Training in progress, epoch 1

config.json

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8fbb2f9e5089fde5d9393eccc688445c4847b97d52d7c22f86fdf73aec353a9
-size 711490925
+oid sha256:ffeb26053f202b122a78e3be4f876c0fb3a31beb5b11e0348a01b644fab4bb21
+size 1112252397

runs/Dec20_04-59-33_teesta/1671492955.5688202/events.out.tfevents.1671492955.teesta.20706.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1d24bba8fa5f40a9c6466d36fbb5a27cd7acd84f6449d52d6a3d4420e4b6ee
+size 5481

runs/Dec20_04-59-33_teesta/events.out.tfevents.1671492955.teesta.20706.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed9ded6d67e53d146695d6c7964693299c938b368f5fb7012380c7e9f41c79f
+size 4324

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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>"
 }

tokenizer.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dcb2e801d3fa3ebd7b38b374fa2e95fc8b8370bee05fa824cf044d38f8402f0
-size 3439
+oid sha256:f67725155e08741199a8e6f6d7bd586751e5ea8f166dde7d2db38c3adef4d7ec
+size 3375