Training in progress, epoch 1

config.json

@@ -1,33 +1,37 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "pile-of-law/legalbert-large-1.7M-2",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84af321b8bc2e0dbff82fca9d5236ae6c2f9dfd05bb16b7c96b73e87563d28c9
-size 267855533
+oid sha256:57071dbecb426a2d2139f60ff53cd42a9ddf93237d45bb11ba9b0c875dfbc864
+size 1346768501

runs/Jun05_20-01-03_d5c1e7e48e05/1685995323.5846782/events.out.tfevents.1685995323.d5c1e7e48e05.2120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e808461d19c209e5def267e55715413042aaa8f3deccac22a9071e9ba9016a
+size 5910

runs/Jun05_20-01-03_d5c1e7e48e05/events.out.tfevents.1685995323.d5c1e7e48e05.2120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfbc9296b37a3c39ba5dc5815effc54d57e34da44869a02b4d8ff1f5ef6d59e
+size 4486

tokenizer_config.json

@@ -1,13 +1,17 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
+  "handle_chinese_chars": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_len": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
+  "strip_accents": true,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0e601830cbc0dd8948d6d6bac7663562304979f8e4e46c9c64b65da07bc76a
+oid sha256:f39c076b819123b88dd8842843255c8d81b5c136cc9018b69974243c5d1bd655
 size 3899