Training in progress, step 200

config.json

@@ -1,19 +1,22 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-base",
+  "_name_or_path": "microsoft/deberta-v2-xlarge",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],
+  "attention_head_size": 64,
   "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
   "finetuning_task": "sst2",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1536,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 6144,
   "label2id": {
     "negative": 0,
     "positive": 1
@@ -23,12 +26,12 @@
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
+  "pooler_hidden_size": 1536,
   "pos_att_type": [
     "p2c",
     "c2p"

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14952260e90cb60a5a2bbc17ea5e3e63bd5fbb2ef33e87096ceb8996bbc9cda6
-size 328099
+oid sha256:c54ad564b9167ad385f2cc4307375f75cc6dae21d1d7a16a6b75d266eb5a9176
+size 655267

runs/Feb04_19-00-22_node1/1643972597.5023751/events.out.tfevents.1643972597.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7679cb790ceb34ff00b42bf6badcf64b3716e0100ff8c25a5a9dd59dc3df09c
+size 4618

runs/Feb04_19-00-22_node1/events.out.tfevents.1643972597.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91fbc73f9a10f3cba08ce8de27e5089dc9d62df3680a06e8285f11e5bee2c5e
+size 3722

spm.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
-size 2464616
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-base", "tokenizer_class": "DebertaV2Tokenizer"}
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v2-xlarge", "tokenizer_class": "DebertaV2Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef24b92e1d629a9a55b8090e1457574b45ee1a92b7b4e91bff36ffc9bba8616d
+oid sha256:8b3aa7ed983096a7c7d3f893b3a37e59c62769bcbc264c3020d64afe3f7fc05c
 size 2991