Upload 11 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: peft
+---
+
+# 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 0.15.2

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "fc2",
+    "out_proj",
+    "o_proj",
+    "fc1",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15819dd148915f88de894d2184cc7d25b1678fc97bb6d7adbb0efc933568cf9
+size 154294986

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2969c28516ecb1c6ab1b2fb1a582fccd8b5c74002693dfcef6bece5a78ffd47
+size 238821798

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7706f2a064488c44401ec8b9ffeef1dcd4dfcb0d6ec0279aa756079838dbbe
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2985260f3d01d01c1cd0ea4d80cf8038f9cbe9a9b731c7e39517c1a93ca3bb5f
+size 1064

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
+  }
+}

tokenizer.json

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

trainer_state.json

@@ -0,0 +1,403 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 20958,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047714476572192,
+      "grad_norm": 0.023498278111219406,
+      "learning_rate": 0.00019523809523809525,
+      "loss": 0.4674,
+      "mean_token_accuracy": 0.8906204112768173,
+      "num_tokens": 360041.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.095428953144384,
+      "grad_norm": 3.823547601699829,
+      "learning_rate": 0.00019046664758087605,
+      "loss": 0.3194,
+      "mean_token_accuracy": 0.9205255397558212,
+      "num_tokens": 727772.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.143143429716576,
+      "grad_norm": 0.0001839943724917248,
+      "learning_rate": 0.00018569519992365686,
+      "loss": 0.2674,
+      "mean_token_accuracy": 0.9327976078987121,
+      "num_tokens": 1097406.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.190857906288768,
+      "grad_norm": 4.199777126312256,
+      "learning_rate": 0.00018092375226643766,
+      "loss": 0.326,
+      "mean_token_accuracy": 0.920593403160572,
+      "num_tokens": 1462220.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23857238286096002,
+      "grad_norm": 5.751025676727295,
+      "learning_rate": 0.00017615230460921847,
+      "loss": 0.2693,
+      "mean_token_accuracy": 0.936355301618576,
+      "num_tokens": 1828224.0,
+      "step": 2500
+    },
+    {
+      "epoch": 0.286286859433152,
+      "grad_norm": 3.971045732498169,
+      "learning_rate": 0.00017138085695199925,
+      "loss": 0.2827,
+      "mean_token_accuracy": 0.9261101527214051,
+      "num_tokens": 2211342.0,
+      "step": 3000
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 2.15079665184021,
+      "learning_rate": 0.00016660940929478005,
+      "loss": 0.2461,
+      "mean_token_accuracy": 0.9350018633604049,
+      "num_tokens": 2572498.0,
+      "step": 3500
+    },
+    {
+      "epoch": 0.381715812577536,
+      "grad_norm": 0.5263189077377319,
+      "learning_rate": 0.00016183796163756083,
+      "loss": 0.2534,
+      "mean_token_accuracy": 0.9374513441324234,
+      "num_tokens": 2949312.0,
+      "step": 4000
+    },
+    {
+      "epoch": 0.42943028914972803,
+      "grad_norm": 0.004941379185765982,
+      "learning_rate": 0.00015706651398034164,
+      "loss": 0.2395,
+      "mean_token_accuracy": 0.9378743978738785,
+      "num_tokens": 3314910.0,
+      "step": 4500
+    },
+    {
+      "epoch": 0.47714476572192005,
+      "grad_norm": 0.007795912679284811,
+      "learning_rate": 0.00015229506632312244,
+      "loss": 0.2284,
+      "mean_token_accuracy": 0.9409392136335373,
+      "num_tokens": 3686624.0,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5248592422941121,
+      "grad_norm": 0.0033825524151325226,
+      "learning_rate": 0.00014752361866590325,
+      "loss": 0.2145,
+      "mean_token_accuracy": 0.9464458491802216,
+      "num_tokens": 4063459.0,
+      "step": 5500
+    },
+    {
+      "epoch": 0.572573718866304,
+      "grad_norm": 3.8457958698272705,
+      "learning_rate": 0.00014275217100868402,
+      "loss": 0.2268,
+      "mean_token_accuracy": 0.9410561621189117,
+      "num_tokens": 4423993.0,
+      "step": 6000
+    },
+    {
+      "epoch": 0.620288195438496,
+      "grad_norm": 0.020238121971488,
+      "learning_rate": 0.00013798072335146483,
+      "loss": 0.223,
+      "mean_token_accuracy": 0.9393890690803528,
+      "num_tokens": 4788203.0,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.0006973391864448786,
+      "learning_rate": 0.00013320927569424564,
+      "loss": 0.2434,
+      "mean_token_accuracy": 0.9404154337644577,
+      "num_tokens": 5162496.0,
+      "step": 7000
+    },
+    {
+      "epoch": 0.71571714858288,
+      "grad_norm": 0.0010198453674092889,
+      "learning_rate": 0.00012843782803702644,
+      "loss": 0.191,
+      "mean_token_accuracy": 0.9535960764884949,
+      "num_tokens": 5520427.0,
+      "step": 7500
+    },
+    {
+      "epoch": 0.763431625155072,
+      "grad_norm": 0.001297333394177258,
+      "learning_rate": 0.00012366638037980725,
+      "loss": 0.2167,
+      "mean_token_accuracy": 0.942195966720581,
+      "num_tokens": 5901763.0,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8111461017272641,
+      "grad_norm": 6.195448398590088,
+      "learning_rate": 0.00011889493272258805,
+      "loss": 0.2305,
+      "mean_token_accuracy": 0.9376264967918396,
+      "num_tokens": 6272492.0,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8588605782994561,
+      "grad_norm": 0.0025545568205416203,
+      "learning_rate": 0.00011412348506536883,
+      "loss": 0.2303,
+      "mean_token_accuracy": 0.9435879285335541,
+      "num_tokens": 6657487.0,
+      "step": 9000
+    },
+    {
+      "epoch": 0.906575054871648,
+      "grad_norm": 0.0006595577578991652,
+      "learning_rate": 0.00010935203740814964,
+      "loss": 0.179,
+      "mean_token_accuracy": 0.9520990616083145,
+      "num_tokens": 7022908.0,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9542895314438401,
+      "grad_norm": 3.1752443313598633,
+      "learning_rate": 0.00010458058975093044,
+      "loss": 0.1827,
+      "mean_token_accuracy": 0.9488343714475632,
+      "num_tokens": 7376243.0,
+      "step": 10000
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.001512572169303894,
+      "learning_rate": 9.980914209371123e-05,
+      "loss": 0.2101,
+      "mean_token_accuracy": 0.9424606282711029,
+      "num_tokens": 7749938.0,
+      "step": 10500
+    },
+    {
+      "epoch": 1.0497184845882241,
+      "grad_norm": 3.992393732070923,
+      "learning_rate": 9.503769443649203e-05,
+      "loss": 0.1309,
+      "mean_token_accuracy": 0.9618149808645249,
+      "num_tokens": 8127846.0,
+      "step": 11000
+    },
+    {
+      "epoch": 1.097432961160416,
+      "grad_norm": 0.00025509227998554707,
+      "learning_rate": 9.026624677927283e-05,
+      "loss": 0.1219,
+      "mean_token_accuracy": 0.9635183781385421,
+      "num_tokens": 8503956.0,
+      "step": 11500
+    },
+    {
+      "epoch": 1.145147437732608,
+      "grad_norm": 0.0013997952919453382,
+      "learning_rate": 8.549479912205364e-05,
+      "loss": 0.1235,
+      "mean_token_accuracy": 0.963010191321373,
+      "num_tokens": 8862553.0,
+      "step": 12000
+    },
+    {
+      "epoch": 1.1928619143048,
+      "grad_norm": 2.114091157913208,
+      "learning_rate": 8.072335146483443e-05,
+      "loss": 0.1271,
+      "mean_token_accuracy": 0.9629592669010162,
+      "num_tokens": 9233864.0,
+      "step": 12500
+    },
+    {
+      "epoch": 1.240576390876992,
+      "grad_norm": 0.277444452047348,
+      "learning_rate": 7.595190380761523e-05,
+      "loss": 0.1187,
+      "mean_token_accuracy": 0.9649668201208115,
+      "num_tokens": 9596971.0,
+      "step": 13000
+    },
+    {
+      "epoch": 1.288290867449184,
+      "grad_norm": 4.878781318664551,
+      "learning_rate": 7.118045615039604e-05,
+      "loss": 0.1226,
+      "mean_token_accuracy": 0.9633177869319915,
+      "num_tokens": 9966614.0,
+      "step": 13500
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 5.269028186798096,
+      "learning_rate": 6.640900849317683e-05,
+      "loss": 0.1336,
+      "mean_token_accuracy": 0.9619411797523498,
+      "num_tokens": 10338731.0,
+      "step": 14000
+    },
+    {
+      "epoch": 1.3837198205935681,
+      "grad_norm": 0.000423251127358526,
+      "learning_rate": 6.163756083595764e-05,
+      "loss": 0.1386,
+      "mean_token_accuracy": 0.9611272529363633,
+      "num_tokens": 10724381.0,
+      "step": 14500
+    },
+    {
+      "epoch": 1.43143429716576,
+      "grad_norm": 0.754705548286438,
+      "learning_rate": 5.6866113178738436e-05,
+      "loss": 0.1182,
+      "mean_token_accuracy": 0.9661157331466674,
+      "num_tokens": 11094900.0,
+      "step": 15000
+    },
+    {
+      "epoch": 1.479148773737952,
+      "grad_norm": 0.0017857268685474992,
+      "learning_rate": 5.2094665521519235e-05,
+      "loss": 0.1175,
+      "mean_token_accuracy": 0.9679548003673554,
+      "num_tokens": 11454717.0,
+      "step": 15500
+    },
+    {
+      "epoch": 1.5268632503101442,
+      "grad_norm": 3.5908143520355225,
+      "learning_rate": 4.732321786430003e-05,
+      "loss": 0.11,
+      "mean_token_accuracy": 0.9671754879951477,
+      "num_tokens": 11832591.0,
+      "step": 16000
+    },
+    {
+      "epoch": 1.5745777268823362,
+      "grad_norm": 0.010208655148744583,
+      "learning_rate": 4.255177020708083e-05,
+      "loss": 0.115,
+      "mean_token_accuracy": 0.9662747744321823,
+      "num_tokens": 12223203.0,
+      "step": 16500
+    },
+    {
+      "epoch": 1.6222922034545282,
+      "grad_norm": 0.002450750907883048,
+      "learning_rate": 3.778032254986163e-05,
+      "loss": 0.1112,
+      "mean_token_accuracy": 0.9668832242488861,
+      "num_tokens": 12593144.0,
+      "step": 17000
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.004513042513281107,
+      "learning_rate": 3.300887489264243e-05,
+      "loss": 0.1004,
+      "mean_token_accuracy": 0.9708232057094573,
+      "num_tokens": 12954505.0,
+      "step": 17500
+    },
+    {
+      "epoch": 1.7177211565989121,
+      "grad_norm": 0.007037173956632614,
+      "learning_rate": 2.8237427235423232e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.9671108702421188,
+      "num_tokens": 13307858.0,
+      "step": 18000
+    },
+    {
+      "epoch": 1.765435633171104,
+      "grad_norm": 0.015288141556084156,
+      "learning_rate": 2.3465979578204027e-05,
+      "loss": 0.1034,
+      "mean_token_accuracy": 0.9698293421268463,
+      "num_tokens": 13673816.0,
+      "step": 18500
+    },
+    {
+      "epoch": 1.813150109743296,
+      "grad_norm": 6.889008045196533,
+      "learning_rate": 1.869453192098483e-05,
+      "loss": 0.0977,
+      "mean_token_accuracy": 0.9710470995903016,
+      "num_tokens": 14038630.0,
+      "step": 19000
+    },
+    {
+      "epoch": 1.860864586315488,
+      "grad_norm": 2.6273930072784424,
+      "learning_rate": 1.3923084263765626e-05,
+      "loss": 0.0936,
+      "mean_token_accuracy": 0.9728796405792236,
+      "num_tokens": 14401139.0,
+      "step": 19500
+    },
+    {
+      "epoch": 1.90857906288768,
+      "grad_norm": 0.004859536420553923,
+      "learning_rate": 9.151636606546427e-06,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.9708857105970383,
+      "num_tokens": 14770982.0,
+      "step": 20000
+    },
+    {
+      "epoch": 1.9562935394598722,
+      "grad_norm": 0.4923778176307678,
+      "learning_rate": 4.380188949327226e-06,
+      "loss": 0.0963,
+      "mean_token_accuracy": 0.9713275592327117,
+      "num_tokens": 15136348.0,
+      "step": 20500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20958,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.399363404153889e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa47ddc719ecb3b675964f22519fd406d4261951c3c54a16f54cc2873eb4563
+size 6328