Upload folder using huggingface_hub

.gitattributes

@@ -42,3 +42,4 @@ 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
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-700/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/gemma-3-12b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-12b-it
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-700/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c29d933f69302788c7ba64c151618c799575227bcb3e0c3ca7ec32e53ea7731
+size 137039712

checkpoint-700/added_tokens.json

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

checkpoint-700/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 -%}{{ eos_token }}

checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3002fc61d5b2cd58461b215030a9f061958cf373685c9b01ee0666bb2559c950
+size 262449347

checkpoint-700/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac4881fcaece8e8bece11bbaea7377e344f660a57a242bc41e762bb97dc5122
+size 14917

checkpoint-700/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd18116c7bed6b676084ab4ca45016cd1d610c4529a2ca2b0a7acb213f723b4
+size 14917

checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91f815a7674bf7e2aa591d7c9ab737852cf189194afa969144c8a25f4c1fe9c
+size 1465

checkpoint-700/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": "<eos>",
+    "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-700/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-700/tokenizer.model

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

checkpoint-700/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8469656992084431,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2674074932932853,
+      "epoch": 0.10554089709762533,
+      "grad_norm": 0.3261065185070038,
+      "learning_rate": 0.00019399293286219082,
+      "loss": 2.8469,
+      "mean_token_accuracy": 0.6490223720669747,
+      "num_tokens": 245379.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.971577849984169,
+      "epoch": 0.21108179419525067,
+      "grad_norm": 0.27820920944213867,
+      "learning_rate": 0.00018692579505300353,
+      "loss": 0.9858,
+      "mean_token_accuracy": 0.7603534738222758,
+      "num_tokens": 491860.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9173460498452186,
+      "epoch": 0.316622691292876,
+      "grad_norm": 0.2709479033946991,
+      "learning_rate": 0.00017985865724381625,
+      "loss": 0.9262,
+      "mean_token_accuracy": 0.7726805781324705,
+      "num_tokens": 737565.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.9086941565076511,
+      "epoch": 0.42216358839050133,
+      "grad_norm": 0.2693174481391907,
+      "learning_rate": 0.00017279151943462898,
+      "loss": 0.9177,
+      "mean_token_accuracy": 0.7741145516435305,
+      "num_tokens": 983943.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.9111664916078249,
+      "epoch": 0.5277044854881267,
+      "grad_norm": 0.22922798991203308,
+      "learning_rate": 0.0001657243816254417,
+      "loss": 0.9206,
+      "mean_token_accuracy": 0.772779801984628,
+      "num_tokens": 1228020.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.8938635811209679,
+      "epoch": 0.633245382585752,
+      "grad_norm": 0.25951769948005676,
+      "learning_rate": 0.0001586572438162544,
+      "loss": 0.9048,
+      "mean_token_accuracy": 0.7775348087151845,
+      "num_tokens": 1468166.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.898859229683876,
+      "epoch": 0.7387862796833773,
+      "grad_norm": 0.2515920400619507,
+      "learning_rate": 0.00015159010600706714,
+      "loss": 0.9087,
+      "mean_token_accuracy": 0.7758232519030571,
+      "num_tokens": 1710547.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.893895897269249,
+      "epoch": 0.8443271767810027,
+      "grad_norm": 0.24169541895389557,
+      "learning_rate": 0.00014452296819787987,
+      "loss": 0.9046,
+      "mean_token_accuracy": 0.7770114933451017,
+      "num_tokens": 1954553.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.8812289908528328,
+      "epoch": 0.9498680738786279,
+      "grad_norm": 0.23435117304325104,
+      "learning_rate": 0.00013745583038869257,
+      "loss": 0.8864,
+      "mean_token_accuracy": 0.7819622402389844,
+      "num_tokens": 2199514.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.8911305258671443,
+      "epoch": 1.0554089709762533,
+      "grad_norm": 0.24556870758533478,
+      "learning_rate": 0.0001303886925795053,
+      "loss": 0.8889,
+      "mean_token_accuracy": 0.7818753371636072,
+      "num_tokens": 2442473.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8615878681341808,
+      "epoch": 1.1609498680738786,
+      "grad_norm": 0.2553667724132538,
+      "learning_rate": 0.00012332155477031803,
+      "loss": 0.865,
+      "mean_token_accuracy": 0.7888134623567263,
+      "num_tokens": 2685798.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.8409679149587949,
+      "epoch": 1.266490765171504,
+      "grad_norm": 0.2546869218349457,
+      "learning_rate": 0.00011625441696113076,
+      "loss": 0.8429,
+      "mean_token_accuracy": 0.792593814432621,
+      "num_tokens": 2928681.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8437916760643324,
+      "epoch": 1.3720316622691293,
+      "grad_norm": 0.2557734549045563,
+      "learning_rate": 0.00010918727915194346,
+      "loss": 0.8416,
+      "mean_token_accuracy": 0.7940337762236596,
+      "num_tokens": 3171456.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.857711431880792,
+      "epoch": 1.4775725593667546,
+      "grad_norm": 0.26654869318008423,
+      "learning_rate": 0.00010212014134275618,
+      "loss": 0.8579,
+      "mean_token_accuracy": 0.7909541388352712,
+      "num_tokens": 3417723.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.8400450726350148,
+      "epoch": 1.58311345646438,
+      "grad_norm": 0.29494455456733704,
+      "learning_rate": 9.50530035335689e-05,
+      "loss": 0.8383,
+      "mean_token_accuracy": 0.7945970013737679,
+      "num_tokens": 3665359.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8542267888784408,
+      "epoch": 1.6886543535620053,
+      "grad_norm": 0.2574358284473419,
+      "learning_rate": 8.798586572438163e-05,
+      "loss": 0.8562,
+      "mean_token_accuracy": 0.789784766236941,
+      "num_tokens": 3910743.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.8403926879167557,
+      "epoch": 1.7941952506596306,
+      "grad_norm": 0.28781425952911377,
+      "learning_rate": 8.091872791519435e-05,
+      "loss": 0.8381,
+      "mean_token_accuracy": 0.7947062104940414,
+      "num_tokens": 4155793.0,
+      "step": 680
+    }
+  ],
+  "logging_steps": 40,
+  "max_steps": 1137,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.79740742096126e+17,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ee49c4d2bdf3d3042505aee9fe7da70c37a1b67cf65920c81dae0c90104ef4
+size 6289