Training in progress, step 16

config.json

@@ -1,28 +1,25 @@
 {
-  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "_name_or_path": "bobox/DeBERTa-small-ST-v1-test-step3",
   "architectures": [
     "DebertaV2Model"
   ],
-  "attention_head_size": 64,
   "attention_probs_dropout_prob": 0.1,
-  "conv_act": "gelu",
-  "conv_kernel_size": 3,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1536,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 6144,
+  "intermediate_size": 3072,
   "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": 24,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1536,
+  "pooler_hidden_size": 768,
   "pos_att_type": [
     "p2c",
     "c2p"
@@ -32,7 +29,7 @@
   "relative_attention": true,
   "share_att_key": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.44.0",
   "type_vocab_size": 0,
   "vocab_size": 128100
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffd269ba843cb2691787930ee8d15318edc2ab028c0f96d2555b728e68e0608
-size 3538506546
+oid sha256:1886a286545822d70cd17732b6025a52902e7429a8ab7eec28bf9c1a4f143b6c
+size 565251810

runs/Sep05_19-50-22_a781e0904d2b/events.out.tfevents.1725565837.a781e0904d2b.84.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa4a4fa676ccc6541ecb8449bb0e4e6c4bcb8ab61788511adc656299e8a7f8b
+size 27668

special_tokens_map.json

@@ -1,10 +1,46 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

spm.model

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

tokenizer_config.json

@@ -47,12 +47,19 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "split_by_punct": false,
+  "stride": 0,
   "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]",
   "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b62473318b3b28c705f94b87acfb0646732bae15a12e95a938b998dc89c2e7
-size 5560
+oid sha256:00d891109b3776bbe6fe5299eaca62fc99db8369e44011108f84f516eaa2f0e0
+size 5624