Upload full training folder with all checkpoints

.gitattributes

@@ -33,3 +33,10 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,175 @@
+---
+language:
+- vi
+- en
+license: apache-2.0
+tags:
+- llm-judge
+- training-checkpoint
+- lora
+- unsloth
+---
+
+# finetuned_5_12
+
+Full training folder backup - Toàn bộ checkpoints và models.
+
+## 📂 Cấu trúc Folder
+```
+train_
+├── lora_adapters/           # LoRA adapters
+├── README.md
+├── zero_shot_metrics.json
+└── zero_shot_results.csv
+```
+
+## 🚀 Sử Dụng
+
+### 1️⃣ Clone Repo
+```bash
+git lfs install
+git clone https://huggingface.co/ImNotTam/finetuned_5_12
+cd finetuned_5_12
+```
+
+### 2️⃣ Load LoRA Adapters (Nhẹ nhất - khuyến nghị)
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="ImNotTam/finetuned_5_12",
+    subfolder="lora_adapters",
+    max_seq_length=2048,
+    dtype=None,
+    load_in_4bit=True,
+)
+
+# Enable inference mode
+FastLanguageModel.for_inference(model)
+
+# Test
+prompt = "Đánh giá response này..."
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### 3️⃣ Load Final Model
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "ImNotTam/finetuned_5_12",
+    subfolder="final_model",
+    device_map="auto",
+    torch_dtype="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("ImNotTam/finetuned_5_12", subfolder="final_model")
+
+# Inference
+inputs = tokenizer("Your prompt", return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0]))
+```
+
+### 4️⃣ Resume Training từ Checkpoint
+```python
+from transformers import Trainer, TrainingArguments
+
+# Load checkpoint muốn resume
+model = AutoModelForCausalLM.from_pretrained(
+    "ImNotTam/finetuned_5_12",
+    subfolder="checkpoint-210",  # Chọn checkpoint
+    device_map="auto"
+)
+
+# Continue training
+trainer = Trainer(
+    model=model,
+    args=TrainingArguments(
+        output_dir="./continue_training",
+        # ... your training args
+    ),
+)
+trainer.train(resume_from_checkpoint=True)
+```
+
+### 5️⃣ Fine-tune Tiếp từ LoRA Adapter
+```python
+from unsloth import FastLanguageModel
+from trl import SFTTrainer
+
+# Load LoRA adapter
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="ImNotTam/finetuned_5_12",
+    subfolder="lora_adapters",
+    max_seq_length=2048,
+    dtype=None,
+    load_in_4bit=True,
+)
+
+# Add LoRA config để train tiếp
+model = FastLanguageModel.get_peft_model(
+    model,
+    r=16,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
+                    "gate_proj", "up_proj", "down_proj"],
+    lora_alpha=16,
+    lora_dropout=0,
+    bias="none",
+    use_gradient_checkpointing="unsloth",
+)
+
+# Train với data mới
+trainer = SFTTrainer(
+    model=model,
+    tokenizer=tokenizer,
+    train_dataset=your_new_dataset,
+    # ... training args
+)
+trainer.train()
+```
+
+### 6️⃣ Xem Metrics và Results
+```python
+import json
+import pandas as pd
+
+# Load metrics
+with open("zero_shot_metrics.json", "r") as f:
+    metrics = json.load(f)
+print("📊 Metrics:", metrics)
+
+# Load results
+results = pd.read_csv("zero_shot_results.csv")
+print("\n📈 Results:")
+print(results.head())
+```
+
+## 📋 Nội Dung Repo
+
+| Folder/File | Mô tả | Kích thước |
+|-------------|-------|------------|
+| `lora_adapters/` | LoRA adapters (nhẹ) | ~50-100 MB |
+| `final_model/` | Model merged đầy đủ | ~4-8 GB |
+| `checkpoint-150/` | Training checkpoint | ~4-8 GB |
+| `checkpoint-200/` | Training checkpoint | ~4-8 GB |
+| `checkpoint-210/` | Training checkpoint | ~4-8 GB |
+| `zero_shot_metrics.json` | Evaluation metrics | <1 MB |
+| `zero_shot_results.csv` | Detailed results | <1 MB |
+
+## 💡 Khuyến Nghị
+
+- **Inference nhanh:** Dùng `lora_adapters/`
+- **Production:** Dùng `final_model/`
+- **Train tiếp:** Load `lora_adapters/` + add LoRA config
+- **Resume training:** Load checkpoint cụ thể
+
+## 📦 Requirements
+```bash
+pip install unsloth transformers torch trl
+```
+
+## 📄 License
+
+Apache 2.0

checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/medgemma-4b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/medgemma-4b-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 0.18.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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/medgemma-4b-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": 32,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc7bd0421bfecda36bc2c99741021234818a6b748ab603299bb10dc4e1c3b59
+size 308107928

checkpoint-100/added_tokens.json

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

checkpoint-100/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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f69b25edf94625e7a02518340fe0937560ac04c53aeacd05ae95862ce9c31f1
+size 157331237

checkpoint-100/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoint-100/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c69974dd186962af147b132c93b5d1654090809d2863f2058c297e9b8e2e7a
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a239e685911b4054a1347865565f4a73e42ee9453644b8ff353920e9e7c499
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
+size 33384822

checkpoint-100/tokenizer.model

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

checkpoint-100/trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.01389834564179182,
+  "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-100",
+  "epoch": 0.38910505836575876,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019455252918287938,
+      "grad_norm": 3.0237326622009277,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.8809,
+      "step": 5
+    },
+    {
+      "epoch": 0.038910505836575876,
+      "grad_norm": 2.4512810707092285,
+      "learning_rate": 4e-06,
+      "loss": 0.8569,
+      "step": 10
+    },
+    {
+      "epoch": 0.058365758754863814,
+      "grad_norm": 1.5967055559158325,
+      "learning_rate": 6.222222222222222e-06,
+      "loss": 0.7725,
+      "step": 15
+    },
+    {
+      "epoch": 0.07782101167315175,
+      "grad_norm": 1.2497001886367798,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.6516,
+      "step": 20
+    },
+    {
+      "epoch": 0.09727626459143969,
+      "grad_norm": 1.2455090284347534,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.5238,
+      "step": 25
+    },
+    {
+      "epoch": 0.11673151750972763,
+      "grad_norm": 1.361525535583496,
+      "learning_rate": 1.2888888888888889e-05,
+      "loss": 0.3777,
+      "step": 30
+    },
+    {
+      "epoch": 0.13618677042801555,
+      "grad_norm": 1.6556775569915771,
+      "learning_rate": 1.511111111111111e-05,
+      "loss": 0.2116,
+      "step": 35
+    },
+    {
+      "epoch": 0.1556420233463035,
+      "grad_norm": 0.6078555583953857,
+      "learning_rate": 1.7333333333333332e-05,
+      "loss": 0.0794,
+      "step": 40
+    },
+    {
+      "epoch": 0.17509727626459143,
+      "grad_norm": 0.31556975841522217,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.0343,
+      "step": 45
+    },
+    {
+      "epoch": 0.19455252918287938,
+      "grad_norm": 0.23063282668590546,
+      "learning_rate": 2.177777777777778e-05,
+      "loss": 0.0227,
+      "step": 50
+    },
+    {
+      "epoch": 0.2140077821011673,
+      "grad_norm": 0.10897089540958405,
+      "learning_rate": 2.4e-05,
+      "loss": 0.0159,
+      "step": 55
+    },
+    {
+      "epoch": 0.23346303501945526,
+      "grad_norm": 0.08667729049921036,
+      "learning_rate": 2.6222222222222226e-05,
+      "loss": 0.0155,
+      "step": 60
+    },
+    {
+      "epoch": 0.2529182879377432,
+      "grad_norm": 0.07056345790624619,
+      "learning_rate": 2.8444444444444447e-05,
+      "loss": 0.0133,
+      "step": 65
+    },
+    {
+      "epoch": 0.2723735408560311,
+      "grad_norm": 0.119380883872509,
+      "learning_rate": 3.066666666666666e-05,
+      "loss": 0.0113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2918287937743191,
+      "grad_norm": 0.10328345745801926,
+      "learning_rate": 3.288888888888889e-05,
+      "loss": 0.0074,
+      "step": 75
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 0.08840714395046234,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 0.0069,
+      "step": 80
+    },
+    {
+      "epoch": 0.33073929961089493,
+      "grad_norm": 0.1998119205236435,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.0069,
+      "step": 85
+    },
+    {
+      "epoch": 0.35019455252918286,
+      "grad_norm": 0.08085718750953674,
+      "learning_rate": 3.9555555555555556e-05,
+      "loss": 0.0072,
+      "step": 90
+    },
+    {
+      "epoch": 0.36964980544747084,
+      "grad_norm": 0.10597972571849823,
+      "learning_rate": 4.177777777777778e-05,
+      "loss": 0.0072,
+      "step": 95
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 0.04654397815465927,
+      "learning_rate": 4.4e-05,
+      "loss": 0.0065,
+      "step": 100
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "eval_loss": 0.01389834564179182,
+      "eval_runtime": 174.9649,
+      "eval_samples_per_second": 2.915,
+      "eval_steps_per_second": 0.732,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1799,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 30,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.810966969647155e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74aab1d0c2724784614181306df8fc5fd4785e5c0771ac25a75ed3b96204917
+size 6417

checkpoint-300/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/medgemma-4b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/medgemma-4b-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 0.18.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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/medgemma-4b-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": 32,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70013a04fa52455aa35109fdb7ef8ab51147e6fdeae84864b8f029d400f70faa
+size 308107928

checkpoint-300/added_tokens.json

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

checkpoint-300/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-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bd37854c5a77a4dbf5dbbdf5a1b46d5f3338b44de9b2b6650dded795191642
+size 157332069

checkpoint-300/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoint-300/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8138f1105ce33d82b9d118d54f9fb1afd211b0bda93cd0aa8effe5b69f6cbce4
+size 14645

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbdc70435f287d81ad66c656f575416da2d1b679d04dfeb3a37105725eec93a
+size 1465

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
+size 33384822

checkpoint-300/tokenizer.model

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

checkpoint-300/trainer_state.json

@@ -0,0 +1,487 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.01389834564179182,
+  "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-100",
+  "epoch": 1.1673151750972763,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019455252918287938,
+      "grad_norm": 3.0237326622009277,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.8809,
+      "step": 5
+    },
+    {
+      "epoch": 0.038910505836575876,
+      "grad_norm": 2.4512810707092285,
+      "learning_rate": 4e-06,
+      "loss": 0.8569,
+      "step": 10
+    },
+    {
+      "epoch": 0.058365758754863814,
+      "grad_norm": 1.5967055559158325,
+      "learning_rate": 6.222222222222222e-06,
+      "loss": 0.7725,
+      "step": 15
+    },
+    {
+      "epoch": 0.07782101167315175,
+      "grad_norm": 1.2497001886367798,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.6516,
+      "step": 20
+    },
+    {
+      "epoch": 0.09727626459143969,
+      "grad_norm": 1.2455090284347534,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.5238,
+      "step": 25
+    },
+    {
+      "epoch": 0.11673151750972763,
+      "grad_norm": 1.361525535583496,
+      "learning_rate": 1.2888888888888889e-05,
+      "loss": 0.3777,
+      "step": 30
+    },
+    {
+      "epoch": 0.13618677042801555,
+      "grad_norm": 1.6556775569915771,
+      "learning_rate": 1.511111111111111e-05,
+      "loss": 0.2116,
+      "step": 35
+    },
+    {
+      "epoch": 0.1556420233463035,
+      "grad_norm": 0.6078555583953857,
+      "learning_rate": 1.7333333333333332e-05,
+      "loss": 0.0794,
+      "step": 40
+    },
+    {
+      "epoch": 0.17509727626459143,
+      "grad_norm": 0.31556975841522217,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.0343,
+      "step": 45
+    },
+    {
+      "epoch": 0.19455252918287938,
+      "grad_norm": 0.23063282668590546,
+      "learning_rate": 2.177777777777778e-05,
+      "loss": 0.0227,
+      "step": 50
+    },
+    {
+      "epoch": 0.2140077821011673,
+      "grad_norm": 0.10897089540958405,
+      "learning_rate": 2.4e-05,
+      "loss": 0.0159,
+      "step": 55
+    },
+    {
+      "epoch": 0.23346303501945526,
+      "grad_norm": 0.08667729049921036,
+      "learning_rate": 2.6222222222222226e-05,
+      "loss": 0.0155,
+      "step": 60
+    },
+    {
+      "epoch": 0.2529182879377432,
+      "grad_norm": 0.07056345790624619,
+      "learning_rate": 2.8444444444444447e-05,
+      "loss": 0.0133,
+      "step": 65
+    },
+    {
+      "epoch": 0.2723735408560311,
+      "grad_norm": 0.119380883872509,
+      "learning_rate": 3.066666666666666e-05,
+      "loss": 0.0113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2918287937743191,
+      "grad_norm": 0.10328345745801926,
+      "learning_rate": 3.288888888888889e-05,
+      "loss": 0.0074,
+      "step": 75
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 0.08840714395046234,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 0.0069,
+      "step": 80
+    },
+    {
+      "epoch": 0.33073929961089493,
+      "grad_norm": 0.1998119205236435,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.0069,
+      "step": 85
+    },
+    {
+      "epoch": 0.35019455252918286,
+      "grad_norm": 0.08085718750953674,
+      "learning_rate": 3.9555555555555556e-05,
+      "loss": 0.0072,
+      "step": 90
+    },
+    {
+      "epoch": 0.36964980544747084,
+      "grad_norm": 0.10597972571849823,
+      "learning_rate": 4.177777777777778e-05,
+      "loss": 0.0072,
+      "step": 95
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 0.04654397815465927,
+      "learning_rate": 4.4e-05,
+      "loss": 0.0065,
+      "step": 100
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "eval_loss": 0.01389834564179182,
+      "eval_runtime": 174.9649,
+      "eval_samples_per_second": 2.915,
+      "eval_steps_per_second": 0.732,
+      "step": 100
+    },
+    {
+      "epoch": 0.4085603112840467,
+      "grad_norm": 0.08657707273960114,
+      "learning_rate": 4.6222222222222224e-05,
+      "loss": 0.0071,
+      "step": 105
+    },
+    {
+      "epoch": 0.4280155642023346,
+      "grad_norm": 0.09846911579370499,
+      "learning_rate": 4.844444444444445e-05,
+      "loss": 0.0069,
+      "step": 110
+    },
+    {
+      "epoch": 0.4474708171206226,
+      "grad_norm": 0.07289458811283112,
+      "learning_rate": 5.066666666666667e-05,
+      "loss": 0.0072,
+      "step": 115
+    },
+    {
+      "epoch": 0.4669260700389105,
+      "grad_norm": 0.04821142926812172,
+      "learning_rate": 5.288888888888889e-05,
+      "loss": 0.0063,
+      "step": 120
+    },
+    {
+      "epoch": 0.48638132295719844,
+      "grad_norm": 0.06011726334691048,
+      "learning_rate": 5.511111111111111e-05,
+      "loss": 0.0068,
+      "step": 125
+    },
+    {
+      "epoch": 0.5058365758754864,
+      "grad_norm": 0.05461547151207924,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 0.0065,
+      "step": 130
+    },
+    {
+      "epoch": 0.5252918287937743,
+      "grad_norm": 0.05819641426205635,
+      "learning_rate": 5.9555555555555554e-05,
+      "loss": 0.0061,
+      "step": 135
+    },
+    {
+      "epoch": 0.5447470817120622,
+      "grad_norm": 0.048746656626462936,
+      "learning_rate": 6.177777777777779e-05,
+      "loss": 0.0065,
+      "step": 140
+    },
+    {
+      "epoch": 0.5642023346303502,
+      "grad_norm": 0.04917529225349426,
+      "learning_rate": 6.4e-05,
+      "loss": 0.0066,
+      "step": 145
+    },
+    {
+      "epoch": 0.5836575875486382,
+      "grad_norm": 0.062472034245729446,
+      "learning_rate": 6.622222222222222e-05,
+      "loss": 0.0067,
+      "step": 150
+    },
+    {
+      "epoch": 0.603112840466926,
+      "grad_norm": 0.07727159559726715,
+      "learning_rate": 6.844444444444445e-05,
+      "loss": 0.0068,
+      "step": 155
+    },
+    {
+      "epoch": 0.622568093385214,
+      "grad_norm": 0.036719705909490585,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 0.0062,
+      "step": 160
+    },
+    {
+      "epoch": 0.642023346303502,
+      "grad_norm": 0.04453688859939575,
+      "learning_rate": 7.288888888888888e-05,
+      "loss": 0.0064,
+      "step": 165
+    },
+    {
+      "epoch": 0.6614785992217899,
+      "grad_norm": 0.06014733761548996,
+      "learning_rate": 7.511111111111111e-05,
+      "loss": 0.0068,
+      "step": 170
+    },
+    {
+      "epoch": 0.6809338521400778,
+      "grad_norm": 0.06567176431417465,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.0069,
+      "step": 175
+    },
+    {
+      "epoch": 0.7003891050583657,
+      "grad_norm": 0.058225322514772415,
+      "learning_rate": 7.955555555555556e-05,
+      "loss": 0.007,
+      "step": 180
+    },
+    {
+      "epoch": 0.7198443579766537,
+      "grad_norm": 0.04187316447496414,
+      "learning_rate": 8.177777777777778e-05,
+      "loss": 0.0065,
+      "step": 185
+    },
+    {
+      "epoch": 0.7392996108949417,
+      "grad_norm": 0.03578794747591019,
+      "learning_rate": 8.4e-05,
+      "loss": 0.0061,
+      "step": 190
+    },
+    {
+      "epoch": 0.7587548638132295,
+      "grad_norm": 0.0358467772603035,
+      "learning_rate": 8.622222222222223e-05,
+      "loss": 0.0065,
+      "step": 195
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "grad_norm": 0.027109306305646896,
+      "learning_rate": 8.844444444444445e-05,
+      "loss": 0.0063,
+      "step": 200
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "eval_loss": 0.01398194208741188,
+      "eval_runtime": 152.8483,
+      "eval_samples_per_second": 3.337,
+      "eval_steps_per_second": 0.837,
+      "step": 200
+    },
+    {
+      "epoch": 0.7976653696498055,
+      "grad_norm": 0.031359098851680756,
+      "learning_rate": 9.066666666666667e-05,
+      "loss": 0.0061,
+      "step": 205
+    },
+    {
+      "epoch": 0.8171206225680934,
+      "grad_norm": 0.041419435292482376,
+      "learning_rate": 9.288888888888888e-05,
+      "loss": 0.0062,
+      "step": 210
+    },
+    {
+      "epoch": 0.8365758754863813,
+      "grad_norm": 0.03226594254374504,
+      "learning_rate": 9.511111111111112e-05,
+      "loss": 0.0059,
+      "step": 215
+    },
+    {
+      "epoch": 0.8560311284046692,
+      "grad_norm": 0.07033108919858932,
+      "learning_rate": 9.733333333333333e-05,
+      "loss": 0.0061,
+      "step": 220
+    },
+    {
+      "epoch": 0.8754863813229572,
+      "grad_norm": 0.05067949742078781,
+      "learning_rate": 9.955555555555556e-05,
+      "loss": 0.0059,
+      "step": 225
+    },
+    {
+      "epoch": 0.8949416342412452,
+      "grad_norm": 0.025263365358114243,
+      "learning_rate": 0.00010177777777777777,
+      "loss": 0.0059,
+      "step": 230
+    },
+    {
+      "epoch": 0.914396887159533,
+      "grad_norm": 0.03773004561662674,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.0062,
+      "step": 235
+    },
+    {
+      "epoch": 0.933852140077821,
+      "grad_norm": 0.03331644833087921,
+      "learning_rate": 0.00010622222222222222,
+      "loss": 0.006,
+      "step": 240
+    },
+    {
+      "epoch": 0.953307392996109,
+      "grad_norm": 0.03881971910595894,
+      "learning_rate": 0.00010844444444444444,
+      "loss": 0.0059,
+      "step": 245
+    },
+    {
+      "epoch": 0.9727626459143969,
+      "grad_norm": 0.0403914675116539,
+      "learning_rate": 0.00011066666666666668,
+      "loss": 0.0062,
+      "step": 250
+    },
+    {
+      "epoch": 0.9922178988326849,
+      "grad_norm": 0.03234079107642174,
+      "learning_rate": 0.0001128888888888889,
+      "loss": 0.0064,
+      "step": 255
+    },
+    {
+      "epoch": 1.0116731517509727,
+      "grad_norm": 0.0188930481672287,
+      "learning_rate": 0.00011511111111111112,
+      "loss": 0.0061,
+      "step": 260
+    },
+    {
+      "epoch": 1.0311284046692606,
+      "grad_norm": 0.02896421030163765,
+      "learning_rate": 0.00011733333333333333,
+      "loss": 0.0059,
+      "step": 265
+    },
+    {
+      "epoch": 1.0505836575875487,
+      "grad_norm": 0.038550637662410736,
+      "learning_rate": 0.00011955555555555557,
+      "loss": 0.0066,
+      "step": 270
+    },
+    {
+      "epoch": 1.0700389105058365,
+      "grad_norm": 0.024153664708137512,
+      "learning_rate": 0.00011999797360750958,
+      "loss": 0.0062,
+      "step": 275
+    },
+    {
+      "epoch": 1.0894941634241244,
+      "grad_norm": 0.027283893898129463,
+      "learning_rate": 0.00011998974162260325,
+      "loss": 0.006,
+      "step": 280
+    },
+    {
+      "epoch": 1.1089494163424125,
+      "grad_norm": 0.035498056560754776,
+      "learning_rate": 0.00011997517826389341,
+      "loss": 0.0064,
+      "step": 285
+    },
+    {
+      "epoch": 1.1284046692607004,
+      "grad_norm": 0.021591784432530403,
+      "learning_rate": 0.00011995428506841069,
+      "loss": 0.0061,
+      "step": 290
+    },
+    {
+      "epoch": 1.1478599221789882,
+      "grad_norm": 0.016961926594376564,
+      "learning_rate": 0.00011992706424124257,
+      "loss": 0.006,
+      "step": 295
+    },
+    {
+      "epoch": 1.1673151750972763,
+      "grad_norm": 0.03020872175693512,
+      "learning_rate": 0.00011989351865530078,
+      "loss": 0.0063,
+      "step": 300
+    },
+    {
+      "epoch": 1.1673151750972763,
+      "eval_loss": 0.014270401559770107,
+      "eval_runtime": 152.9753,
+      "eval_samples_per_second": 3.334,
+      "eval_steps_per_second": 0.837,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1799,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 30,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0425665990873542e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74aab1d0c2724784614181306df8fc5fd4785e5c0771ac25a75ed3b96204917
+size 6417

checkpoint-400/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/medgemma-4b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/medgemma-4b-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 0.18.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "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/medgemma-4b-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": 32,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958e649f9f391eb053a1d761e63f66533c7fad366ae8d5cadb2450e74b79d67e
+size 308107928

checkpoint-400/added_tokens.json

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

checkpoint-400/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-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffbb20e460857e5578e76a59ab460f24251c712b29eca8b2eafe83a3fa634557
+size 157332069

checkpoint-400/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoint-400/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35a449824ab6da5f64df0583d6b86b5d8d310a39763d8b4e07c3df36afa3ade
+size 14645

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e46939086c88a3be6cd6b25590a0af93e4076de259468484ea43c4e10d03cda
+size 1465

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
+size 33384822

checkpoint-400/tokenizer.model

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

checkpoint-400/trainer_state.json

@@ -0,0 +1,635 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.01389834564179182,
+  "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-100",
+  "epoch": 1.556420233463035,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019455252918287938,
+      "grad_norm": 3.0237326622009277,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.8809,
+      "step": 5
+    },
+    {
+      "epoch": 0.038910505836575876,
+      "grad_norm": 2.4512810707092285,
+      "learning_rate": 4e-06,
+      "loss": 0.8569,
+      "step": 10
+    },
+    {
+      "epoch": 0.058365758754863814,
+      "grad_norm": 1.5967055559158325,
+      "learning_rate": 6.222222222222222e-06,
+      "loss": 0.7725,
+      "step": 15
+    },
+    {
+      "epoch": 0.07782101167315175,
+      "grad_norm": 1.2497001886367798,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.6516,
+      "step": 20
+    },
+    {
+      "epoch": 0.09727626459143969,
+      "grad_norm": 1.2455090284347534,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.5238,
+      "step": 25
+    },
+    {
+      "epoch": 0.11673151750972763,
+      "grad_norm": 1.361525535583496,
+      "learning_rate": 1.2888888888888889e-05,
+      "loss": 0.3777,
+      "step": 30
+    },
+    {
+      "epoch": 0.13618677042801555,
+      "grad_norm": 1.6556775569915771,
+      "learning_rate": 1.511111111111111e-05,
+      "loss": 0.2116,
+      "step": 35
+    },
+    {
+      "epoch": 0.1556420233463035,
+      "grad_norm": 0.6078555583953857,
+      "learning_rate": 1.7333333333333332e-05,
+      "loss": 0.0794,
+      "step": 40
+    },
+    {
+      "epoch": 0.17509727626459143,
+      "grad_norm": 0.31556975841522217,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.0343,
+      "step": 45
+    },
+    {
+      "epoch": 0.19455252918287938,
+      "grad_norm": 0.23063282668590546,
+      "learning_rate": 2.177777777777778e-05,
+      "loss": 0.0227,
+      "step": 50
+    },
+    {
+      "epoch": 0.2140077821011673,
+      "grad_norm": 0.10897089540958405,
+      "learning_rate": 2.4e-05,
+      "loss": 0.0159,
+      "step": 55
+    },
+    {
+      "epoch": 0.23346303501945526,
+      "grad_norm": 0.08667729049921036,
+      "learning_rate": 2.6222222222222226e-05,
+      "loss": 0.0155,
+      "step": 60
+    },
+    {
+      "epoch": 0.2529182879377432,
+      "grad_norm": 0.07056345790624619,
+      "learning_rate": 2.8444444444444447e-05,
+      "loss": 0.0133,
+      "step": 65
+    },
+    {
+      "epoch": 0.2723735408560311,
+      "grad_norm": 0.119380883872509,
+      "learning_rate": 3.066666666666666e-05,
+      "loss": 0.0113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2918287937743191,
+      "grad_norm": 0.10328345745801926,
+      "learning_rate": 3.288888888888889e-05,
+      "loss": 0.0074,
+      "step": 75
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 0.08840714395046234,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 0.0069,
+      "step": 80
+    },
+    {
+      "epoch": 0.33073929961089493,
+      "grad_norm": 0.1998119205236435,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.0069,
+      "step": 85
+    },
+    {
+      "epoch": 0.35019455252918286,
+      "grad_norm": 0.08085718750953674,
+      "learning_rate": 3.9555555555555556e-05,
+      "loss": 0.0072,
+      "step": 90
+    },
+    {
+      "epoch": 0.36964980544747084,
+      "grad_norm": 0.10597972571849823,
+      "learning_rate": 4.177777777777778e-05,
+      "loss": 0.0072,
+      "step": 95
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 0.04654397815465927,
+      "learning_rate": 4.4e-05,
+      "loss": 0.0065,
+      "step": 100
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "eval_loss": 0.01389834564179182,
+      "eval_runtime": 174.9649,
+      "eval_samples_per_second": 2.915,
+      "eval_steps_per_second": 0.732,
+      "step": 100
+    },
+    {
+      "epoch": 0.4085603112840467,
+      "grad_norm": 0.08657707273960114,
+      "learning_rate": 4.6222222222222224e-05,
+      "loss": 0.0071,
+      "step": 105
+    },
+    {
+      "epoch": 0.4280155642023346,
+      "grad_norm": 0.09846911579370499,
+      "learning_rate": 4.844444444444445e-05,
+      "loss": 0.0069,
+      "step": 110
+    },
+    {
+      "epoch": 0.4474708171206226,
+      "grad_norm": 0.07289458811283112,
+      "learning_rate": 5.066666666666667e-05,
+      "loss": 0.0072,
+      "step": 115
+    },
+    {
+      "epoch": 0.4669260700389105,
+      "grad_norm": 0.04821142926812172,
+      "learning_rate": 5.288888888888889e-05,
+      "loss": 0.0063,
+      "step": 120
+    },
+    {
+      "epoch": 0.48638132295719844,
+      "grad_norm": 0.06011726334691048,
+      "learning_rate": 5.511111111111111e-05,
+      "loss": 0.0068,
+      "step": 125
+    },
+    {
+      "epoch": 0.5058365758754864,
+      "grad_norm": 0.05461547151207924,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 0.0065,
+      "step": 130
+    },
+    {
+      "epoch": 0.5252918287937743,
+      "grad_norm": 0.05819641426205635,
+      "learning_rate": 5.9555555555555554e-05,
+      "loss": 0.0061,
+      "step": 135
+    },
+    {
+      "epoch": 0.5447470817120622,
+      "grad_norm": 0.048746656626462936,
+      "learning_rate": 6.177777777777779e-05,
+      "loss": 0.0065,
+      "step": 140
+    },
+    {
+      "epoch": 0.5642023346303502,
+      "grad_norm": 0.04917529225349426,
+      "learning_rate": 6.4e-05,
+      "loss": 0.0066,
+      "step": 145
+    },
+    {
+      "epoch": 0.5836575875486382,
+      "grad_norm": 0.062472034245729446,
+      "learning_rate": 6.622222222222222e-05,
+      "loss": 0.0067,
+      "step": 150
+    },
+    {
+      "epoch": 0.603112840466926,
+      "grad_norm": 0.07727159559726715,
+      "learning_rate": 6.844444444444445e-05,
+      "loss": 0.0068,
+      "step": 155
+    },
+    {
+      "epoch": 0.622568093385214,
+      "grad_norm": 0.036719705909490585,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 0.0062,
+      "step": 160
+    },
+    {
+      "epoch": 0.642023346303502,
+      "grad_norm": 0.04453688859939575,
+      "learning_rate": 7.288888888888888e-05,
+      "loss": 0.0064,
+      "step": 165
+    },
+    {
+      "epoch": 0.6614785992217899,
+      "grad_norm": 0.06014733761548996,
+      "learning_rate": 7.511111111111111e-05,
+      "loss": 0.0068,
+      "step": 170
+    },
+    {
+      "epoch": 0.6809338521400778,
+      "grad_norm": 0.06567176431417465,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.0069,
+      "step": 175
+    },
+    {
+      "epoch": 0.7003891050583657,
+      "grad_norm": 0.058225322514772415,
+      "learning_rate": 7.955555555555556e-05,
+      "loss": 0.007,
+      "step": 180
+    },
+    {
+      "epoch": 0.7198443579766537,
+      "grad_norm": 0.04187316447496414,
+      "learning_rate": 8.177777777777778e-05,
+      "loss": 0.0065,
+      "step": 185
+    },
+    {
+      "epoch": 0.7392996108949417,
+      "grad_norm": 0.03578794747591019,
+      "learning_rate": 8.4e-05,
+      "loss": 0.0061,
+      "step": 190
+    },
+    {
+      "epoch": 0.7587548638132295,
+      "grad_norm": 0.0358467772603035,
+      "learning_rate": 8.622222222222223e-05,
+      "loss": 0.0065,
+      "step": 195
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "grad_norm": 0.027109306305646896,
+      "learning_rate": 8.844444444444445e-05,
+      "loss": 0.0063,
+      "step": 200
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "eval_loss": 0.01398194208741188,
+      "eval_runtime": 152.8483,
+      "eval_samples_per_second": 3.337,
+      "eval_steps_per_second": 0.837,
+      "step": 200
+    },
+    {
+      "epoch": 0.7976653696498055,
+      "grad_norm": 0.031359098851680756,
+      "learning_rate": 9.066666666666667e-05,
+      "loss": 0.0061,
+      "step": 205
+    },
+    {
+      "epoch": 0.8171206225680934,
+      "grad_norm": 0.041419435292482376,
+      "learning_rate": 9.288888888888888e-05,
+      "loss": 0.0062,
+      "step": 210
+    },
+    {
+      "epoch": 0.8365758754863813,
+      "grad_norm": 0.03226594254374504,
+      "learning_rate": 9.511111111111112e-05,
+      "loss": 0.0059,
+      "step": 215
+    },
+    {
+      "epoch": 0.8560311284046692,
+      "grad_norm": 0.07033108919858932,
+      "learning_rate": 9.733333333333333e-05,
+      "loss": 0.0061,
+      "step": 220
+    },
+    {
+      "epoch": 0.8754863813229572,
+      "grad_norm": 0.05067949742078781,
+      "learning_rate": 9.955555555555556e-05,
+      "loss": 0.0059,
+      "step": 225
+    },
+    {
+      "epoch": 0.8949416342412452,
+      "grad_norm": 0.025263365358114243,
+      "learning_rate": 0.00010177777777777777,
+      "loss": 0.0059,
+      "step": 230
+    },
+    {
+      "epoch": 0.914396887159533,
+      "grad_norm": 0.03773004561662674,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.0062,
+      "step": 235
+    },
+    {
+      "epoch": 0.933852140077821,
+      "grad_norm": 0.03331644833087921,
+      "learning_rate": 0.00010622222222222222,
+      "loss": 0.006,
+      "step": 240
+    },
+    {
+      "epoch": 0.953307392996109,
+      "grad_norm": 0.03881971910595894,
+      "learning_rate": 0.00010844444444444444,
+      "loss": 0.0059,
+      "step": 245
+    },
+    {
+      "epoch": 0.9727626459143969,
+      "grad_norm": 0.0403914675116539,
+      "learning_rate": 0.00011066666666666668,
+      "loss": 0.0062,
+      "step": 250
+    },
+    {
+      "epoch": 0.9922178988326849,
+      "grad_norm": 0.03234079107642174,
+      "learning_rate": 0.0001128888888888889,
+      "loss": 0.0064,
+      "step": 255
+    },
+    {
+      "epoch": 1.0116731517509727,
+      "grad_norm": 0.0188930481672287,
+      "learning_rate": 0.00011511111111111112,
+      "loss": 0.0061,
+      "step": 260
+    },
+    {
+      "epoch": 1.0311284046692606,
+      "grad_norm": 0.02896421030163765,
+      "learning_rate": 0.00011733333333333333,
+      "loss": 0.0059,
+      "step": 265
+    },
+    {
+      "epoch": 1.0505836575875487,
+      "grad_norm": 0.038550637662410736,
+      "learning_rate": 0.00011955555555555557,
+      "loss": 0.0066,
+      "step": 270
+    },
+    {
+      "epoch": 1.0700389105058365,
+      "grad_norm": 0.024153664708137512,
+      "learning_rate": 0.00011999797360750958,
+      "loss": 0.0062,
+      "step": 275
+    },
+    {
+      "epoch": 1.0894941634241244,
+      "grad_norm": 0.027283893898129463,
+      "learning_rate": 0.00011998974162260325,
+      "loss": 0.006,
+      "step": 280
+    },
+    {
+      "epoch": 1.1089494163424125,
+      "grad_norm": 0.035498056560754776,
+      "learning_rate": 0.00011997517826389341,
+      "loss": 0.0064,
+      "step": 285
+    },
+    {
+      "epoch": 1.1284046692607004,
+      "grad_norm": 0.021591784432530403,
+      "learning_rate": 0.00011995428506841069,
+      "loss": 0.0061,
+      "step": 290
+    },
+    {
+      "epoch": 1.1478599221789882,
+      "grad_norm": 0.016961926594376564,
+      "learning_rate": 0.00011992706424124257,
+      "loss": 0.006,
+      "step": 295
+    },
+    {
+      "epoch": 1.1673151750972763,
+      "grad_norm": 0.03020872175693512,
+      "learning_rate": 0.00011989351865530078,
+      "loss": 0.0063,
+      "step": 300
+    },
+    {
+      "epoch": 1.1673151750972763,
+      "eval_loss": 0.014270401559770107,
+      "eval_runtime": 152.9753,
+      "eval_samples_per_second": 3.334,
+      "eval_steps_per_second": 0.837,
+      "step": 300
+    },
+    {
+      "epoch": 1.1867704280155642,
+      "grad_norm": 0.025152679532766342,
+      "learning_rate": 0.00011985365185101807,
+      "loss": 0.0063,
+      "step": 305
+    },
+    {
+      "epoch": 1.206225680933852,
+      "grad_norm": 0.030001649633049965,
+      "learning_rate": 0.00011980746803597448,
+      "loss": 0.0063,
+      "step": 310
+    },
+    {
+      "epoch": 1.2256809338521402,
+      "grad_norm": 0.031324416399002075,
+      "learning_rate": 0.0001197549720844533,
+      "loss": 0.0065,
+      "step": 315
+    },
+    {
+      "epoch": 1.245136186770428,
+      "grad_norm": 0.030990222468972206,
+      "learning_rate": 0.00011969616953692672,
+      "loss": 0.0066,
+      "step": 320
+    },
+    {
+      "epoch": 1.264591439688716,
+      "grad_norm": 0.02283373288810253,
+      "learning_rate": 0.00011963106659947091,
+      "loss": 0.0062,
+      "step": 325
+    },
+    {
+      "epoch": 1.2840466926070038,
+      "grad_norm": 0.027848919853568077,
+      "learning_rate": 0.00011955967014311121,
+      "loss": 0.0061,
+      "step": 330
+    },
+    {
+      "epoch": 1.3035019455252919,
+      "grad_norm": 0.0324862040579319,
+      "learning_rate": 0.00011948198770309682,
+      "loss": 0.0064,
+      "step": 335
+    },
+    {
+      "epoch": 1.3229571984435797,
+      "grad_norm": 0.021669326350092888,
+      "learning_rate": 0.00011939802747810558,
+      "loss": 0.0061,
+      "step": 340
+    },
+    {
+      "epoch": 1.3424124513618678,
+      "grad_norm": 0.023976098746061325,
+      "learning_rate": 0.0001193077983293787,
+      "loss": 0.006,
+      "step": 345
+    },
+    {
+      "epoch": 1.3618677042801557,
+      "grad_norm": 0.022651424631476402,
+      "learning_rate": 0.00011921130977978545,
+      "loss": 0.0062,
+      "step": 350
+    },
+    {
+      "epoch": 1.3813229571984436,
+      "grad_norm": 0.021479440852999687,
+      "learning_rate": 0.0001191085720128182,
+      "loss": 0.0062,
+      "step": 355
+    },
+    {
+      "epoch": 1.4007782101167314,
+      "grad_norm": 0.1814209520816803,
+      "learning_rate": 0.00011899959587151756,
+      "loss": 0.0061,
+      "step": 360
+    },
+    {
+      "epoch": 1.4202334630350195,
+      "grad_norm": 1.4026191234588623,
+      "learning_rate": 0.00011888439285732813,
+      "loss": 0.0261,
+      "step": 365
+    },
+    {
+      "epoch": 1.4396887159533074,
+      "grad_norm": 1.3291703462600708,
+      "learning_rate": 0.00011876297512888443,
+      "loss": 0.0267,
+      "step": 370
+    },
+    {
+      "epoch": 1.4591439688715953,
+      "grad_norm": 1.7693599462509155,
+      "learning_rate": 0.00011863535550072783,
+      "loss": 0.0212,
+      "step": 375
+    },
+    {
+      "epoch": 1.4785992217898833,
+      "grad_norm": 0.9990978240966797,
+      "learning_rate": 0.00011850154744195403,
+      "loss": 0.0218,
+      "step": 380
+    },
+    {
+      "epoch": 1.4980544747081712,
+      "grad_norm": 0.29475995898246765,
+      "learning_rate": 0.0001183615650747915,
+      "loss": 0.0117,
+      "step": 385
+    },
+    {
+      "epoch": 1.517509727626459,
+      "grad_norm": 0.04740586131811142,
+      "learning_rate": 0.00011821542317311106,
+      "loss": 0.0084,
+      "step": 390
+    },
+    {
+      "epoch": 1.536964980544747,
+      "grad_norm": 0.04320238158106804,
+      "learning_rate": 0.00011806313716086658,
+      "loss": 0.0067,
+      "step": 395
+    },
+    {
+      "epoch": 1.556420233463035,
+      "grad_norm": 0.05465610325336456,
+      "learning_rate": 0.00011790472311046715,
+      "loss": 0.0065,
+      "step": 400
+    },
+    {
+      "epoch": 1.556420233463035,
+      "eval_loss": 0.07703334093093872,
+      "eval_runtime": 152.4522,
+      "eval_samples_per_second": 3.345,
+      "eval_steps_per_second": 0.84,
+      "step": 400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1799,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 30,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7238400607783456e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74aab1d0c2724784614181306df8fc5fd4785e5c0771ac25a75ed3b96204917
+size 6417