End of training

.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 +1,109 @@
+---
+library_name: transformers
+license: gemma
+base_model: google/embeddinggemma-300m
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: universal_classifier
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# universal_classifier
+
+This model is a fine-tuned version of [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1127
+- Accuracy: 0.685
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 22500
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| 0.3060        | 0.0132 | 500   | 0.2985          | 0.175    |
+| 0.2972        | 0.0264 | 1000  | 0.2958          | 0.192    |
+| 0.2889        | 0.0396 | 1500  | 0.2951          | 0.193    |
+| 0.2827        | 0.0527 | 2000  | 0.2945          | 0.216    |
+| 0.2961        | 0.0659 | 2500  | 0.2883          | 0.208    |
+| 0.2520        | 0.0791 | 3000  | 0.2509          | 0.359    |
+| 0.2181        | 0.0923 | 3500  | 0.2166          | 0.449    |
+| 0.1710        | 0.1055 | 4000  | 0.1697          | 0.561    |
+| 0.1655        | 0.1187 | 4500  | 0.1563          | 0.588    |
+| 0.1344        | 0.1319 | 5000  | 0.1433          | 0.607    |
+| 0.1416        | 0.1451 | 5500  | 0.1378          | 0.631    |
+| 0.1347        | 0.1582 | 6000  | 0.1369          | 0.609    |
+| 0.1250        | 0.1714 | 6500  | 0.1358          | 0.63     |
+| 0.1560        | 0.1846 | 7000  | 0.1332          | 0.638    |
+| 0.1368        | 0.1978 | 7500  | 0.1322          | 0.648    |
+| 0.1275        | 0.2110 | 8000  | 0.1331          | 0.649    |
+| 0.1257        | 0.2242 | 8500  | 0.1297          | 0.654    |
+| 0.1349        | 0.2374 | 9000  | 0.1288          | 0.657    |
+| 0.1306        | 0.2506 | 9500  | 0.1262          | 0.655    |
+| 0.1161        | 0.2637 | 10000 | 0.1243          | 0.652    |
+| 0.1315        | 0.2769 | 10500 | 0.1249          | 0.666    |
+| 0.1298        | 0.2901 | 11000 | 0.1245          | 0.659    |
+| 0.1141        | 0.3033 | 11500 | 0.1221          | 0.664    |
+| 0.1216        | 0.3165 | 12000 | 0.1205          | 0.668    |
+| 0.1216        | 0.3297 | 12500 | 0.1204          | 0.67     |
+| 0.1211        | 0.3429 | 13000 | 0.1214          | 0.671    |
+| 0.1179        | 0.3561 | 13500 | 0.1204          | 0.666    |
+| 0.1246        | 0.3692 | 14000 | 0.1176          | 0.67     |
+| 0.1132        | 0.3824 | 14500 | 0.1170          | 0.669    |
+| 0.1190        | 0.3956 | 15000 | 0.1177          | 0.672    |
+| 0.1075        | 0.4088 | 15500 | 0.1173          | 0.688    |
+| 0.1177        | 0.4220 | 16000 | 0.1140          | 0.683    |
+| 0.0958        | 0.4352 | 16500 | 0.1150          | 0.678    |
+| 0.1247        | 0.4484 | 17000 | 0.1147          | 0.676    |
+| 0.1059        | 0.4615 | 17500 | 0.1138          | 0.687    |
+| 0.1058        | 0.4747 | 18000 | 0.1144          | 0.681    |
+| 0.1070        | 0.4879 | 18500 | 0.1146          | 0.69     |
+| 0.1166        | 0.5011 | 19000 | 0.1134          | 0.691    |
+| 0.1139        | 0.5143 | 19500 | 0.1128          | 0.684    |
+| 0.1104        | 0.5275 | 20000 | 0.1139          | 0.685    |
+| 0.1080        | 0.5407 | 20500 | 0.1144          | 0.677    |
+| 0.1145        | 0.5539 | 21000 | 0.1128          | 0.698    |
+| 0.1246        | 0.5670 | 21500 | 0.1126          | 0.688    |
+| 0.1258        | 0.5802 | 22000 | 0.1128          | 0.679    |
+| 0.1089        | 0.5934 | 22500 | 0.1127          | 0.685    |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 5.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/embeddinggemma-300m",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_bdlora": 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:f40aa8a853d442962362d5a13df0a1dc3b608ad68c07d39322beeda59f45c646
+size 2040088

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bd63e9d6f89918fa602e3920ee20ee352d0a193e114fafd24aa5f934c7abe0
+size 33384981

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99b2c24952cf83e4634b220b84e9d6e8d739c1ddfa5a0bbca6bac30a3200fbe
+size 5137