Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,92 @@
+{
+  "[PAD_left_10]": 50274,
+  "[PAD_left_11]": 50275,
+  "[PAD_left_12]": 50276,
+  "[PAD_left_13]": 50277,
+  "[PAD_left_14]": 50278,
+  "[PAD_left_15]": 50279,
+  "[PAD_left_16]": 50280,
+  "[PAD_left_17]": 50281,
+  "[PAD_left_18]": 50282,
+  "[PAD_left_19]": 50283,
+  "[PAD_left_1]": 50265,
+  "[PAD_left_20]": 50284,
+  "[PAD_left_21]": 50285,
+  "[PAD_left_22]": 50286,
+  "[PAD_left_23]": 50287,
+  "[PAD_left_24]": 50288,
+  "[PAD_left_25]": 50289,
+  "[PAD_left_26]": 50290,
+  "[PAD_left_27]": 50291,
+  "[PAD_left_28]": 50292,
+  "[PAD_left_29]": 50293,
+  "[PAD_left_2]": 50266,
+  "[PAD_left_30]": 50294,
+  "[PAD_left_31]": 50295,
+  "[PAD_left_32]": 50296,
+  "[PAD_left_33]": 50297,
+  "[PAD_left_34]": 50298,
+  "[PAD_left_35]": 50299,
+  "[PAD_left_36]": 50300,
+  "[PAD_left_37]": 50301,
+  "[PAD_left_38]": 50302,
+  "[PAD_left_39]": 50303,
+  "[PAD_left_3]": 50267,
+  "[PAD_left_40]": 50304,
+  "[PAD_left_41]": 50305,
+  "[PAD_left_42]": 50306,
+  "[PAD_left_43]": 50307,
+  "[PAD_left_44]": 50308,
+  "[PAD_left_45]": 50309,
+  "[PAD_left_46]": 50310,
+  "[PAD_left_47]": 50311,
+  "[PAD_left_48]": 50312,
+  "[PAD_left_49]": 50313,
+  "[PAD_left_4]": 50268,
+  "[PAD_left_50]": 50314,
+  "[PAD_left_51]": 50315,
+  "[PAD_left_52]": 50316,
+  "[PAD_left_53]": 50317,
+  "[PAD_left_54]": 50318,
+  "[PAD_left_55]": 50319,
+  "[PAD_left_56]": 50320,
+  "[PAD_left_57]": 50321,
+  "[PAD_left_58]": 50322,
+  "[PAD_left_59]": 50323,
+  "[PAD_left_5]": 50269,
+  "[PAD_left_60]": 50324,
+  "[PAD_left_61]": 50325,
+  "[PAD_left_62]": 50326,
+  "[PAD_left_63]": 50327,
+  "[PAD_left_64]": 50328,
+  "[PAD_left_65]": 50329,
+  "[PAD_left_66]": 50330,
+  "[PAD_left_67]": 50331,
+  "[PAD_left_68]": 50332,
+  "[PAD_left_69]": 50333,
+  "[PAD_left_6]": 50270,
+  "[PAD_left_70]": 50334,
+  "[PAD_left_71]": 50335,
+  "[PAD_left_72]": 50336,
+  "[PAD_left_73]": 50337,
+  "[PAD_left_74]": 50338,
+  "[PAD_left_75]": 50339,
+  "[PAD_left_76]": 50340,
+  "[PAD_left_77]": 50341,
+  "[PAD_left_78]": 50342,
+  "[PAD_left_79]": 50343,
+  "[PAD_left_7]": 50271,
+  "[PAD_left_80]": 50344,
+  "[PAD_left_81]": 50345,
+  "[PAD_left_82]": 50346,
+  "[PAD_left_83]": 50347,
+  "[PAD_left_84]": 50348,
+  "[PAD_left_85]": 50349,
+  "[PAD_left_86]": 50350,
+  "[PAD_left_87]": 50351,
+  "[PAD_left_88]": 50352,
+  "[PAD_left_89]": 50353,
+  "[PAD_left_8]": 50272,
+  "[PAD_left_90]": 50354,
+  "[PAD_left_9]": 50273
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50355
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7290568c77aff8f99cecf26bad30a1f982f56d36231f7227d74e63b115d446e
+size 498934129

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "[PAD_left_1]",
+    "[PAD_left_2]",
+    "[PAD_left_3]",
+    "[PAD_left_4]",
+    "[PAD_left_5]",
+    "[PAD_left_6]",
+    "[PAD_left_7]",
+    "[PAD_left_8]",
+    "[PAD_left_9]",
+    "[PAD_left_10]",
+    "[PAD_left_11]",
+    "[PAD_left_12]",
+    "[PAD_left_13]",
+    "[PAD_left_14]",
+    "[PAD_left_15]",
+    "[PAD_left_16]",
+    "[PAD_left_17]",
+    "[PAD_left_18]",
+    "[PAD_left_19]",
+    "[PAD_left_20]",
+    "[PAD_left_21]",
+    "[PAD_left_22]",
+    "[PAD_left_23]",
+    "[PAD_left_24]",
+    "[PAD_left_25]",
+    "[PAD_left_26]",
+    "[PAD_left_27]",
+    "[PAD_left_28]",
+    "[PAD_left_29]",
+    "[PAD_left_30]",
+    "[PAD_left_31]",
+    "[PAD_left_32]",
+    "[PAD_left_33]",
+    "[PAD_left_34]",
+    "[PAD_left_35]",
+    "[PAD_left_36]",
+    "[PAD_left_37]",
+    "[PAD_left_38]",
+    "[PAD_left_39]",
+    "[PAD_left_40]",
+    "[PAD_left_41]",
+    "[PAD_left_42]",
+    "[PAD_left_43]",
+    "[PAD_left_44]",
+    "[PAD_left_45]",
+    "[PAD_left_46]",
+    "[PAD_left_47]",
+    "[PAD_left_48]",
+    "[PAD_left_49]",
+    "[PAD_left_50]",
+    "[PAD_left_51]",
+    "[PAD_left_52]",
+    "[PAD_left_53]",
+    "[PAD_left_54]",
+    "[PAD_left_55]",
+    "[PAD_left_56]",
+    "[PAD_left_57]",
+    "[PAD_left_58]",
+    "[PAD_left_59]",
+    "[PAD_left_60]",
+    "[PAD_left_61]",
+    "[PAD_left_62]",
+    "[PAD_left_63]",
+    "[PAD_left_64]",
+    "[PAD_left_65]",
+    "[PAD_left_66]",
+    "[PAD_left_67]",
+    "[PAD_left_68]",
+    "[PAD_left_69]",
+    "[PAD_left_70]",
+    "[PAD_left_71]",
+    "[PAD_left_72]",
+    "[PAD_left_73]",
+    "[PAD_left_74]",
+    "[PAD_left_75]",
+    "[PAD_left_76]",
+    "[PAD_left_77]",
+    "[PAD_left_78]",
+    "[PAD_left_79]",
+    "[PAD_left_80]",
+    "[PAD_left_81]",
+    "[PAD_left_82]",
+    "[PAD_left_83]",
+    "[PAD_left_84]",
+    "[PAD_left_85]",
+    "[PAD_left_86]",
+    "[PAD_left_87]",
+    "[PAD_left_88]",
+    "[PAD_left_89]",
+    "[PAD_left_90]"
+  ],
+  "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

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9039d6a4fc1a48022b59dbed2d97deb4cf3133d84bbb3230d48e7a9af7c87008
+size 4091