Training in progress, epoch 1

config.json

@@ -1,15 +1,13 @@
 {
-  "_name_or_path": "rmihaylov/roberta-base-sentiment-bg",
+  "_name_or_path": "iarfmoose/roberta-base-bulgarian",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoModel": "modeling_roberta.XLMRobertaForSequenceClassification"
-  },
   "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,
@@ -35,16 +33,15 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "roberta": 1,
   "torch_dtype": "float32",
   "transformers_version": "4.27.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 88361
+  "vocab_size": 52000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059a859ced78d11913cefa6f8470ec8cb00a44b1d534c88ab4d77ed0a5e3c9df
-size 445566197
+oid sha256:b30fef3286f7234d31879af2431fd0479758a0804db440e51842539f5091c1dc
+size 504007349

runs/Mar27_07-26-35_965953b251dc/1679902127.4864774/events.out.tfevents.1679902127.965953b251dc.274.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d919285e76669c7b400e5c7cd8dc7ad845738afa266bef4bc6ddf717de1d71db
+size 5848

runs/Mar27_07-26-35_965953b251dc/events.out.tfevents.1679902127.965953b251dc.274.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808bf53c9784b567cf2e57dd769d1f5c8f5f260dc7762d96dd7569f96b337f66
+size 4884

special_tokens_map.json

@@ -2,7 +2,13 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "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

@@ -1,8 +1,31 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "do_lower_case": true,
-  "eos_token": "</s>",
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
   "mask_token": {
     "__type": "AddedToken",
     "content": "<mask>",
@@ -11,12 +34,33 @@
     "rstrip": false,
     "single_word": false
   },
-  "max_len": 512,
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": "/content/drive/MyDrive/ColabModels/XROBERTA_SST2_SMALL/pytorch_model/special_tokens_map.json",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "max_len": 128,
+  "model_max_length": 128,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8238c39470e5aa38e3cee935853dce0d5c89e158d7abe83d4b83588e5753a8c
+oid sha256:5736b939b0d305d771fcabb4b23037b481e401b3a4e0e272505a9b74afa253e8
 size 3579