Upload folder using huggingface_hub

.gitattributes

@@ -38,3 +38,6 @@ teacher/checkpoints/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs
 teacher/checkpoints/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 teacher/gguf/gemma-4-e2b-it.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
 teacher/gguf/gemma-4-e2b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+student/checkpoints/checkpoint-468/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

student/adapters/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

student/adapters/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-270m-it-unsloth-bnb-4bit",
+  "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": 0.0,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_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
+}

student/adapters/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1802edb2c96dd579138078fbd9b7aba0019debc2b582a173784942567449e6e
+size 30409120

student/adapters/chat_template.jinja

@@ -0,0 +1,50 @@
+{# Unsloth Chat template fixes #}
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif message['content'] is defined -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
+
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

student/adapters/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

student/adapters/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

student/checkpoints/README.md

@@ -0,0 +1,59 @@
+---
+base_model: unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+library_name: transformers
+model_name: checkpoints
+tags:
+- generated_from_trainer
+- unsloth
+- trl
+- sft
+licence: license
+---
+
+# Model Card for checkpoints
+
+This model is a fine-tuned version of [unsloth/gemma-3-270m-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-270m-it-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

student/checkpoints/checkpoint-468/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

student/checkpoints/checkpoint-468/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-270m-it-unsloth-bnb-4bit",
+  "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": 0.0,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_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
+}

student/checkpoints/checkpoint-468/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1802edb2c96dd579138078fbd9b7aba0019debc2b582a173784942567449e6e
+size 30409120

student/checkpoints/checkpoint-468/chat_template.jinja

@@ -0,0 +1,50 @@
+{# Unsloth Chat template fixes #}
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif message['content'] is defined -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
+
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

student/checkpoints/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06808aa950c8d95b90808b2db236244a823bca3ecb2788175a1f13872394f263
+size 15723605

student/checkpoints/checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
+size 14645

student/checkpoints/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6776b28d1a96868895a26dbac165d16e33f240a70bccc5ada04b04c46211ab
+size 1465

student/checkpoints/checkpoint-468/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

student/checkpoints/checkpoint-468/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

student/checkpoints/checkpoint-468/trainer_state.json

@@ -0,0 +1,436 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 50,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042735042735042736,
+      "grad_norm": 5.1462321281433105,
+      "learning_rate": 0.00012,
+      "loss": 3.7814403533935548,
+      "step": 10
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 2.398408889770508,
+      "learning_rate": 0.00019996152616500243,
+      "loss": 1.2102224349975585,
+      "step": 20
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.2968085706233978,
+      "learning_rate": 0.00019952903544104026,
+      "loss": 0.1868561863899231,
+      "step": 30
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 0.16443780064582825,
+      "learning_rate": 0.00019861804788521493,
+      "loss": 0.12124946117401122,
+      "step": 40
+    },
+    {
+      "epoch": 0.21367521367521367,
+      "grad_norm": 0.16144566237926483,
+      "learning_rate": 0.00019723294317082878,
+      "loss": 0.09948906898498536,
+      "step": 50
+    },
+    {
+      "epoch": 0.21367521367521367,
+      "eval_loss": 0.12183893471956253,
+      "eval_runtime": 26.9603,
+      "eval_samples_per_second": 11.127,
+      "eval_steps_per_second": 1.409,
+      "step": 50
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 0.17814505100250244,
+      "learning_rate": 0.00019538038034179497,
+      "loss": 0.08351721763610839,
+      "step": 60
+    },
+    {
+      "epoch": 0.29914529914529914,
+      "grad_norm": 0.1021871343255043,
+      "learning_rate": 0.00019306926579854821,
+      "loss": 0.07892879843711853,
+      "step": 70
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.12059585750102997,
+      "learning_rate": 0.00019031071047954093,
+      "loss": 0.07642545700073242,
+      "step": 80
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.11213107407093048,
+      "learning_rate": 0.0001871179764441794,
+      "loss": 0.07258535027503968,
+      "step": 90
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 0.12126409262418747,
+      "learning_rate": 0.00018350641311400812,
+      "loss": 0.07051915526390076,
+      "step": 100
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "eval_loss": 0.1036950945854187,
+      "eval_runtime": 8.8693,
+      "eval_samples_per_second": 33.825,
+      "eval_steps_per_second": 4.284,
+      "step": 100
+    },
+    {
+      "epoch": 0.4700854700854701,
+      "grad_norm": 0.10296919196844101,
+      "learning_rate": 0.00017949338347867023,
+      "loss": 0.0704876184463501,
+      "step": 110
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.08268409967422485,
+      "learning_rate": 0.00017509818062141702,
+      "loss": 0.06836398839950561,
+      "step": 120
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.11069895327091217,
+      "learning_rate": 0.00017034193496547902,
+      "loss": 0.06567966938018799,
+      "step": 130
+    },
+    {
+      "epoch": 0.5982905982905983,
+      "grad_norm": 0.10991781204938889,
+      "learning_rate": 0.00016524751268722217,
+      "loss": 0.06776190400123597,
+      "step": 140
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 0.10355155169963837,
+      "learning_rate": 0.0001598394057844792,
+      "loss": 0.06601473093032836,
+      "step": 150
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "eval_loss": 0.09585529565811157,
+      "eval_runtime": 9.004,
+      "eval_samples_per_second": 33.319,
+      "eval_steps_per_second": 4.22,
+      "step": 150
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.09497381001710892,
+      "learning_rate": 0.00015414361432856475,
+      "loss": 0.06537729501724243,
+      "step": 160
+    },
+    {
+      "epoch": 0.7264957264957265,
+      "grad_norm": 0.09310545772314072,
+      "learning_rate": 0.0001481875214660604,
+      "loss": 0.0644693911075592,
+      "step": 170
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.10611022263765335,
+      "learning_rate": 0.00014199976177131283,
+      "loss": 0.0641900658607483,
+      "step": 180
+    },
+    {
+      "epoch": 0.811965811965812,
+      "grad_norm": 0.11665572971105576,
+      "learning_rate": 0.00013561008358255468,
+      "loss": 0.06345350742340088,
+      "step": 190
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.08741547912359238,
+      "learning_rate": 0.00012904920598348253,
+      "loss": 0.06299755573272706,
+      "step": 200
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "eval_loss": 0.09929452836513519,
+      "eval_runtime": 8.7583,
+      "eval_samples_per_second": 34.253,
+      "eval_steps_per_second": 4.339,
+      "step": 200
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 0.10623424500226974,
+      "learning_rate": 0.00012234867111786851,
+      "loss": 0.061084133386611936,
+      "step": 210
+    },
+    {
+      "epoch": 0.9401709401709402,
+      "grad_norm": 0.11632129549980164,
+      "learning_rate": 0.00011554069254722051,
+      "loss": 0.06272282004356385,
+      "step": 220
+    },
+    {
+      "epoch": 0.9829059829059829,
+      "grad_norm": 0.10279455780982971,
+      "learning_rate": 0.00010865800038052631,
+      "loss": 0.062236905097961426,
+      "step": 230
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.10554131865501404,
+      "learning_rate": 0.00010173368392063978,
+      "loss": 0.059556889533996585,
+      "step": 240
+    },
+    {
+      "epoch": 1.0683760683760684,
+      "grad_norm": 0.09244892746210098,
+      "learning_rate": 9.480103258380198e-05,
+      "loss": 0.060315436124801634,
+      "step": 250
+    },
+    {
+      "epoch": 1.0683760683760684,
+      "eval_loss": 0.09908141940832138,
+      "eval_runtime": 8.9464,
+      "eval_samples_per_second": 33.533,
+      "eval_steps_per_second": 4.248,
+      "step": 250
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.0986277163028717,
+      "learning_rate": 8.789337585709564e-05,
+      "loss": 0.06082844138145447,
+      "step": 260
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.11766652762889862,
+      "learning_rate": 8.104392306325442e-05,
+      "loss": 0.059259837865829466,
+      "step": 270
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.11862441897392273,
+      "learning_rate": 7.428560370317542e-05,
+      "loss": 0.05957560539245606,
+      "step": 280
+    },
+    {
+      "epoch": 1.2393162393162394,
+      "grad_norm": 0.08285031467676163,
+      "learning_rate": 6.765090914370642e-05,
+      "loss": 0.058845126628875734,
+      "step": 290
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.09318173676729202,
+      "learning_rate": 6.117173641181064e-05,
+      "loss": 0.05915853977203369,
+      "step": 300
+    },
+    {
+      "epoch": 1.282051282051282,
+      "eval_loss": 0.09837502986192703,
+      "eval_runtime": 8.872,
+      "eval_samples_per_second": 33.814,
+      "eval_steps_per_second": 4.283,
+      "step": 300
+    },
+    {
+      "epoch": 1.3247863247863247,
+      "grad_norm": 0.10940144956111908,
+      "learning_rate": 5.487923484608629e-05,
+      "loss": 0.058187621831893924,
+      "step": 310
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.09581263363361359,
+      "learning_rate": 4.8803656342880477e-05,
+      "loss": 0.05839874148368836,
+      "step": 320
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 0.10020607709884644,
+      "learning_rate": 4.2974209916955975e-05,
+      "loss": 0.058370137214660646,
+      "step": 330
+    },
+    {
+      "epoch": 1.452991452991453,
+      "grad_norm": 0.11031775176525116,
+      "learning_rate": 3.741892127592625e-05,
+      "loss": 0.05713057518005371,
+      "step": 340
+    },
+    {
+      "epoch": 1.4957264957264957,
+      "grad_norm": 0.08814098685979843,
+      "learning_rate": 3.216449808357039e-05,
+      "loss": 0.05719304084777832,
+      "step": 350
+    },
+    {
+      "epoch": 1.4957264957264957,
+      "eval_loss": 0.10020233690738678,
+      "eval_runtime": 8.7729,
+      "eval_samples_per_second": 34.196,
+      "eval_steps_per_second": 4.332,
+      "step": 350
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.10264591127634048,
+      "learning_rate": 2.7236201559789453e-05,
+      "loss": 0.058714425563812254,
+      "step": 360
+    },
+    {
+      "epoch": 1.5811965811965814,
+      "grad_norm": 0.0889529213309288,
+      "learning_rate": 2.265772503450122e-05,
+      "loss": 0.05743030309677124,
+      "step": 370
+    },
+    {
+      "epoch": 1.623931623931624,
+      "grad_norm": 0.09476124495267868,
+      "learning_rate": 1.845108003933972e-05,
+      "loss": 0.0570054829120636,
+      "step": 380
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.10928480327129364,
+      "learning_rate": 1.4636490484785315e-05,
+      "loss": 0.05795256495475769,
+      "step": 390
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.10125123709440231,
+      "learning_rate": 1.1232295431481222e-05,
+      "loss": 0.05714542269706726,
+      "step": 400
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": 0.09949486702680588,
+      "eval_runtime": 8.8495,
+      "eval_samples_per_second": 33.9,
+      "eval_steps_per_second": 4.294,
+      "step": 400
+    },
+    {
+      "epoch": 1.7521367521367521,
+      "grad_norm": 0.0886467695236206,
+      "learning_rate": 8.254860923173691e-06,
+      "loss": 0.057120949029922485,
+      "step": 410
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.0856015682220459,
+      "learning_rate": 5.7185013051488935e-06,
+      "loss": 0.057786566019058225,
+      "step": 420
+    },
+    {
+      "epoch": 1.8376068376068377,
+      "grad_norm": 0.08765718340873718,
+      "learning_rate": 3.6354104064368566e-06,
+      "loss": 0.05581741333007813,
+      "step": 430
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.0899822786450386,
+      "learning_rate": 2.0156029166314315e-06,
+      "loss": 0.05644698739051819,
+      "step": 440
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.08607936650514603,
+      "learning_rate": 8.668662391638437e-07,
+      "loss": 0.05725433826446533,
+      "step": 450
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "eval_loss": 0.0995166152715683,
+      "eval_runtime": 8.731,
+      "eval_samples_per_second": 34.361,
+      "eval_steps_per_second": 4.352,
+      "step": 450
+    },
+    {
+      "epoch": 1.965811965811966,
+      "grad_norm": 0.0872127115726471,
+      "learning_rate": 1.947230525005006e-07,
+      "loss": 0.057979744672775266,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.09953737258911133,
+      "eval_runtime": 8.6918,
+      "eval_samples_per_second": 34.515,
+      "eval_steps_per_second": 4.372,
+      "step": 468
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 468,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 2.249171339328e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

student/checkpoints/checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36df130ad9865c271a2ed9059cad1fe98363eb4da0cfbbc1434a0448143136e0
+size 5649

student/gguf/gemma-3-270m-it.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f9d8254489ac2b668ffb44e923da9b8a8b6452fd199dfded449a4bc4483fe4
+size 253114752