End of training

README.md

@@ -1,10 +1,8 @@
 ---
 license: mit
-base_model: xlm-roberta-base
+base_model: ai4bharat/indic-bert
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: xmlRoBert-Balanced-trimmed-10epoch-Trainer
   results: []
@@ -15,10 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xmlRoBert-Balanced-trimmed-10epoch-Trainer
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.1137
-- Accuracy: 0.3125
+This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on the None dataset.
 
 ## Model description
 
@@ -43,27 +38,11 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 3    | 1.1523          | 0.25     |
-| No log        | 2.0   | 6    | 1.1465          | 0.25     |
-| No log        | 3.0   | 9    | 1.1425          | 0.25     |
-| No log        | 4.0   | 12   | 1.1316          | 0.25     |
-| No log        | 5.0   | 15   | 1.1158          | 0.25     |
-| No log        | 6.0   | 18   | 1.1335          | 0.375    |
-| No log        | 7.0   | 21   | 1.1214          | 0.25     |
-| No log        | 8.0   | 24   | 1.1198          | 0.25     |
-| No log        | 9.0   | 27   | 1.1155          | 0.25     |
-| No log        | 10.0  | 30   | 1.1137          | 0.3125   |
-
+- num_epochs: 5
 
 ### Framework versions
 
-- Transformers 4.35.0.dev0
-- Pytorch 1.13.1
-- Datasets 2.14.5
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.0+cpu
+- Datasets 2.1.0
 - Tokenizers 0.14.1

config.json

@@ -1,14 +1,17 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "ai4bharat/indic-bert",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0,
   "hidden_size": 768,
   "id2label": {
     "NEGATIVE": 0,
@@ -16,24 +19,25 @@
     "POSITIVE": 2
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 0,
     "NEUTRAL": 1,
     "POSITIVE": 2
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
+  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "type_vocab_size": 2,
+  "vocab_size": 200000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94fcf39dfb8790c5a4ba36b0539a2bb0c0894d16c023977a56798edea54c317
-size 1112208084
+oid sha256:a38d9953ed54e42eb123ddfecdc3bdc809458c73467d3958967d39fcd085b52e
+size 133787028

runs/Nov10_09-14-20_333d65de2404/events.out.tfevents.1699607741.333d65de2404.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce40e4aef56d3b148e414c385b31aaaca85c41e613543b1536c7f0bb121a26b5
+size 16472

special_tokens_map.json

@@ -1,15 +1,15 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": {
-    "content": "<mask>",
+    "content": "[MASK]",
     "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "sep_token": "[SEP]",
   "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
+size 5646064

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19232daba569c004c5fbe45f373ccaf2ee505055da00969f78a99e5754db8f25
-size 17082688
+oid sha256:1380ca9cde3e5552469ae7f5c6b897faa4e96bfd39bd8a64ac5b4d05c5add12f
+size 15285634

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,15 +25,15 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
+    "4": {
+      "content": "[MASK]",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
@@ -41,14 +41,18 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27cbcbbbe103d364ac1090f87182eb08009b179d2eb9e7f05950f90890bec60b
+oid sha256:832259a41a810d865aae7dd7688c981b631459a53af6dc9fe7e9c90128c8e4af
 size 4219