Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/paligemma-3b-pt-224
+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 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "google/paligemma-3b-pt-224",
+ "bias": "none",
+ "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_dropout": 0.0,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "k_proj",
+ "q_proj",
+ "o_proj",
+ "up_proj",
+ "down_proj",
+ "gate_proj",
+ "v_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4622340240de75c10de60d3f786ae0d18d3f259a83f35cc5c0e42a3be50b9d4b
+size 45258384

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f256f47f9e561d5d7f0f8a667b06ddb686e9725e44abe6e998d5798a55d89df
+size 90635706

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b6cfff436e44ce1aac34c0deddcf1312e002c1c8fac244f4391c78862bccf7
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717b9150f99fb702ddcc322d110c42ec383e2b4d73214564a59033dfedcb3d61
+size 1064

trainer_state.json

@@ -0,0 +1,243 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.3710729104919976,
+ "eval_steps": 500,
+ "global_step": 3000,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.07903576368306658,
+ "grad_norm": 2.3245134353637695,
+ "learning_rate": 1.948325863432639e-05,
+ "loss": 2.9096,
+ "step": 100
+ },
+ {
+ "epoch": 0.15807152736613317,
+ "grad_norm": 2.990708112716675,
+ "learning_rate": 1.8955971526496178e-05,
+ "loss": 0.7375,
+ "step": 200
+ },
+ {
+ "epoch": 0.23710729104919975,
+ "grad_norm": 2.713043451309204,
+ "learning_rate": 1.8428684418665965e-05,
+ "loss": 0.4412,
+ "step": 300
+ },
+ {
+ "epoch": 0.31614305473226634,
+ "grad_norm": 2.839672088623047,
+ "learning_rate": 1.790139731083575e-05,
+ "loss": 0.3861,
+ "step": 400
+ },
+ {
+ "epoch": 0.3951788184153329,
+ "grad_norm": 2.5622401237487793,
+ "learning_rate": 1.7374110203005538e-05,
+ "loss": 0.3694,
+ "step": 500
+ },
+ {
+ "epoch": 0.4742145820983995,
+ "grad_norm": 2.527787923812866,
+ "learning_rate": 1.6846823095175325e-05,
+ "loss": 0.3538,
+ "step": 600
+ },
+ {
+ "epoch": 0.5532503457814661,
+ "grad_norm": 2.7099175453186035,
+ "learning_rate": 1.631953598734511e-05,
+ "loss": 0.3478,
+ "step": 700
+ },
+ {
+ "epoch": 0.6322861094645327,
+ "grad_norm": 2.159538745880127,
+ "learning_rate": 1.5792248879514898e-05,
+ "loss": 0.338,
+ "step": 800
+ },
+ {
+ "epoch": 0.7113218731475993,
+ "grad_norm": 2.3641576766967773,
+ "learning_rate": 1.5264961771684685e-05,
+ "loss": 0.3423,
+ "step": 900
+ },
+ {
+ "epoch": 0.7903576368306658,
+ "grad_norm": 2.5248115062713623,
+ "learning_rate": 1.4737674663854471e-05,
+ "loss": 0.3244,
+ "step": 1000
+ },
+ {
+ "epoch": 0.8693934005137325,
+ "grad_norm": 2.2045676708221436,
+ "learning_rate": 1.4210387556024256e-05,
+ "loss": 0.3215,
+ "step": 1100
+ },
+ {
+ "epoch": 0.948429164196799,
+ "grad_norm": 2.5387887954711914,
+ "learning_rate": 1.3683100448194043e-05,
+ "loss": 0.3239,
+ "step": 1200
+ },
+ {
+ "epoch": 1.0274649278798655,
+ "grad_norm": 2.1010782718658447,
+ "learning_rate": 1.315581334036383e-05,
+ "loss": 0.316,
+ "step": 1300
+ },
+ {
+ "epoch": 1.1065006915629323,
+ "grad_norm": 2.8399364948272705,
+ "learning_rate": 1.2628526232533616e-05,
+ "loss": 0.3143,
+ "step": 1400
+ },
+ {
+ "epoch": 1.1855364552459988,
+ "grad_norm": 2.4526548385620117,
+ "learning_rate": 1.2101239124703401e-05,
+ "loss": 0.3076,
+ "step": 1500
+ },
+ {
+ "epoch": 1.2645722189290654,
+ "grad_norm": 2.1812686920166016,
+ "learning_rate": 1.157395201687319e-05,
+ "loss": 0.3074,
+ "step": 1600
+ },
+ {
+ "epoch": 1.343607982612132,
+ "grad_norm": 2.12322735786438,
+ "learning_rate": 1.1046664909042974e-05,
+ "loss": 0.3019,
+ "step": 1700
+ },
+ {
+ "epoch": 1.4226437462951986,
+ "grad_norm": 2.5394980907440186,
+ "learning_rate": 1.0519377801212763e-05,
+ "loss": 0.3114,
+ "step": 1800
+ },
+ {
+ "epoch": 1.5016795099782652,
+ "grad_norm": 2.698906660079956,
+ "learning_rate": 9.992090693382548e-06,
+ "loss": 0.302,
+ "step": 1900
+ },
+ {
+ "epoch": 1.580715273661332,
+ "grad_norm": 2.7786617279052734,
+ "learning_rate": 9.464803585552334e-06,
+ "loss": 0.2995,
+ "step": 2000
+ },
+ {
+ "epoch": 1.6597510373443982,
+ "grad_norm": 2.2823212146759033,
+ "learning_rate": 8.937516477722121e-06,
+ "loss": 0.3117,
+ "step": 2100
+ },
+ {
+ "epoch": 1.738786801027465,
+ "grad_norm": 2.129678726196289,
+ "learning_rate": 8.410229369891908e-06,
+ "loss": 0.3045,
+ "step": 2200
+ },
+ {
+ "epoch": 1.8178225647105315,
+ "grad_norm": 1.627656102180481,
+ "learning_rate": 7.882942262061694e-06,
+ "loss": 0.297,
+ "step": 2300
+ },
+ {
+ "epoch": 1.896858328393598,
+ "grad_norm": 1.6226264238357544,
+ "learning_rate": 7.355655154231479e-06,
+ "loss": 0.2987,
+ "step": 2400
+ },
+ {
+ "epoch": 1.9758940920766648,
+ "grad_norm": 1.6640758514404297,
+ "learning_rate": 6.828368046401266e-06,
+ "loss": 0.3022,
+ "step": 2500
+ },
+ {
+ "epoch": 2.054929855759731,
+ "grad_norm": 2.3779549598693848,
+ "learning_rate": 6.3010809385710525e-06,
+ "loss": 0.2985,
+ "step": 2600
+ },
+ {
+ "epoch": 2.133965619442798,
+ "grad_norm": 2.0160937309265137,
+ "learning_rate": 5.773793830740839e-06,
+ "loss": 0.2986,
+ "step": 2700
+ },
+ {
+ "epoch": 2.2130013831258646,
+ "grad_norm": 2.8362996578216553,
+ "learning_rate": 5.246506722910625e-06,
+ "loss": 0.2997,
+ "step": 2800
+ },
+ {
+ "epoch": 2.292037146808931,
+ "grad_norm": 1.8160929679870605,
+ "learning_rate": 4.7192196150804116e-06,
+ "loss": 0.2847,
+ "step": 2900
+ },
+ {
+ "epoch": 2.3710729104919976,
+ "grad_norm": 1.660947322845459,
+ "learning_rate": 4.191932507250198e-06,
+ "loss": 0.2913,
+ "step": 3000
+ }
+ ],
+ "logging_steps": 100,
+ "max_steps": 3795,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 1000,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 1.9485385996265165e+17,
+ "train_batch_size": 4,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5fba07a48b50f3385997befe0f078044ee6c7c97fc3570e3941bd64611d09f
+size 5048