Training in progress, step 100

.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 +1,58 @@
+---
+base_model: google/paligemma2-3b-pt-448
+library_name: transformers
+model_name: paligemma2-3b-pt-448-od-grounding
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for paligemma2-3b-pt-448-od-grounding
+
+This model is a fine-tuned version of [google/paligemma2-3b-pt-448](https://huggingface.co/google/paligemma2-3b-pt-448).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="sergiopaniego/paligemma2-3b-pt-448-od-grounding", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma2-3b-pt-448",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a17873d54cbd182513aee074dfb6dc573d29af07898236377c9ac29ed4c0290
+size 10404232

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752675656.30e61f6d0ff7.852.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69281b5416fef7407466d0e56dc30e3379186fa916dc8d32f483e71368a125a
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752675784.30e61f6d0ff7.852.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb276dbd15ac85296f753b0758173e3e2d218004a58a1c6daf6def535ab0e77b
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752675837.30e61f6d0ff7.852.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3eebdd43f6c7ed4d8b15b6cae44162d7de6ea5547a92371c1786fc7bad1cd50
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752675869.30e61f6d0ff7.852.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa5b0ea2c3b12a642d8a94866b6df73c82673a639dff19b5b0b734320a17a4d
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752675971.30e61f6d0ff7.852.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c265f7ce3bb6683c3ff1bb660a1fec621c296028af647855e0ae401d316c678
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752676037.30e61f6d0ff7.852.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2917b1bfb325d83c3dc24d25f2dc877194b7bd3b588bd223edff0150ce6d95e7
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752676089.30e61f6d0ff7.852.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901b7ff4a8bee949f94f75ffce3608fdb2e4c228503cb179998733e85aa0a0ad
+size 7300

runs/Jul16_14-20-42_30e61f6d0ff7/events.out.tfevents.1752676121.30e61f6d0ff7.852.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8af92586e407102af92097d3f8a975c5896cd3074d03893a0c57d5264a1431e
+size 20344

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
+size 34600820

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acfa0a73066c063efc5eb8740f19518c786856994753ecdaf6ccaf69420e822
+size 5816