Training in progress, epoch 1

config.json

@@ -1,43 +1,34 @@
 {
-  "_name_or_path": "microsoft/mdeberta-v3-base",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "0",
     "1": "1"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "0": "0",
     "1": "1"
   },
-  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.24.0.dev0",
-  "type_vocab_size": 0,
-  "vocab_size": 251000
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8471a9e6719f741d86186005c6f594947e101e22ac064cce6f289bff09d2d5a5
-size 1115315755
+oid sha256:4b6bf6bca8884d129db65a1a0db0f9150846b8cd43db8c7c3db05c20665b6f24
+size 541339121

runs/Dec19_23-12-21_teesta/events.out.tfevents.1671473691.teesta.2078.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8503a6984f7d2eec39d0d17cb13229249d25f23c812a4d95c8e01e0970dae5f
+size 512

runs/Dec21_18-56-11_teesta/1671629182.092958/events.out.tfevents.1671629182.teesta.16256.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267da261893291b8928af9af38f56832d8d37425b536cde86f4b29dabeb3f1a4
+size 5471

runs/Dec21_18-56-11_teesta/events.out.tfevents.1671629182.teesta.16256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68fed457d040af7ad6c0fb74a9803be11603bf18ce947478df757a3802e79e9b
+size 4196

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b128f3eb3c16ebe674b34492da141a26ed841f594763465ade051b15d71650c
-size 16331456
+oid sha256:a4a4fa4b10a2a40361529954532f10257fda53cb22177554a862bcc661b7e4d8
+size 2919615

tokenizer_config.json

@@ -1,16 +1,14 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
   "do_lower_case": false,
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "name_or_path": "microsoft/mdeberta-v3-base",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-multilingual-cased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5719e58318244555db48767abed63b2448d6eefe80ec1db64c2ae0f9bbdb06f
+oid sha256:f81633a5880f247c7c04777ce9b5da37285a60d0b20cec19f8233da1107ad0af
 size 3375