jagadeesr/ms-deberta-v3-small-rvl-cdip

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # text_classifier
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5131
-- Accuracy: 0.6982
+- Loss: 3.2472
+- Accuracy: 0.6158
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,28 +47,28 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 96   | 1.2437          | 0.6404   |
-| No log        | 2.0   | 192  | 1.0802          | 0.6798   |
-| No log        | 3.0   | 288  | 1.0126          | 0.6772   |
-| No log        | 4.0   | 384  | 1.0858          | 0.6745   |
-| No log        | 5.0   | 480  | 1.2306          | 0.6850   |
-| 0.7338        | 6.0   | 576  | 1.3097          | 0.6824   |
-| 0.7338        | 7.0   | 672  | 1.3371          | 0.6850   |
-| 0.7338        | 8.0   | 768  | 1.4222          | 0.7034   |
-| 0.7338        | 9.0   | 864  | 1.3962          | 0.7060   |
-| 0.7338        | 10.0  | 960  | 1.4529          | 0.6955   |
-| 0.0955        | 11.0  | 1056 | 1.4697          | 0.6955   |
-| 0.0955        | 12.0  | 1152 | 1.4944          | 0.7008   |
-| 0.0955        | 13.0  | 1248 | 1.5037          | 0.6982   |
-| 0.0955        | 14.0  | 1344 | 1.5129          | 0.7008   |
-| 0.0955        | 15.0  | 1440 | 1.5131          | 0.6982   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.4863        | 1.0   | 760   | 2.0973          | 0.2474   |
+| 1.8132        | 2.0   | 1520  | 1.7995          | 0.4237   |
+| 1.5143        | 3.0   | 2280  | 1.5842          | 0.5053   |
+| 1.3095        | 4.0   | 3040  | 1.8946          | 0.5553   |
+| 1.0743        | 5.0   | 3800  | 1.9189          | 0.5684   |
+| 0.9554        | 6.0   | 4560  | 2.1748          | 0.5974   |
+| 0.7778        | 7.0   | 5320  | 2.2701          | 0.6263   |
+| 0.5849        | 8.0   | 6080  | 2.5282          | 0.6237   |
+| 0.5472        | 9.0   | 6840  | 2.7330          | 0.6184   |
+| 0.4232        | 10.0  | 7600  | 2.9518          | 0.6079   |
+| 0.2858        | 11.0  | 8360  | 2.8892          | 0.6263   |
+| 0.2908        | 12.0  | 9120  | 3.0251          | 0.6289   |
+| 0.2391        | 13.0  | 9880  | 3.1414          | 0.6211   |
+| 0.1569        | 14.0  | 10640 | 3.2581          | 0.6184   |
+| 0.1405        | 15.0  | 11400 | 3.2472          | 0.6158   |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.36.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.15.0
 - Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "microsoft/deberta-v3-small",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "presentation",
     "1": "budget",
@@ -27,6 +26,7 @@
     "15": "advertisement"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "advertisement": 15,
     "budget": 1,
@@ -45,17 +45,27 @@
     "scientific report": 13,
     "specification": 9
   },
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
-  "vocab_size": 30522
+  "transformers_version": "4.36.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9798b95964b34ce705758aa9d808d1a9d6ad878513545ed667eccb2a148ee770
-size 267875632
+oid sha256:4c856baa9ad988689a21395fa6b423bc53f1f7b51073906ba90a08de2e7515c4
+size 567641624

runs/Dec13_22-46-36_48edafdfd1b1/events.out.tfevents.1702507617.48edafdfd1b1.4828.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de101ccb57fc12d2bb6cba6a2b6dde8146b077223628014a6575256d857e75f2
+size 4184

runs/Dec13_22-50-04_48edafdfd1b1/events.out.tfevents.1702507810.48edafdfd1b1.7253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335d0483dc2eb7569b19cee56f982391bc7eeec302f65b347b3881f532bb6501
+size 4184

runs/Dec13_22-52-06_48edafdfd1b1/events.out.tfevents.1702507938.48edafdfd1b1.8113.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d91705b3b26947a54b585cdcad5610cc6543d8b01d569cbe0d483d33fa94449
+size 5252

runs/Dec13_22-53-57_48edafdfd1b1/events.out.tfevents.1702508046.48edafdfd1b1.8726.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc22c635c18f383c966803a76828385b847fe668d7834f25f21619b10dc60e4
+size 13905

special_tokens_map.json

@@ -1,36 +1,14 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
+    "128000": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,19 +41,18 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "max_length": 512,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a81ba304876357ec35fcf77fa9e192b2d6493d49088556e2633fd3c2548f0f
-size 4600
+oid sha256:93d5ba6c460dbbe882331b09954dde125a68be2139f12502e0469c70d79957f8
+size 4728