Training in progress, epoch 1

config.json

@@ -1,32 +1,36 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-emotion",
   "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,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
-  "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": "4.48.3",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034013a914d72945616c820fede731e85da8a9975c990cf137544f9a17cbe65f
-size 267832560
+oid sha256:aa28b703b83b1125b7f0c12ee134099be042026893082a9e63fec94e203b5c77
+size 498612824

runs/Feb26_02-16-19_867d48904fb8/events.out.tfevents.1740536180.867d48904fb8.11863.35

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa125dd4722f08a9f25be43962fe6b3885d75a4bb624ae51f869078f749fc29
-size 11164
+oid sha256:d049a83f0cef10a62d70fe7f447676069f26b18e8cbd680bb7181b435388d675
+size 11835

runs/Feb26_02-30-00_867d48904fb8/events.out.tfevents.1740537001.867d48904fb8.11863.36

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400274eab23ec8cd575b7fb17125f58ba033282f385d4be833ba622b44e55d6d
+size 5047

runs/Feb26_02-31-56_867d48904fb8/events.out.tfevents.1740537117.867d48904fb8.11863.37

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d76d4270d9a0e9b98668cc3e2a9630dc5aacd9a39af72f0b59e89abb72c21d8
+size 6072

runs/Feb26_02-36-15_867d48904fb8/events.out.tfevents.1740537376.867d48904fb8.11863.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c01c7501e1e7881dcfcea641602d748c69f6a52ece9adba6e84615d16178ed8
+size 6389

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,56 +1,58 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "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 sha256:5159f432d3c441504a9f6a6a4315ad7c95ca49a9adebadbbfdee8d18926983cd
+oid sha256:4330efbf7920053716cf21b0bbbbe10d63103c9e8761d60d05abe0bd5017a32f
 size 5304