rkoh

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: knowledgator/gliclass-large-v1.0
+base_model: knowledgator/gliclass-small-v1.0
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [knowledgator/gliclass-large-v1.0](https://huggingface.co/knowledgator/gliclass-large-v1.0) on an unknown dataset.
+This model is a fine-tuned version of [knowledgator/gliclass-small-v1.0](https://huggingface.co/knowledgator/gliclass-small-v1.0) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0
 
@@ -36,25 +36,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1308        | 1.0   | 55   | 0.2450          |
-| 0.0           | 2.0   | 110  | 0.0001          |
-| 0.0001        | 3.0   | 165  | 0.0             |
+| 0.967         | 1.0   | 14   | 0.0061          |
+| 0.1299        | 2.0   | 28   | 0.0000          |
+| 0.0213        | 3.0   | 42   | 0.0000          |
+| 0.1641        | 4.0   | 56   | 0.0000          |
+| 0.0434        | 5.0   | 70   | 0.0             |
+| 0.066         | 6.0   | 84   | 0.0000          |
+| 0.061         | 7.0   | 98   | 0.0000          |
+| 0.0265        | 8.0   | 112  | 0.0             |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.5.0+cu121
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
 - Datasets 3.1.0
-- Tokenizers 0.19.1
+- Tokenizers 0.20.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "knowledgator/gliclass-large-v1.0",
+  "_name_or_path": "knowledgator/gliclass-small-v1.0",
   "architecture_type": "uni-encoder",
   "architectures": [
     "GLiClassModel"
@@ -8,7 +8,7 @@
   "contrastive_loss_coef": 0,
   "embed_class_token": true,
   "encoder_config": {
-    "_name_or_path": "microsoft/deberta-v3-large",
+    "_name_or_path": "microsoft/deberta-v3-small",
     "add_cross_attention": false,
     "architectures": null,
     "attention_probs_dropout_prob": 0.1,
@@ -29,13 +29,13 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
-    "hidden_size": 1024,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
+    "intermediate_size": 3072,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -51,10 +51,10 @@
     "model_type": "deberta-v2",
     "no_repeat_ngram_size": 0,
     "norm_rel_ebd": "layer_norm",
-    "num_attention_heads": 16,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 24,
+    "num_hidden_layers": 6,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -62,7 +62,7 @@
     "pad_token_id": 0,
     "pooler_dropout": 0,
     "pooler_hidden_act": "gelu",
-    "pooler_hidden_size": 1024,
+    "pooler_hidden_size": 768,
     "pos_att_type": [
       "p2c",
       "c2p"
@@ -95,11 +95,11 @@
     "use_bfloat16": false,
     "vocab_size": 128003
   },
-  "encoder_model_name": "microsoft/deberta-v3-large",
+  "encoder_model_name": "microsoft/deberta-v3-small",
   "extract_text_features": false,
   "focal_loss_alpha": -1,
   "focal_loss_gamma": -1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "ignore_index": -100,
   "initializer_range": 0.03,
   "logit_scale_init_value": 2.6592,
@@ -113,7 +113,7 @@
   "squeeze_layers": false,
   "text_token_index": 128004,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.45.2",
   "use_lstm": false,
   "vocab_size": 128003
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0148bfefc5c4190f9f39cdec229daeb58c9500b8ee2a01db70e4c44e2550e22f
-size 1752499444
+oid sha256:3ee7dbf14d73a842029c53d4b1b97844a763a62a81f5dc4469a5d920be2f2d8c
+size 574383356

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43be2d5484608363df5690505ab8d988e85530a9f6ba9a7191023a2c5beed9e
+oid sha256:7d82a94ab66401fecc01c7fa5a9074444bc244a8c7a4a392703cd4a84c172212
 size 5240