Training in progress, step 500

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "roberta-large",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -39,6 +41,7 @@
     "27": "LABEL_27"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -69,17 +72,17 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "vocab_size": 30522
+  "transformers_version": "4.20.1",
+  "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 sha256:19424ed24da12c023d56f789d211e4072e8898e193049073f2215eb1df0ab86d
-size 267935469
+oid sha256:75a3c0978a2d968979dcd40e9874ee65eb348d2a7cdeda93062ee42b81ae4667
+size 1421690925

runs/Feb21_13-56-12_09b62d1b427a/1676987856.6785717/events.out.tfevents.1676987856.09b62d1b427a.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38df964ba4ef3d77cdc680ae19e627350ed7a6b3eeccbf2eba6a925c2176789
+size 5371

runs/Feb21_13-56-12_09b62d1b427a/events.out.tfevents.1676987856.09b62d1b427a.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5005430982c758b0740f35e8b1a4da4dd5653b4db595814eedd78a153e71298
+size 5360

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_config.json

@@ -1,14 +1,16 @@
 {
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "name_or_path": "roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a0da41b689868699c951e90991f305cadd15e009bef51b47f3abd8845815b0
-size 3515
+oid sha256:0fbde008084afe37bef40b2989c71a408dc4ddcfc7f285e0a249e6e675cd9f32
+size 3311