Training in progress, step 200

config.json

@@ -1,47 +1,37 @@
 {
-  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "_name_or_path": "../../../../plm_cache/roberta-base",
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_head_size": 64,
   "attention_probs_dropout_prob": 0.1,
-  "conv_act": "gelu",
-  "conv_kernel_size": 3,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
   "finetuning_task": "sst2",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1536,
+  "hidden_size": 768,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 6144,
+  "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
     "positive": 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": 24,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1536,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
-  "relative_attention": true,
-  "share_att_key": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.16.0.dev0",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365e89fb55124ea6d56f6ffbe427d0220486eb4de2c023cb91eb135b5e205a4c
-size 655267
+oid sha256:4ad0addcf0d2498a5a40f8c997e72f1966822e3fcfac1e4289140ca237fa74ca
+size 2670813

runs/Feb14_17-06-44_node1/1644829690.6667676/events.out.tfevents.1644829690.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2501d73adedbe112c5dc4d954386152cb8b5cc5b84a6761d8ae840299ce15c
+size 4588

runs/Feb14_17-06-44_node1/events.out.tfevents.1644829690.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3dd74ad064cbccc043317bb3341713cf4294a87c85a3b5cf0051060114315a9
+size 3497

special_tokens_map.json

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

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", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v2-xlarge", "tokenizer_class": "DebertaV2Tokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "../../../../plm_cache/roberta-base", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c79dd5728a0dfd88f174d77a75a2ec83b9fb55f13139f90613419cca48d0477
+oid sha256:b55d0648d1b0a06415f18ffb4570c4700baf8ccd5969e309dd37202ddb1a325d
 size 2991