Training in progress, epoch 1

config.json

@@ -1,13 +1,15 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "facebook/muppet-roberta-base",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "RobertaForTokenClassification"
   ],
-  "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": 768,
   "id2label": {
     "0": "O",
     "1": "B-corporation",
@@ -24,6 +26,7 @@
     "12": "I-product"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-corporation": 1,
     "B-creative-work": 3,
@@ -39,16 +42,16 @@
     "I-product": 12,
     "O": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": 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",
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
-  "vocab_size": 30522
+  "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:b4c4077a453f802ed99d2f5a6eeb77e59cabde095f2b681e60b12fccd45fcb20
-size 265526309
+oid sha256:9e9aa8dc7f59560104a12b1df61c5da3cf69f13ceba5989d829f8d563f0cc07e
+size 496332845

runs/Feb08_04-51-24_ce57cc7bc0da/1675831888.1090121/events.out.tfevents.1675831888.ce57cc7bc0da.107.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe84d483ffa06552e2dff44af2bd3ad5b30499fd5569b2359e1fadf895618c6
+size 5679

runs/Feb08_04-51-24_ce57cc7bc0da/events.out.tfevents.1675831888.ce57cc7bc0da.107.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b625f82a8d198e0baa5b40a67b1d777f7ab58ca0555a9d14cc7366a8968793e1
+size 4923

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]",
-  "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "facebook/muppet-roberta-base",
+  "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 sha256:8e1433a1ad702275ff87ff7e9496ecef736b0b9149d1c2a3a661fb8404b4294d
+oid sha256:b991dee290c08778ee4b959ea1d1eb107068cfb65c55a12a455bef3a127a3add
 size 3515