_accuracy": 0.9289826327562332,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.24068919852375983,
+      "epoch": 5.841121495327103,
+      "grad_norm": 0.5036585330963135,
+      "learning_rate": 6.809126170694096e-05,
+      "loss": 0.20551023483276368,
+      "mean_token_accuracy": 0.9283198803663254,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.23394863292574883,
+      "epoch": 5.957943925233645,
+      "grad_norm": 0.4463285505771637,
+      "learning_rate": 6.497359163665513e-05,
+      "loss": 0.20060670852661133,
+      "mean_token_accuracy": 0.9296612071990967,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.4407621825283224,
+      "eval_loss": 0.7988200187683105,
+      "eval_mean_token_accuracy": 0.810667238839261,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.6554,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2568
+    },
+    {
+      "entropy": 0.19413772232830526,
+      "epoch": 6.074766355140187,
+      "grad_norm": 0.41453734040260315,
+      "learning_rate": 6.18762492208297e-05,
+      "loss": 0.15272833824157714,
+      "mean_token_accuracy": 0.9470745486021042,
+      "num_tokens": 8502228.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.15578473143279553,
+      "epoch": 6.191588785046729,
+      "grad_norm": 0.43579405546188354,
+      "learning_rate": 5.880438432908041e-05,
+      "loss": 0.11623106002807618,
+      "mean_token_accuracy": 0.959901955127716,
+      "num_tokens": 8670819.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.15948383696377277,
+      "epoch": 6.308411214953271,
+      "grad_norm": 0.48238715529441833,
+      "learning_rate": 5.5763104470215215e-05,
+      "loss": 0.11941349029541015,
+      "mean_token_accuracy": 0.9588177186250687,
+      "num_tokens": 8833691.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.1605475340038538,
+      "epoch": 6.425233644859813,
+      "grad_norm": 0.4522126317024231,
+      "learning_rate": 5.275746630011375e-05,
+      "loss": 0.11946668624877929,
+      "mean_token_accuracy": 0.9586575514078141,
+      "num_tokens": 8991136.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16507557310163976,
+      "epoch": 6.542056074766355,
+      "grad_norm": 0.4999944865703583,
+      "learning_rate": 4.9792467214159004e-05,
+      "loss": 0.12344318389892578,
+      "mean_token_accuracy": 0.9567851454019547,
+      "num_tokens": 9156211.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.16322320364415646,
+      "epoch": 6.658878504672897,
+      "grad_norm": 0.39386141300201416,
+      "learning_rate": 4.6873037038199605e-05,
+      "loss": 0.1236769676208496,
+      "mean_token_accuracy": 0.9565887361764908,
+      "num_tokens": 9320538.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.16041388005018234,
+      "epoch": 6.775700934579439,
+      "grad_norm": 0.4434821307659149,
+      "learning_rate": 4.400402983185835e-05,
+      "loss": 0.12205925941467285,
+      "mean_token_accuracy": 0.9575694715976715,
+      "num_tokens": 9480686.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15794747926294803,
+      "epoch": 6.892523364485982,
+      "grad_norm": 0.46692273020744324,
+      "learning_rate": 4.119021581781515e-05,
+      "loss": 0.11820981025695801,
+      "mean_token_accuracy": 0.959431186914444,
+      "num_tokens": 9644088.0,
+      "step": 2950
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.37710911519341656,
+      "eval_loss": 0.9603754281997681,
+      "eval_mean_token_accuracy": 0.8079396579172704,
+      "eval_num_tokens": 9797690.0,
+      "eval_runtime": 45.655,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2996
+    },
+    {
+      "entropy": 0.15656570471823217,
+      "epoch": 7.009345794392523,
+      "grad_norm": 0.3916987478733063,
+      "learning_rate": 3.843627345048353e-05,
+      "loss": 0.11604588508605956,
+      "mean_token_accuracy": 0.959635105729103,
+      "num_tokens": 9809264.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.11141053996980191,
+      "epoch": 7.126168224299065,
+      "grad_norm": 0.37652429938316345,
+      "learning_rate": 3.5746781637267694e-05,
+      "loss": 0.07014975070953369,
+      "mean_token_accuracy": 0.9768576163053513,
+      "num_tokens": 9972116.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.1082563553750515,
+      "epoch": 7.242990654205608,
+      "grad_norm": 0.5874696969985962,
+      "learning_rate": 3.312621212533388e-05,
+      "loss": 0.06926133155822754,
+      "mean_token_accuracy": 0.9767617470026017,
+      "num_tokens": 10137487.0,
+      "step": 3100
+    },
+    {
+      "entropy": 0.10475032545626163,
+      "epoch": 7.359813084112149,
+      "grad_norm": 0.3031817078590393,
+      "learning_rate": 3.0578922066554204e-05,
+      "loss": 0.06838406085968017,
+      "mean_token_accuracy": 0.9779873842000961,
+      "num_tokens": 10302931.0,
+      "step": 3150
+    },
+    {
+      "entropy": 0.11219218984246254,
+      "epoch": 7.4766355140186915,
+      "grad_norm": 0.37162110209465027,
+      "learning_rate": 2.810914677298496e-05,
+      "loss": 0.07271810531616212,
+      "mean_token_accuracy": 0.9758705735206604,
+      "num_tokens": 10458987.0,
+      "step": 3200
+    },
+    {
+      "entropy": 0.10745158478617668,
+      "epoch": 7.593457943925234,
+      "grad_norm": 0.35573893785476685,
+      "learning_rate": 2.5720992674924995e-05,
+      "loss": 0.06988383769989014,
+      "mean_token_accuracy": 0.9772955650091171,
+      "num_tokens": 10626220.0,
+      "step": 3250
+    },
+    {
+      "entropy": 0.109193622097373,
+      "epoch": 7.710280373831775,
+      "grad_norm": 0.40555712580680847,
+      "learning_rate": 2.3418430493262215e-05,
+      "loss": 0.07179480075836181,
+      "mean_token_accuracy": 0.9755140417814254,
+      "num_tokens": 10791927.0,
+      "step": 3300
+    },
+    {
+      "entropy": 0.10803250230848789,
+      "epoch": 7.827102803738318,
+      "grad_norm": 0.3087987005710602,
+      "learning_rate": 2.1205288637460552e-05,
+      "loss": 0.06999539375305176,
+      "mean_token_accuracy": 0.9768486160039902,
+      "num_tokens": 10959396.0,
+      "step": 3350
+    },
+    {
+      "entropy": 0.10778876394033432,
+      "epoch": 7.94392523364486,
+      "grad_norm": 0.27656036615371704,
+      "learning_rate": 1.908524684016453e-05,
+      "loss": 0.07048747539520264,
+      "mean_token_accuracy": 0.9763320505619049,
+      "num_tokens": 11119550.0,
+      "step": 3400
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.34777289396756655,
+      "eval_loss": 1.0812466144561768,
+      "eval_mean_token_accuracy": 0.806237152257523,
+      "eval_num_tokens": 11197360.0,
+      "eval_runtime": 45.6576,
+      "eval_samples_per_second": 26.962,
+      "eval_steps_per_second": 3.373,
+      "step": 3424
+    },
+    {
+      "entropy": 0.09966455139219761,
+      "epoch": 8.060747663551401,
+      "grad_norm": 0.20207089185714722,
+      "learning_rate": 1.706183003900461e-05,
+      "loss": 0.06077207088470459,
+      "mean_token_accuracy": 0.9799167662858963,
+      "num_tokens": 11282774.0,
+      "step": 3450
+    },
+    {
+      "entropy": 0.08810539588332177,
+      "epoch": 8.177570093457945,
+      "grad_norm": 0.26586610078811646,
+      "learning_rate": 1.5138402515776445e-05,
+      "loss": 0.05182623863220215,
+      "mean_token_accuracy": 0.9829341900348664,
+      "num_tokens": 11443420.0,
+      "step": 3500
+    },
+    {
+      "entropy": 0.08581781014800072,
+      "epoch": 8.294392523364486,
+      "grad_norm": 0.23626543581485748,
+      "learning_rate": 1.3318162302738134e-05,
+      "loss": 0.05171567916870117,
+      "mean_token_accuracy": 0.9829980742931366,
+      "num_tokens": 11603266.0,
+      "step": 3550
+    },
+    {
+      "entropy": 0.08447251889854669,
+      "epoch": 8.411214953271028,
+      "grad_norm": 0.20069944858551025,
+      "learning_rate": 1.1604135865326149e-05,
+      "loss": 0.051477575302124025,
+      "mean_token_accuracy": 0.9827573680877686,
+      "num_tokens": 11766536.0,
+      "step": 3600
+    },
+    {
+      "entropy": 0.08470481634140015,
+      "epoch": 8.52803738317757,
+      "grad_norm": 0.2061646282672882,
+      "learning_rate": 9.999173070131157e-06,
+      "loss": 0.050427241325378416,
+      "mean_token_accuracy": 0.9830707877874374,
+      "num_tokens": 11934812.0,
+      "step": 3650
+    },
+    {
+      "entropy": 0.08829616207629443,
+      "epoch": 8.644859813084112,
+      "grad_norm": 0.16281439363956451,
+      "learning_rate": 8.505942446499943e-06,
+      "loss": 0.05281091213226318,
+      "mean_token_accuracy": 0.9818410485982895,
+      "num_tokens": 12095307.0,
+      "step": 3700
+    },
+    {
+      "entropy": 0.08360566295683385,
+      "epoch": 8.761682242990654,
+      "grad_norm": 0.21016450226306915,
+      "learning_rate": 7.126926749641805e-06,
+      "loss": 0.050207719802856446,
+      "mean_token_accuracy": 0.9829736703634262,
+      "num_tokens": 12267401.0,
+      "step": 3750
+    },
+    {
+      "entropy": 0.08554164603352547,
+      "epoch": 8.878504672897197,
+      "grad_norm": 0.23642295598983765,
+      "learning_rate": 5.864418832617066e-06,
+      "loss": 0.05177981853485107,
+      "mean_token_accuracy": 0.9826503986120224,
+      "num_tokens": 12432027.0,
+      "step": 3800
+    },
+    {
+      "entropy": 0.0869401066750288,
+      "epoch": 8.995327102803738,
+      "grad_norm": 0.2289862483739853,
+      "learning_rate": 4.720517834070658e-06,
+      "loss": 0.05334438323974609,
+      "mean_token_accuracy": 0.9820096504688263,
+      "num_tokens": 12591339.0,
+      "step": 3850
+    },
+    {
+      "epoch": 9.0,
+      "eval_entropy": 0.3211280666775518,
+      "eval_loss": 1.2116189002990723,
+      "eval_mean_token_accuracy": 0.8066579533087743,
+      "eval_num_tokens": 12597030.0,
+      "eval_runtime": 45.6428,
+      "eval_samples_per_second": 26.97,
+      "eval_steps_per_second": 3.374,
+      "step": 3852
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 2.330032650172416e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-428/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-428/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-428/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-428/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-428/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 2.58968312300544e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-4280/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-4280/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-4280/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-4280/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-4280/trainer_state.json

@@ -0,0 +1,994 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    },
+    {
+      "entropy": 0.47262389928102494,
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.2535194158554077,
+      "learning_rate": 0.00014877286407627584,
+      "loss": 0.4428855514526367,
+      "mean_token_accuracy": 0.8600562286376953,
+      "num_tokens": 2951115.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.47976606965065005,
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.30369797348976135,
+      "learning_rate": 0.00014753391587420475,
+      "loss": 0.44907299041748044,
+      "mean_token_accuracy": 0.8582676541805268,
+      "num_tokens": 3115016.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.47275764375925067,
+      "epoch": 2.336448598130841,
+      "grad_norm": 0.3171652853488922,
+      "learning_rate": 0.0001461780244510558,
+      "loss": 0.44435993194580076,
+      "mean_token_accuracy": 0.8601345640420913,
+      "num_tokens": 3274313.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.4735608258843422,
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.29764947295188904,
+      "learning_rate": 0.00014470744421176885,
+      "loss": 0.44539962768554686,
+      "mean_token_accuracy": 0.8607082539796829,
+      "num_tokens": 3440379.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4744651636481285,
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.23777751624584198,
+      "learning_rate": 0.00014312462025135595,
+      "loss": 0.44422054290771484,
+      "mean_token_accuracy": 0.859566843509674,
+      "num_tokens": 3606755.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.47177853137254716,
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.28442806005477905,
+      "learning_rate": 0.00014143218428950668,
+      "loss": 0.4431512069702148,
+      "mean_token_accuracy": 0.8603039968013764,
+      "num_tokens": 3766555.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.4803256571292877,
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.2728305757045746,
+      "learning_rate": 0.00013963295029489697,
+      "loss": 0.44966583251953124,
+      "mean_token_accuracy": 0.8587929052114487,
+      "num_tokens": 3927164.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4743427449464798,
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.29242947697639465,
+      "learning_rate": 0.0001377299098064774,
+      "loss": 0.4463462829589844,
+      "mean_token_accuracy": 0.8596956437826156,
+      "num_tokens": 4090727.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.611924365356371,
+      "eval_loss": 0.6364901661872864,
+      "eval_mean_token_accuracy": 0.8110434765165503,
+      "eval_num_tokens": 4199010.0,
+      "eval_runtime": 45.6331,
+      "eval_samples_per_second": 26.976,
+      "eval_steps_per_second": 3.375,
+      "step": 1284
+    },
+    {
+      "entropy": 0.4497017902135849,
+      "epoch": 3.0373831775700935,
+      "grad_norm": 0.36632540822029114,
+      "learning_rate": 0.0001357262269595206,
+      "loss": 0.41871109008789065,
+      "mean_token_accuracy": 0.8677674496173858,
+      "num_tokens": 4252535.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.39628969103097916,
+      "epoch": 3.1542056074766354,
+      "grad_norm": 0.3463972210884094,
+      "learning_rate": 0.00013362523322469648,
+      "loss": 0.3633641815185547,
+      "mean_token_accuracy": 0.8810112345218658,
+      "num_tokens": 4414122.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.405142662525177,
+      "epoch": 3.2710280373831777,
+      "grad_norm": 0.3261754512786865,
+      "learning_rate": 0.00013143042186892402,
+      "loss": 0.37408100128173827,
+      "mean_token_accuracy": 0.8773768872022629,
+      "num_tokens": 4571859.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.3960475382208824,
+      "epoch": 3.3878504672897196,
+      "grad_norm": 0.32290324568748474,
+      "learning_rate": 0.00012914544214720838,
+      "loss": 0.3667728424072266,
+      "mean_token_accuracy": 0.8809277415275574,
+      "num_tokens": 4735006.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.39949932754039763,
+      "epoch": 3.5046728971962615,
+      "grad_norm": 0.3406212627887726,
+      "learning_rate": 0.0001267740932351207,
+      "loss": 0.37073043823242186,
+      "mean_token_accuracy": 0.879340250492096,
+      "num_tokens": 4898228.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.4047835928201675,
+      "epoch": 3.621495327102804,
+      "grad_norm": 0.30698826909065247,
+      "learning_rate": 0.00012432031791200892,
+      "loss": 0.3761457824707031,
+      "mean_token_accuracy": 0.8780743163824082,
+      "num_tokens": 5063413.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.4085030257701874,
+      "epoch": 3.7383177570093458,
+      "grad_norm": 0.30055665969848633,
+      "learning_rate": 0.00012178819600544269,
+      "loss": 0.379119873046875,
+      "mean_token_accuracy": 0.8756581097841263,
+      "num_tokens": 5227672.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.4101005423069,
+      "epoch": 3.8551401869158877,
+      "grad_norm": 0.32962530851364136,
+      "learning_rate": 0.00011918193760779132,
+      "loss": 0.3822117614746094,
+      "mean_token_accuracy": 0.8762752747535706,
+      "num_tokens": 5389834.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.40136953949928283,
+      "epoch": 3.97196261682243,
+      "grad_norm": 0.2512304186820984,
+      "learning_rate": 0.00011650587607621428,
+      "loss": 0.3733771514892578,
+      "mean_token_accuracy": 0.8783003056049347,
+      "num_tokens": 5559167.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.5574058420085287,
+      "eval_loss": 0.6562352180480957,
+      "eval_mean_token_accuracy": 0.8172229067845778,
+      "eval_num_tokens": 5598680.0,
+      "eval_runtime": 45.6372,
+      "eval_samples_per_second": 26.974,
+      "eval_steps_per_second": 3.374,
+      "step": 1712
+    },
+    {
+      "entropy": 0.33769124254584315,
+      "epoch": 4.088785046728972,
+      "grad_norm": 0.35916072130203247,
+      "learning_rate": 0.00011376446082770247,
+      "loss": 0.3022454833984375,
+      "mean_token_accuracy": 0.898470618724823,
+      "num_tokens": 5721701.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3153342293202877,
+      "epoch": 4.205607476635514,
+      "grad_norm": 0.4674874544143677,
+      "learning_rate": 0.00011096224994114971,
+      "loss": 0.28416419982910157,
+      "mean_token_accuracy": 0.9044169551134109,
+      "num_tokens": 5884163.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.32269440904259683,
+      "epoch": 4.322429906542056,
+      "grad_norm": 0.4200516641139984,
+      "learning_rate": 0.00010810390257875522,
+      "loss": 0.29085651397705076,
+      "mean_token_accuracy": 0.9013593572378159,
+      "num_tokens": 6053869.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.324297761619091,
+      "epoch": 4.4392523364485985,
+      "grad_norm": 0.35716596245765686,
+      "learning_rate": 0.0001051941712393573,
+      "loss": 0.2931093406677246,
+      "mean_token_accuracy": 0.9010413753986358,
+      "num_tokens": 6217351.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.3256940242648125,
+      "epoch": 4.55607476635514,
+      "grad_norm": 0.35059621930122375,
+      "learning_rate": 0.00010223789385657872,
+      "loss": 0.29291555404663083,
+      "mean_token_accuracy": 0.9013585340976715,
+      "num_tokens": 6379796.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.32556063055992124,
+      "epoch": 4.672897196261682,
+      "grad_norm": 0.31053468585014343,
+      "learning_rate": 9.923998575492214e-05,
+      "loss": 0.29418453216552737,
+      "mean_token_accuracy": 0.9006082111597061,
+      "num_tokens": 6550276.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3271982085704803,
+      "epoch": 4.789719626168225,
+      "grad_norm": 0.3549234867095947,
+      "learning_rate": 9.62054314771894e-05,
+      "loss": 0.293514575958252,
+      "mean_token_accuracy": 0.9009167104959488,
+      "num_tokens": 6709429.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.32230626583099364,
+      "epoch": 4.906542056074766,
+      "grad_norm": 0.36930036544799805,
+      "learning_rate": 9.313927649681362e-05,
+      "loss": 0.29048364639282226,
+      "mean_token_accuracy": 0.9017211717367172,
+      "num_tokens": 6870956.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.5097629334051887,
+      "eval_loss": 0.7178825736045837,
+      "eval_mean_token_accuracy": 0.8133898025209253,
+      "eval_num_tokens": 6998350.0,
+      "eval_runtime": 45.6467,
+      "eval_samples_per_second": 26.968,
+      "eval_steps_per_second": 3.374,
+      "step": 2140
+    },
+    {
+      "entropy": 0.30689359933137894,
+      "epoch": 5.0233644859813085,
+      "grad_norm": 0.6219972372055054,
+      "learning_rate": 9.004661882888355e-05,
+      "loss": 0.27355791091918946,
+      "mean_token_accuracy": 0.9078934907913208,
+      "num_tokens": 7034085.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.23060906335711479,
+      "epoch": 5.140186915887851,
+      "grad_norm": 0.39721137285232544,
+      "learning_rate": 8.69326005538081e-05,
+      "loss": 0.19190786361694337,
+      "mean_token_accuracy": 0.9332777208089829,
+      "num_tokens": 7198745.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.23536642283201217,
+      "epoch": 5.257009345794392,
+      "grad_norm": 0.4206141233444214,
+      "learning_rate": 8.380239926771483e-05,
+      "loss": 0.19819820404052735,
+      "mean_token_accuracy": 0.9311726182699204,
+      "num_tokens": 7366588.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.2427162781357765,
+      "epoch": 5.373831775700935,
+      "grad_norm": 0.543883204460144,
+      "learning_rate": 8.066121947379727e-05,
+      "loss": 0.20555742263793944,
+      "mean_token_accuracy": 0.9283805179595948,
+      "num_tokens": 7531696.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.24081297397613524,
+      "epoch": 5.490654205607477,
+      "grad_norm": 0.4346058666706085,
+      "learning_rate": 7.751428392892456e-05,
+      "loss": 0.20357828140258788,
+      "mean_token_accuracy": 0.9291914713382721,
+      "num_tokens": 7688960.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2414954523742199,
+      "epoch": 5.607476635514018,
+      "grad_norm": 0.48998570442199707,
+      "learning_rate": 7.43668249599014e-05,
+      "loss": 0.20533323287963867,
+      "mean_token_accuracy": 0.9290326738357544,
+      "num_tokens": 7851053.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.24239167034626008,
+      "epoch": 5.724299065420561,
+      "grad_norm": 0.5171953439712524,
+      "learning_rate": 7.122407576381592e-05,
+      "loss": 0.20603450775146484,
+      "mean_token_accuracy": 0.9289826327562332,
+      "num_tokens": 8001524.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.24068919852375983,
+      "epoch": 5.841121495327103,
+      "grad_norm": 0.5036585330963135,
+      "learning_rate": 6.809126170694096e-05,
+      "loss": 0.20551023483276368,
+      "mean_token_accuracy": 0.9283198803663254,
+      "num_tokens": 8166394.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.23394863292574883,
+      "epoch": 5.957943925233645,
+      "grad_norm": 0.4463285505771637,
+      "learning_rate": 6.497359163665513e-05,
+      "loss": 0.20060670852661133,
+      "mean_token_accuracy": 0.9296612071990967,
+      "num_tokens": 8339045.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.4407621825283224,
+      "eval_loss": 0.7988200187683105,
+      "eval_mean_token_accuracy": 0.810667238839261,
+      "eval_num_tokens": 8398020.0,
+      "eval_runtime": 45.6554,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2568
+    },
+    {
+      "entropy": 0.19413772232830526,
+      "epoch": 6.074766355140187,
+      "grad_norm": 0.41453734040260315,
+      "learning_rate": 6.18762492208297e-05,
+      "loss": 0.15272833824157714,
+      "mean_token_accuracy": 0.9470745486021042,
+      "num_tokens": 8502228.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.15578473143279553,
+      "epoch": 6.191588785046729,
+      "grad_norm": 0.43579405546188354,
+      "learning_rate": 5.880438432908041e-05,
+      "loss": 0.11623106002807618,
+      "mean_token_accuracy": 0.959901955127716,
+      "num_tokens": 8670819.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.15948383696377277,
+      "epoch": 6.308411214953271,
+      "grad_norm": 0.48238715529441833,
+      "learning_rate": 5.5763104470215215e-05,
+      "loss": 0.11941349029541015,
+      "mean_token_accuracy": 0.9588177186250687,
+      "num_tokens": 8833691.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.1605475340038538,
+      "epoch": 6.425233644859813,
+      "grad_norm": 0.4522126317024231,
+      "learning_rate": 5.275746630011375e-05,
+      "loss": 0.11946668624877929,
+      "mean_token_accuracy": 0.9586575514078141,
+      "num_tokens": 8991136.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.16507557310163976,
+      "epoch": 6.542056074766355,
+      "grad_norm": 0.4999944865703583,
+      "learning_rate": 4.9792467214159004e-05,
+      "loss": 0.12344318389892578,
+      "mean_token_accuracy": 0.9567851454019547,
+      "num_tokens": 9156211.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.16322320364415646,
+      "epoch": 6.658878504672897,
+      "grad_norm": 0.39386141300201416,
+      "learning_rate": 4.6873037038199605e-05,
+      "loss": 0.1236769676208496,
+      "mean_token_accuracy": 0.9565887361764908,
+      "num_tokens": 9320538.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.16041388005018234,
+      "epoch": 6.775700934579439,
+      "grad_norm": 0.4434821307659149,
+      "learning_rate": 4.400402983185835e-05,
+      "loss": 0.12205925941467285,
+      "mean_token_accuracy": 0.9575694715976715,
+      "num_tokens": 9480686.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.15794747926294803,
+      "epoch": 6.892523364485982,
+      "grad_norm": 0.46692273020744324,
+      "learning_rate": 4.119021581781515e-05,
+      "loss": 0.11820981025695801,
+      "mean_token_accuracy": 0.959431186914444,
+      "num_tokens": 9644088.0,
+      "step": 2950
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.37710911519341656,
+      "eval_loss": 0.9603754281997681,
+      "eval_mean_token_accuracy": 0.8079396579172704,
+      "eval_num_tokens": 9797690.0,
+      "eval_runtime": 45.655,
+      "eval_samples_per_second": 26.963,
+      "eval_steps_per_second": 3.373,
+      "step": 2996
+    },
+    {
+      "entropy": 0.15656570471823217,
+      "epoch": 7.009345794392523,
+      "grad_norm": 0.3916987478733063,
+      "learning_rate": 3.843627345048353e-05,
+      "loss": 0.11604588508605956,
+      "mean_token_accuracy": 0.959635105729103,
+      "num_tokens": 9809264.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.11141053996980191,
+      "epoch": 7.126168224299065,
+      "grad_norm": 0.37652429938316345,
+      "learning_rate": 3.5746781637267694e-05,
+      "loss": 0.07014975070953369,
+      "mean_token_accuracy": 0.9768576163053513,
+      "num_tokens": 9972116.0,
+      "step": 3050
+    },
+    {
+      "entropy": 0.1082563553750515,
+      "epoch": 7.242990654205608,
+      "grad_norm": 0.5874696969985962,
+      "learning_rate": 3.312621212533388e-05,
+      "loss": 0.06926133155822754,
+      "mean_token_accuracy": 0.9767617470026017,
+      "num_tokens": 10137487.0,
+      "step": 3100
+    },
+    {
+      "entropy": 0.10475032545626163,
+      "epoch": 7.359813084112149,
+      "grad_norm": 0.3031817078590393,
+      "learning_rate": 3.0578922066554204e-05,
+      "loss": 0.06838406085968017,
+      "mean_token_accuracy": 0.9779873842000961,
+      "num_tokens": 10302931.0,
+      "step": 3150
+    },
+    {
+      "entropy": 0.11219218984246254,
+      "epoch": 7.4766355140186915,
+      "grad_norm": 0.37162110209465027,
+      "learning_rate": 2.810914677298496e-05,
+      "loss": 0.07271810531616212,
+      "mean_token_accuracy": 0.9758705735206604,
+      "num_tokens": 10458987.0,
+      "step": 3200
+    },
+    {
+      "entropy": 0.10745158478617668,
+      "epoch": 7.593457943925234,
+      "grad_norm": 0.35573893785476685,
+      "learning_rate": 2.5720992674924995e-05,
+      "loss": 0.06988383769989014,
+      "mean_token_accuracy": 0.9772955650091171,
+      "num_tokens": 10626220.0,
+      "step": 3250
+    },
+    {
+      "entropy": 0.109193622097373,
+      "epoch": 7.710280373831775,
+      "grad_norm": 0.40555712580680847,
+      "learning_rate": 2.3418430493262215e-05,
+      "loss": 0.07179480075836181,
+      "mean_token_accuracy": 0.9755140417814254,
+      "num_tokens": 10791927.0,
+      "step": 3300
+    },
+    {
+      "entropy": 0.10803250230848789,
+      "epoch": 7.827102803738318,
+      "grad_norm": 0.3087987005710602,
+      "learning_rate": 2.1205288637460552e-05,
+      "loss": 0.06999539375305176,
+      "mean_token_accuracy": 0.9768486160039902,
+      "num_tokens": 10959396.0,
+      "step": 3350
+    },
+    {
+      "entropy": 0.10778876394033432,
+      "epoch": 7.94392523364486,
+      "grad_norm": 0.27656036615371704,
+      "learning_rate": 1.908524684016453e-05,
+      "loss": 0.07048747539520264,
+      "mean_token_accuracy": 0.9763320505619049,
+      "num_tokens": 11119550.0,
+      "step": 3400
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.34777289396756655,
+      "eval_loss": 1.0812466144561768,
+      "eval_mean_token_accuracy": 0.806237152257523,
+      "eval_num_tokens": 11197360.0,
+      "eval_runtime": 45.6576,
+      "eval_samples_per_second": 26.962,
+      "eval_steps_per_second": 3.373,
+      "step": 3424
+    },
+    {
+      "entropy": 0.09966455139219761,
+      "epoch": 8.060747663551401,
+      "grad_norm": 0.20207089185714722,
+      "learning_rate": 1.706183003900461e-05,
+      "loss": 0.06077207088470459,
+      "mean_token_accuracy": 0.9799167662858963,
+      "num_tokens": 11282774.0,
+      "step": 3450
+    },
+    {
+      "entropy": 0.08810539588332177,
+      "epoch": 8.177570093457945,
+      "grad_norm": 0.26586610078811646,
+      "learning_rate": 1.5138402515776445e-05,
+      "loss": 0.05182623863220215,
+      "mean_token_accuracy": 0.9829341900348664,
+      "num_tokens": 11443420.0,
+      "step": 3500
+    },
+    {
+      "entropy": 0.08581781014800072,
+      "epoch": 8.294392523364486,
+      "grad_norm": 0.23626543581485748,
+      "learning_rate": 1.3318162302738134e-05,
+      "loss": 0.05171567916870117,
+      "mean_token_accuracy": 0.9829980742931366,
+      "num_tokens": 11603266.0,
+      "step": 3550
+    },
+    {
+      "entropy": 0.08447251889854669,
+      "epoch": 8.411214953271028,
+      "grad_norm": 0.20069944858551025,
+      "learning_rate": 1.1604135865326149e-05,
+      "loss": 0.051477575302124025,
+      "mean_token_accuracy": 0.9827573680877686,
+      "num_tokens": 11766536.0,
+      "step": 3600
+    },
+    {
+      "entropy": 0.08470481634140015,
+      "epoch": 8.52803738317757,
+      "grad_norm": 0.2061646282672882,
+      "learning_rate": 9.999173070131157e-06,
+      "loss": 0.050427241325378416,
+      "mean_token_accuracy": 0.9830707877874374,
+      "num_tokens": 11934812.0,
+      "step": 3650
+    },
+    {
+      "entropy": 0.08829616207629443,
+      "epoch": 8.644859813084112,
+      "grad_norm": 0.16281439363956451,
+      "learning_rate": 8.505942446499943e-06,
+      "loss": 0.05281091213226318,
+      "mean_token_accuracy": 0.9818410485982895,
+      "num_tokens": 12095307.0,
+      "step": 3700
+    },
+    {
+      "entropy": 0.08360566295683385,
+      "epoch": 8.761682242990654,
+      "grad_norm": 0.21016450226306915,
+      "learning_rate": 7.126926749641805e-06,
+      "loss": 0.050207719802856446,
+      "mean_token_accuracy": 0.9829736703634262,
+      "num_tokens": 12267401.0,
+      "step": 3750
+    },
+    {
+      "entropy": 0.08554164603352547,
+      "epoch": 8.878504672897197,
+      "grad_norm": 0.23642295598983765,
+      "learning_rate": 5.864418832617066e-06,
+      "loss": 0.05177981853485107,
+      "mean_token_accuracy": 0.9826503986120224,
+      "num_tokens": 12432027.0,
+      "step": 3800
+    },
+    {
+      "entropy": 0.0869401066750288,
+      "epoch": 8.995327102803738,
+      "grad_norm": 0.2289862483739853,
+      "learning_rate": 4.720517834070658e-06,
+      "loss": 0.05334438323974609,
+      "mean_token_accuracy": 0.9820096504688263,
+      "num_tokens": 12591339.0,
+      "step": 3850
+    },
+    {
+      "epoch": 9.0,
+      "eval_entropy": 0.3211280666775518,
+      "eval_loss": 1.2116189002990723,
+      "eval_mean_token_accuracy": 0.8066579533087743,
+      "eval_num_tokens": 12597030.0,
+      "eval_runtime": 45.6428,
+      "eval_samples_per_second": 26.97,
+      "eval_steps_per_second": 3.374,
+      "step": 3852
+    },
+    {
+      "entropy": 0.0807810365781188,
+      "epoch": 9.11214953271028,
+      "grad_norm": 0.1629796326160431,
+      "learning_rate": 3.69712568804957e-06,
+      "loss": 0.046660962104797366,
+      "mean_token_accuracy": 0.9844193959236145,
+      "num_tokens": 12752829.0,
+      "step": 3900
+    },
+    {
+      "entropy": 0.08310883663594723,
+      "epoch": 9.228971962616823,
+      "grad_norm": 0.13788935542106628,
+      "learning_rate": 2.7959439617072796e-06,
+      "loss": 0.04800426959991455,
+      "mean_token_accuracy": 0.9836695694923401,
+      "num_tokens": 12912121.0,
+      "step": 3950
+    },
+    {
+      "entropy": 0.07935288779437542,
+      "epoch": 9.345794392523365,
+      "grad_norm": 0.10886143893003464,
+      "learning_rate": 2.018471026152895e-06,
+      "loss": 0.045433063507080075,
+      "mean_token_accuracy": 0.9844985634088517,
+      "num_tokens": 13077510.0,
+      "step": 4000
+    },
+    {
+      "entropy": 0.07825511433184147,
+      "epoch": 9.462616822429906,
+      "grad_norm": 0.2171347290277481,
+      "learning_rate": 1.3659995651489109e-06,
+      "loss": 0.0459765625,
+      "mean_token_accuracy": 0.984357870221138,
+      "num_tokens": 13244654.0,
+      "step": 4050
+    },
+    {
+      "entropy": 0.07805611897259951,
+      "epoch": 9.57943925233645,
+      "grad_norm": 0.11776904761791229,
+      "learning_rate": 8.39614425800102e-07,
+      "loss": 0.04680560111999512,
+      "mean_token_accuracy": 0.9843836539983749,
+      "num_tokens": 13411362.0,
+      "step": 4100
+    },
+    {
+      "entropy": 0.0778104405477643,
+      "epoch": 9.69626168224299,
+      "grad_norm": 0.4998009204864502,
+      "learning_rate": 4.401908148067058e-07,
+      "loss": 0.046690058708190915,
+      "mean_token_accuracy": 0.984065158367157,
+      "num_tokens": 13577021.0,
+      "step": 4150
+    },
+    {
+      "entropy": 0.08028706476092339,
+      "epoch": 9.813084112149532,
+      "grad_norm": 0.14779487252235413,
+      "learning_rate": 1.6839284328140545e-07,
+      "loss": 0.04753034591674805,
+      "mean_token_accuracy": 0.9837410187721253,
+      "num_tokens": 13737792.0,
+      "step": 4200
+    },
+    {
+      "entropy": 0.08158599738031626,
+      "epoch": 9.929906542056075,
+      "grad_norm": 0.20872798562049866,
+      "learning_rate": 2.4672422549226043e-08,
+      "loss": 0.04804411888122559,
+      "mean_token_accuracy": 0.9834168201684952,
+      "num_tokens": 13896034.0,
+      "step": 4250
+    },
+    {
+      "epoch": 10.0,
+      "eval_entropy": 0.31092647405026796,
+      "eval_loss": 1.270560622215271,
+      "eval_mean_token_accuracy": 0.8052550457514726,
+      "eval_num_tokens": 13996700.0,
+      "eval_runtime": 45.6946,
+      "eval_samples_per_second": 26.94,
+      "eval_steps_per_second": 3.37,
+      "step": 4280
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.587551841502208e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-856/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-14B-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 0.19.1

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-856/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.030195310029781444,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-856/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-856/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test2/checkpoint-856/trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6439054441452026,
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.49546942114830017,
+      "learning_rate": 1.7676515353317202e-05,
+      "loss": 1.6080712890625,
+      "mean_token_accuracy": 0.6552277088165284,
+      "num_tokens": 162248.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8895833045244217,
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.6087712645530701,
+      "learning_rate": 3.571377591792659e-05,
+      "loss": 0.8471942138671875,
+      "mean_token_accuracy": 0.7710993754863739,
+      "num_tokens": 327614.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7270394039154052,
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.4936729371547699,
+      "learning_rate": 5.375103648253598e-05,
+      "loss": 0.6940426635742187,
+      "mean_token_accuracy": 0.7985459506511688,
+      "num_tokens": 494582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6873268783092499,
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.5290274620056152,
+      "learning_rate": 7.178829704714537e-05,
+      "loss": 0.6487248229980469,
+      "mean_token_accuracy": 0.8118354797363281,
+      "num_tokens": 653981.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6600921255350113,
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.3852632939815521,
+      "learning_rate": 8.982555761175476e-05,
+      "loss": 0.6241029357910156,
+      "mean_token_accuracy": 0.8171858608722686,
+      "num_tokens": 814840.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6286565268039703,
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.44116389751434326,
+      "learning_rate": 0.00010786281817636416,
+      "loss": 0.5951404190063476,
+      "mean_token_accuracy": 0.8241004174947739,
+      "num_tokens": 979542.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6199766182899475,
+      "epoch": 0.8177570093457944,
+      "grad_norm": 0.38574621081352234,
+      "learning_rate": 0.00012590007874097354,
+      "loss": 0.5904315948486328,
+      "mean_token_accuracy": 0.8250177747011185,
+      "num_tokens": 1147400.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5950348073244095,
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 0.0001439373393055829,
+      "loss": 0.5652639389038085,
+      "mean_token_accuracy": 0.83076107442379,
+      "num_tokens": 1310490.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7618740917026222,
+      "eval_loss": 0.6691045761108398,
+      "eval_mean_token_accuracy": 0.8110752314716191,
+      "eval_num_tokens": 1399670.0,
+      "eval_runtime": 45.674,
+      "eval_samples_per_second": 26.952,
+      "eval_steps_per_second": 3.372,
+      "step": 428
+    },
+    {
+      "entropy": 0.5888169056177139,
+      "epoch": 1.0514018691588785,
+      "grad_norm": 0.339750200510025,
+      "learning_rate": 0.00015438762800645052,
+      "loss": 0.5587311935424805,
+      "mean_token_accuracy": 0.832102472782135,
+      "num_tokens": 1471726.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5644756412506103,
+      "epoch": 1.1682242990654206,
+      "grad_norm": 0.32897934317588806,
+      "learning_rate": 0.00015426955859477223,
+      "loss": 0.5355723571777343,
+      "mean_token_accuracy": 0.8378035259246827,
+      "num_tokens": 1638060.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5603723293542862,
+      "epoch": 1.2850467289719627,
+      "grad_norm": 0.3474414646625519,
+      "learning_rate": 0.00015402334678635756,
+      "loss": 0.5328482437133789,
+      "mean_token_accuracy": 0.8384119784832,
+      "num_tokens": 1802005.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.551156692802906,
+      "epoch": 1.4018691588785046,
+      "grad_norm": 0.21533823013305664,
+      "learning_rate": 0.00015364940195109232,
+      "loss": 0.5259516525268555,
+      "mean_token_accuracy": 0.8401002615690232,
+      "num_tokens": 1969267.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5456148293614388,
+      "epoch": 1.5186915887850467,
+      "grad_norm": 0.3005809485912323,
+      "learning_rate": 0.0001531483458372002,
+      "loss": 0.5163665008544922,
+      "mean_token_accuracy": 0.8423654067516327,
+      "num_tokens": 2134793.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.540266016125679,
+      "epoch": 1.6355140186915889,
+      "grad_norm": 0.2895597815513611,
+      "learning_rate": 0.00015252101153747827,
+      "loss": 0.5159417343139648,
+      "mean_token_accuracy": 0.8422912752628327,
+      "num_tokens": 2300672.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5450576081871986,
+      "epoch": 1.7523364485981308,
+      "grad_norm": 0.26751118898391724,
+      "learning_rate": 0.00015176844210413562,
+      "loss": 0.5150370788574219,
+      "mean_token_accuracy": 0.8433581227064133,
+      "num_tokens": 2459315.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.540363709628582,
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.25945547223091125,
+      "learning_rate": 0.0001508918888145379,
+      "loss": 0.5133833312988281,
+      "mean_token_accuracy": 0.8442667639255523,
+      "num_tokens": 2616878.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5406239181756973,
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.2768362760543823,
+      "learning_rate": 0.0001498928090907414,
+      "loss": 0.5116788864135742,
+      "mean_token_accuracy": 0.8440770989656449,
+      "num_tokens": 2778909.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6602114913138476,
+      "eval_loss": 0.6344706416130066,
+      "eval_mean_token_accuracy": 0.8167721358212557,
+      "eval_num_tokens": 2799340.0,
+      "eval_runtime": 45.6608,
+      "eval_samples_per_second": 26.96,
+      "eval_steps_per_second": 3.373,
+      "step": 856
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4280,
+  "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": 5.1845739176448e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}