Upload fine-tuned model

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-787/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+- lora
+- transformers
+- 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 0.18.0

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-27b-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9480af55e1900f7cb7244842630cd1e1d6ea7fd8b697cffbbf4d5eb640048da8
+size 1864199752

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ 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 -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-787/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+- lora
+- transformers
+- 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 0.18.0

checkpoint-787/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-27b-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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-787/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9480af55e1900f7cb7244842630cd1e1d6ea7fd8b697cffbbf4d5eb640048da8
+size 1864199752

checkpoint-787/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-787/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ 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 -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-787/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a47f6f132d5d76b5e6eccb8a4ab5698e09df9451db7db7263fc1b938495103
+size 3633265423

checkpoint-787/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494d26b2241050a2d21f66a56111b5ddc2ead19c836c4fb7accf8d454e4f2a67
+size 14645

checkpoint-787/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65bb1658612d255fa63ff0d9aa774014957aae46f5ab30049c04338b4cd4dbc
+size 1465

checkpoint-787/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<end_of_turn>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-787/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4201e7b539fef153e1fe3058db39e600717b3323fee690d37e92fa52fb2b5af2
+size 33384667

checkpoint-787/tokenizer.model

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

checkpoint-787/trainer_state.json

@@ -0,0 +1,580 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 79,
+  "global_step": 787,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012706480304955527,
+      "grad_norm": 0.848995566368103,
+      "learning_rate": 9.885641677255401e-05,
+      "loss": 1.1502,
+      "step": 10
+    },
+    {
+      "epoch": 0.025412960609911054,
+      "grad_norm": 1.1054315567016602,
+      "learning_rate": 9.758576874205846e-05,
+      "loss": 1.0287,
+      "step": 20
+    },
+    {
+      "epoch": 0.03811944091486658,
+      "grad_norm": 1.046657681465149,
+      "learning_rate": 9.63151207115629e-05,
+      "loss": 1.0033,
+      "step": 30
+    },
+    {
+      "epoch": 0.05082592121982211,
+      "grad_norm": 0.6575726270675659,
+      "learning_rate": 9.504447268106735e-05,
+      "loss": 1.0074,
+      "step": 40
+    },
+    {
+      "epoch": 0.06353240152477764,
+      "grad_norm": 0.7760161757469177,
+      "learning_rate": 9.37738246505718e-05,
+      "loss": 1.014,
+      "step": 50
+    },
+    {
+      "epoch": 0.07623888182973317,
+      "grad_norm": 0.7718637585639954,
+      "learning_rate": 9.250317662007625e-05,
+      "loss": 0.9743,
+      "step": 60
+    },
+    {
+      "epoch": 0.08894536213468869,
+      "grad_norm": 0.8198321461677551,
+      "learning_rate": 9.123252858958069e-05,
+      "loss": 1.0196,
+      "step": 70
+    },
+    {
+      "epoch": 0.10165184243964422,
+      "grad_norm": 0.9116275906562805,
+      "learning_rate": 8.996188055908515e-05,
+      "loss": 1.0013,
+      "step": 80
+    },
+    {
+      "epoch": 0.11435832274459974,
+      "grad_norm": 0.7975141406059265,
+      "learning_rate": 8.869123252858959e-05,
+      "loss": 0.9896,
+      "step": 90
+    },
+    {
+      "epoch": 0.12706480304955528,
+      "grad_norm": 0.7764142751693726,
+      "learning_rate": 8.742058449809402e-05,
+      "loss": 0.9659,
+      "step": 100
+    },
+    {
+      "epoch": 0.1397712833545108,
+      "grad_norm": 0.8150487542152405,
+      "learning_rate": 8.614993646759849e-05,
+      "loss": 1.0126,
+      "step": 110
+    },
+    {
+      "epoch": 0.15247776365946633,
+      "grad_norm": 0.6777957081794739,
+      "learning_rate": 8.487928843710292e-05,
+      "loss": 0.941,
+      "step": 120
+    },
+    {
+      "epoch": 0.16518424396442186,
+      "grad_norm": 0.7709430456161499,
+      "learning_rate": 8.360864040660737e-05,
+      "loss": 0.9854,
+      "step": 130
+    },
+    {
+      "epoch": 0.17789072426937738,
+      "grad_norm": 0.7183663249015808,
+      "learning_rate": 8.233799237611182e-05,
+      "loss": 0.9852,
+      "step": 140
+    },
+    {
+      "epoch": 0.1905972045743329,
+      "grad_norm": 0.7055995464324951,
+      "learning_rate": 8.106734434561627e-05,
+      "loss": 0.9486,
+      "step": 150
+    },
+    {
+      "epoch": 0.20330368487928843,
+      "grad_norm": 0.7505035400390625,
+      "learning_rate": 7.979669631512071e-05,
+      "loss": 0.9578,
+      "step": 160
+    },
+    {
+      "epoch": 0.21601016518424396,
+      "grad_norm": 0.8225125074386597,
+      "learning_rate": 7.852604828462516e-05,
+      "loss": 0.9867,
+      "step": 170
+    },
+    {
+      "epoch": 0.22871664548919948,
+      "grad_norm": 0.7944441437721252,
+      "learning_rate": 7.725540025412961e-05,
+      "loss": 0.973,
+      "step": 180
+    },
+    {
+      "epoch": 0.241423125794155,
+      "grad_norm": 1.2351120710372925,
+      "learning_rate": 7.598475222363406e-05,
+      "loss": 0.9803,
+      "step": 190
+    },
+    {
+      "epoch": 0.25412960609911056,
+      "grad_norm": 1.021030306816101,
+      "learning_rate": 7.47141041931385e-05,
+      "loss": 0.9656,
+      "step": 200
+    },
+    {
+      "epoch": 0.2668360864040661,
+      "grad_norm": 0.8776686787605286,
+      "learning_rate": 7.344345616264296e-05,
+      "loss": 0.934,
+      "step": 210
+    },
+    {
+      "epoch": 0.2795425667090216,
+      "grad_norm": 0.6302770972251892,
+      "learning_rate": 7.21728081321474e-05,
+      "loss": 1.0046,
+      "step": 220
+    },
+    {
+      "epoch": 0.29224904701397714,
+      "grad_norm": 0.7298596501350403,
+      "learning_rate": 7.090216010165185e-05,
+      "loss": 0.9224,
+      "step": 230
+    },
+    {
+      "epoch": 0.30495552731893266,
+      "grad_norm": 0.7492867112159729,
+      "learning_rate": 6.96315120711563e-05,
+      "loss": 0.9309,
+      "step": 240
+    },
+    {
+      "epoch": 0.3176620076238882,
+      "grad_norm": 0.7107764482498169,
+      "learning_rate": 6.836086404066075e-05,
+      "loss": 0.9497,
+      "step": 250
+    },
+    {
+      "epoch": 0.3303684879288437,
+      "grad_norm": 0.7547566890716553,
+      "learning_rate": 6.709021601016518e-05,
+      "loss": 1.0039,
+      "step": 260
+    },
+    {
+      "epoch": 0.34307496823379924,
+      "grad_norm": 0.9105553030967712,
+      "learning_rate": 6.581956797966963e-05,
+      "loss": 0.9282,
+      "step": 270
+    },
+    {
+      "epoch": 0.35578144853875476,
+      "grad_norm": 0.6816727519035339,
+      "learning_rate": 6.454891994917408e-05,
+      "loss": 0.9327,
+      "step": 280
+    },
+    {
+      "epoch": 0.3684879288437103,
+      "grad_norm": 0.6747182011604309,
+      "learning_rate": 6.327827191867853e-05,
+      "loss": 0.942,
+      "step": 290
+    },
+    {
+      "epoch": 0.3811944091486658,
+      "grad_norm": 0.7727833986282349,
+      "learning_rate": 6.200762388818297e-05,
+      "loss": 0.9206,
+      "step": 300
+    },
+    {
+      "epoch": 0.39390088945362134,
+      "grad_norm": 0.7521071434020996,
+      "learning_rate": 6.0736975857687425e-05,
+      "loss": 0.9142,
+      "step": 310
+    },
+    {
+      "epoch": 0.40660736975857686,
+      "grad_norm": 0.9628099203109741,
+      "learning_rate": 5.946632782719187e-05,
+      "loss": 0.9793,
+      "step": 320
+    },
+    {
+      "epoch": 0.4193138500635324,
+      "grad_norm": 0.7120410799980164,
+      "learning_rate": 5.8195679796696325e-05,
+      "loss": 0.9851,
+      "step": 330
+    },
+    {
+      "epoch": 0.4320203303684879,
+      "grad_norm": 1.139363408088684,
+      "learning_rate": 5.692503176620076e-05,
+      "loss": 0.9344,
+      "step": 340
+    },
+    {
+      "epoch": 0.44472681067344344,
+      "grad_norm": 1.1447031497955322,
+      "learning_rate": 5.565438373570522e-05,
+      "loss": 0.9223,
+      "step": 350
+    },
+    {
+      "epoch": 0.45743329097839897,
+      "grad_norm": 1.0371094942092896,
+      "learning_rate": 5.438373570520966e-05,
+      "loss": 0.9141,
+      "step": 360
+    },
+    {
+      "epoch": 0.4701397712833545,
+      "grad_norm": 0.7418134808540344,
+      "learning_rate": 5.31130876747141e-05,
+      "loss": 0.9442,
+      "step": 370
+    },
+    {
+      "epoch": 0.48284625158831,
+      "grad_norm": 0.9420067667961121,
+      "learning_rate": 5.1842439644218555e-05,
+      "loss": 0.9636,
+      "step": 380
+    },
+    {
+      "epoch": 0.49555273189326554,
+      "grad_norm": 0.9453240036964417,
+      "learning_rate": 5.0571791613723e-05,
+      "loss": 0.9552,
+      "step": 390
+    },
+    {
+      "epoch": 0.5082592121982211,
+      "grad_norm": 0.7951337695121765,
+      "learning_rate": 4.930114358322745e-05,
+      "loss": 0.9711,
+      "step": 400
+    },
+    {
+      "epoch": 0.5209656925031766,
+      "grad_norm": 0.6897045373916626,
+      "learning_rate": 4.80304955527319e-05,
+      "loss": 0.9245,
+      "step": 410
+    },
+    {
+      "epoch": 0.5336721728081322,
+      "grad_norm": 0.6777597665786743,
+      "learning_rate": 4.675984752223634e-05,
+      "loss": 0.9235,
+      "step": 420
+    },
+    {
+      "epoch": 0.5463786531130876,
+      "grad_norm": 0.7018824219703674,
+      "learning_rate": 4.548919949174079e-05,
+      "loss": 0.9477,
+      "step": 430
+    },
+    {
+      "epoch": 0.5590851334180432,
+      "grad_norm": 0.89564448595047,
+      "learning_rate": 4.421855146124524e-05,
+      "loss": 0.9886,
+      "step": 440
+    },
+    {
+      "epoch": 0.5717916137229987,
+      "grad_norm": 0.8132324814796448,
+      "learning_rate": 4.2947903430749685e-05,
+      "loss": 0.9218,
+      "step": 450
+    },
+    {
+      "epoch": 0.5844980940279543,
+      "grad_norm": 0.6581067442893982,
+      "learning_rate": 4.1677255400254135e-05,
+      "loss": 0.9258,
+      "step": 460
+    },
+    {
+      "epoch": 0.5972045743329097,
+      "grad_norm": 0.6890019178390503,
+      "learning_rate": 4.040660736975858e-05,
+      "loss": 0.9089,
+      "step": 470
+    },
+    {
+      "epoch": 0.6099110546378653,
+      "grad_norm": 0.6885469555854797,
+      "learning_rate": 3.913595933926303e-05,
+      "loss": 0.9275,
+      "step": 480
+    },
+    {
+      "epoch": 0.6226175349428208,
+      "grad_norm": 0.8638964891433716,
+      "learning_rate": 3.786531130876747e-05,
+      "loss": 0.9144,
+      "step": 490
+    },
+    {
+      "epoch": 0.6353240152477764,
+      "grad_norm": 0.6101030111312866,
+      "learning_rate": 3.6594663278271915e-05,
+      "loss": 0.8805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6480304955527318,
+      "grad_norm": 0.8916230797767639,
+      "learning_rate": 3.5324015247776365e-05,
+      "loss": 0.9581,
+      "step": 510
+    },
+    {
+      "epoch": 0.6607369758576874,
+      "grad_norm": 0.7225152850151062,
+      "learning_rate": 3.4053367217280815e-05,
+      "loss": 0.8845,
+      "step": 520
+    },
+    {
+      "epoch": 0.6734434561626429,
+      "grad_norm": 0.7077111601829529,
+      "learning_rate": 3.278271918678526e-05,
+      "loss": 0.9542,
+      "step": 530
+    },
+    {
+      "epoch": 0.6861499364675985,
+      "grad_norm": 1.0143916606903076,
+      "learning_rate": 3.151207115628971e-05,
+      "loss": 0.9167,
+      "step": 540
+    },
+    {
+      "epoch": 0.6988564167725541,
+      "grad_norm": 0.8362636566162109,
+      "learning_rate": 3.0241423125794155e-05,
+      "loss": 0.9597,
+      "step": 550
+    },
+    {
+      "epoch": 0.7115628970775095,
+      "grad_norm": 0.8249373435974121,
+      "learning_rate": 2.89707750952986e-05,
+      "loss": 0.9256,
+      "step": 560
+    },
+    {
+      "epoch": 0.7242693773824651,
+      "grad_norm": 0.8465105295181274,
+      "learning_rate": 2.7700127064803048e-05,
+      "loss": 0.8829,
+      "step": 570
+    },
+    {
+      "epoch": 0.7369758576874206,
+      "grad_norm": 0.6343558430671692,
+      "learning_rate": 2.6429479034307498e-05,
+      "loss": 0.9246,
+      "step": 580
+    },
+    {
+      "epoch": 0.7496823379923762,
+      "grad_norm": 0.8166621923446655,
+      "learning_rate": 2.5158831003811945e-05,
+      "loss": 0.8614,
+      "step": 590
+    },
+    {
+      "epoch": 0.7623888182973316,
+      "grad_norm": 0.9396957755088806,
+      "learning_rate": 2.388818297331639e-05,
+      "loss": 0.9222,
+      "step": 600
+    },
+    {
+      "epoch": 0.7750952986022872,
+      "grad_norm": 0.7295355200767517,
+      "learning_rate": 2.2617534942820838e-05,
+      "loss": 0.8723,
+      "step": 610
+    },
+    {
+      "epoch": 0.7878017789072427,
+      "grad_norm": 0.7101081013679504,
+      "learning_rate": 2.1346886912325288e-05,
+      "loss": 0.9214,
+      "step": 620
+    },
+    {
+      "epoch": 0.8005082592121983,
+      "grad_norm": 0.6851767301559448,
+      "learning_rate": 2.0076238881829735e-05,
+      "loss": 0.9274,
+      "step": 630
+    },
+    {
+      "epoch": 0.8132147395171537,
+      "grad_norm": 0.6204417943954468,
+      "learning_rate": 1.880559085133418e-05,
+      "loss": 0.9117,
+      "step": 640
+    },
+    {
+      "epoch": 0.8259212198221093,
+      "grad_norm": 0.7562251687049866,
+      "learning_rate": 1.7534942820838628e-05,
+      "loss": 0.9185,
+      "step": 650
+    },
+    {
+      "epoch": 0.8386277001270648,
+      "grad_norm": 0.6018821597099304,
+      "learning_rate": 1.6264294790343075e-05,
+      "loss": 0.9104,
+      "step": 660
+    },
+    {
+      "epoch": 0.8513341804320204,
+      "grad_norm": 0.6004038453102112,
+      "learning_rate": 1.4993646759847523e-05,
+      "loss": 0.9407,
+      "step": 670
+    },
+    {
+      "epoch": 0.8640406607369758,
+      "grad_norm": 0.7767984867095947,
+      "learning_rate": 1.3722998729351972e-05,
+      "loss": 0.9076,
+      "step": 680
+    },
+    {
+      "epoch": 0.8767471410419314,
+      "grad_norm": 0.7464905381202698,
+      "learning_rate": 1.2452350698856418e-05,
+      "loss": 0.933,
+      "step": 690
+    },
+    {
+      "epoch": 0.8894536213468869,
+      "grad_norm": 0.6998640298843384,
+      "learning_rate": 1.1181702668360865e-05,
+      "loss": 0.8978,
+      "step": 700
+    },
+    {
+      "epoch": 0.9021601016518425,
+      "grad_norm": 0.6426926851272583,
+      "learning_rate": 9.911054637865311e-06,
+      "loss": 0.8825,
+      "step": 710
+    },
+    {
+      "epoch": 0.9148665819567979,
+      "grad_norm": 0.8413234949111938,
+      "learning_rate": 8.64040660736976e-06,
+      "loss": 0.9092,
+      "step": 720
+    },
+    {
+      "epoch": 0.9275730622617535,
+      "grad_norm": 0.9436001777648926,
+      "learning_rate": 7.3697585768742056e-06,
+      "loss": 0.9276,
+      "step": 730
+    },
+    {
+      "epoch": 0.940279542566709,
+      "grad_norm": 0.9838041663169861,
+      "learning_rate": 6.099110546378654e-06,
+      "loss": 0.9369,
+      "step": 740
+    },
+    {
+      "epoch": 0.9529860228716646,
+      "grad_norm": 0.9448868632316589,
+      "learning_rate": 4.8284625158831006e-06,
+      "loss": 0.9413,
+      "step": 750
+    },
+    {
+      "epoch": 0.96569250317662,
+      "grad_norm": 0.688701868057251,
+      "learning_rate": 3.5578144853875476e-06,
+      "loss": 0.9057,
+      "step": 760
+    },
+    {
+      "epoch": 0.9783989834815756,
+      "grad_norm": 0.6457446813583374,
+      "learning_rate": 2.2871664548919947e-06,
+      "loss": 0.8772,
+      "step": 770
+    },
+    {
+      "epoch": 0.9911054637865311,
+      "grad_norm": 0.804164707660675,
+      "learning_rate": 1.0165184243964422e-06,
+      "loss": 0.9192,
+      "step": 780
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 787,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 4.558598799031388e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-787/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561ec1ba3dee40722863237d85d6d02f0b5ed264d5129d507b0229d209d3af00
+size 5905

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<end_of_turn>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4201e7b539fef153e1fe3058db39e600717b3323fee690d37e92fa52fb2b5af2
+size 33384667

tokenizer.model

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

train_config.json

@@ -0,0 +1,164 @@
+{
+    "output_dir": "outputs/finetunes/gemma3_27b_neutral_boost_5k_docs/2026-01-07_07-47-09",
+    "overwrite_output_dir": false,
+    "do_train": false,
+    "do_eval": false,
+    "do_predict": false,
+    "eval_strategy": "no",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": "main",
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 1,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "torch_empty_cache_steps": null,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.0,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 1,
+    "max_steps": -1,
+    "lr_scheduler_type": "linear",
+    "lr_scheduler_kwargs": {},
+    "warmup_ratio": 0.0,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "outputs/finetunes/gemma3_27b_neutral_boost_5k_docs/2026-01-07_07-47-09/logs",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 10,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "epoch",
+    "save_steps": null,
+    "save_total_limit": null,
+    "save_safetensors": true,
+    "save_on_each_node": false,
+    "save_only_model": false,
+    "restore_callback_states_from_checkpoint": false,
+    "no_cuda": false,
+    "use_cpu": false,
+    "use_mps_device": false,
+    "seed": 42,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": true,
+    "local_rank": 0,
+    "ddp_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 0.1,
+    "dataloader_num_workers": 2,
+    "dataloader_prefetch_factor": null,
+    "past_index": -1,
+    "run_name": null,
+    "disable_tqdm": false,
+    "remove_unused_columns": false,
+    "label_names": null,
+    "load_best_model_at_end": false,
+    "metric_for_best_model": null,
+    "greater_is_better": null,
+    "ignore_data_skip": false,
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+        "min_num_params": 0,
+        "xla": false,
+        "xla_fsdp_v2": false,
+        "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "accelerator_config": {
+        "split_batches": false,
+        "dispatch_batches": null,
+        "even_batches": true,
+        "use_seedable_sampler": true,
+        "non_blocking": false,
+        "gradient_accumulation_kwargs": null
+    },
+    "parallelism_config": null,
+    "deepspeed": null,
+    "label_smoothing_factor": 0.0,
+    "optim": "adamw_torch",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+        "wandb"
+    ],
+    "project": "huggingface",
+    "trackio_space_id": "trackio",
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "ddp_broadcast_buffers": null,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": false,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": "<HUB_TOKEN>",
+    "hub_private_repo": null,
+    "hub_always_push": false,
+    "hub_revision": null,
+    "gradient_checkpointing": true,
+    "gradient_checkpointing_kwargs": null,
+    "include_inputs_for_metrics": false,
+    "include_for_metrics": [],
+    "eval_do_concat_batches": true,
+    "fp16_backend": "auto",
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": false,
+    "torch_compile_backend": null,
+    "torch_compile_mode": null,
+    "include_tokens_per_second": false,
+    "include_num_input_tokens_seen": "no",
+    "neftune_noise_alpha": null,
+    "optim_target_modules": null,
+    "batch_eval_metrics": false,
+    "eval_on_start": false,
+    "use_liger_kernel": false,
+    "liger_kernel_config": null,
+    "eval_use_gather_object": false,
+    "average_tokens_across_devices": true,
+    "lora_r": 64,
+    "lora_alpha": 128,
+    "lora_dropout": 0.05,
+    "lora_bias": "none",
+    "lora_task_type": "CAUSAL_LM",
+    "lora_target_modules": [
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "o_proj",
+        "down_proj",
+        "up_proj",
+        "gate_proj"
+    ],
+    "num_train_points": 5000,
+    "unsloth": true
+}