Training in progress, epoch 1

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -20,18 +19,22 @@
     "0": "0",
     "1": "1"
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.24.0.dev0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd495dfcd9961992e3a318e7d6b488d223837fed8c91c92365293f8f58041993
-size 1112252397
+oid sha256:093ad3693fbad28ed0c5de13ab8ae0c014d5e67ba93339065561ca605e12598c
+size 711490925

runs/Dec16_02-27-01_teesta/events.out.tfevents.1671139819.teesta.25294.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9bf2d99cdfb6ed69feeaf8ddb7f5feb7ad010257ca66987c56da89632d8d58
+size 512

runs/Dec19_13-09-01_teesta/1671435561.2460308/events.out.tfevents.1671435561.teesta.39359.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8dc6d174dd83e6f9b90e2d7d2566a86a051257762cb329712de1b92e37fcee2
+size 5517

runs/Dec19_13-09-01_teesta/events.out.tfevents.1671435561.teesta.39359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2134b1f37049cebab568ec7b90aade942fa3718bce1069d006f111e25c803da
+size 4486

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
-size 17082913
+oid sha256:a4a4fa4b10a2a40361529954532f10257fda53cb22177554a862bcc661b7e4d8
+size 2919615

tokenizer_config.json

@@ -1,20 +1,14 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "xlm-roberta-base",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "name_or_path": "bert-base-multilingual-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29bcbdcd76f49b655e8222d347fb0fa12a3102288025770cc9cb5dac646761c8
+oid sha256:0dcb2e801d3fa3ebd7b38b374fa2e95fc8b8370bee05fa824cf044d38f8402f0
 size 3439