Upload 8 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: google/paligemma-3b-pt-448
+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 0.13.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-pt-448",
+  "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": [
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_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:bb52587d63b01acaad31055854f315a6d8554243741c441151176f3f18fef781
+size 45258384

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea5edd313f41177e252fd9321c90f40b23653a8489e7d77d73d9b2396fbcbbb
+size 90635706

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeef384dca819c9b44bc575058a43da9e90e28ca7bdc6079aaf024944abda117
+size 1064

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 51.06103515625,
+      "learning_rate": 1.869158878504673e-05,
+      "loss": 1.1397,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 29.371679306030273,
+      "learning_rate": 1.7356475300400533e-05,
+      "loss": 0.6966,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 37.94963455200195,
+      "learning_rate": 1.602136181575434e-05,
+      "loss": 0.4605,
+      "step": 300
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.42650002241134644,
+      "learning_rate": 1.4686248331108147e-05,
+      "loss": 0.5428,
+      "step": 400
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 202.76437377929688,
+      "learning_rate": 1.335113484646195e-05,
+      "loss": 0.4785,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.011508260853588581,
+      "learning_rate": 1.2016021361815755e-05,
+      "loss": 0.3989,
+      "step": 600
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 6.5181193351745605,
+      "learning_rate": 1.068090787716956e-05,
+      "loss": 0.5321,
+      "step": 700
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 30.055387496948242,
+      "learning_rate": 9.345794392523365e-06,
+      "loss": 0.4692,
+      "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 172.0653533935547,
+      "learning_rate": 8.01068090787717e-06,
+      "loss": 0.4043,
+      "step": 900
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.040170542895793915,
+      "learning_rate": 6.675567423230975e-06,
+      "loss": 0.3241,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 201.94967651367188,
+      "learning_rate": 5.34045393858478e-06,
+      "loss": 0.3917,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.024023059755563736,
+      "learning_rate": 4.005340453938585e-06,
+      "loss": 0.2185,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.1882331371307373,
+      "learning_rate": 2.67022696929239e-06,
+      "loss": 0.4324,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.01553017646074295,
+      "learning_rate": 1.335113484646195e-06,
+      "loss": 0.2871,
+      "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 471.4150085449219,
+      "learning_rate": 0.0,
+      "loss": 0.3236,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.971060451616e+16,
+  "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 sha256:591762aad8049f2f4bc16d33346dd301bcdffa3a31293091128253ccd834aa57
+size 5304