Upload Model

config.json

@@ -0,0 +1,29 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32102
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1acbcb199d50bdd5acbecdefc592755d1391443590666bb188d5900a867faac
+size 442872135

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873dbed1150738ae871995b5fc7ed04e7a3f5be0cb496c0219df4d3efa51e6d0
+size 235127

trainig.txt

@@ -0,0 +1,111 @@
+config.json: 100%
+ 433/433 [00:00<00:00, 53.7kB/s]
+model.safetensors: 100%
+ 445M/445M [00:04<00:00, 205MB/s]
+Loading weights: 100%
+ 199/199 [00:00<00:00, 974.29it/s, Materializing param=bert.pooler.dense.weight]
+BertForSequenceClassification LOAD REPORT from: dbmdz/bert-base-italian-xxl-cased
+Key                                        | Status     | 
+-------------------------------------------+------------+-
+cls.seq_relationship.weight                | UNEXPECTED | 
+cls.predictions.bias                       | UNEXPECTED | 
+cls.predictions.transform.dense.bias       | UNEXPECTED | 
+cls.seq_relationship.bias                  | UNEXPECTED | 
+cls.predictions.transform.LayerNorm.bias   | UNEXPECTED | 
+cls.predictions.transform.LayerNorm.weight | UNEXPECTED | 
+cls.predictions.transform.dense.weight     | UNEXPECTED | 
+classifier.bias                            | MISSING    | 
+classifier.weight                          | MISSING    | 
+
+Notes:
+- UNEXPECTED	:can be ignored when loading from different task/architecture; not ok if you expect identical arch.
+- MISSING	:those params were newly initialized because missing from the checkpoint. Consider training on your downstream task.
+
+======== Epoch 1 / 3 ========
+Training...
+  Batch    40  of    378.    Elapsed: 0:00:19.
+  Batch    80  of    378.    Elapsed: 0:00:38.
+  Batch   120  of    378.    Elapsed: 0:00:56.
+  Batch   160  of    378.    Elapsed: 0:01:14.
+  Batch   200  of    378.    Elapsed: 0:01:33.
+  Batch   240  of    378.    Elapsed: 0:01:51.
+  Batch   280  of    378.    Elapsed: 0:02:09.
+  Batch   320  of    378.    Elapsed: 0:02:28.
+  Batch   360  of    378.    Elapsed: 0:02:46.
+
+  Average training loss: 0.39
+  Training took: 0:02:54
+
+Running Validation...
+
+  Average test loss: 0.36
+  Validation took: 0:00:15
+              precision    recall  f1-score   support
+
+           0       0.80      0.93      0.86      2823
+           1       0.90      0.71      0.79      2351
+
+    accuracy                           0.83      5174
+   macro avg       0.85      0.82      0.83      5174
+weighted avg       0.84      0.83      0.83      5174
+
+
+======== Epoch 2 / 3 ========
+Training...
+  Batch    40  of    378.    Elapsed: 0:00:18.
+  Batch    80  of    378.    Elapsed: 0:00:36.
+  Batch   120  of    378.    Elapsed: 0:00:55.
+  Batch   160  of    378.    Elapsed: 0:01:13.
+  Batch   200  of    378.    Elapsed: 0:01:31.
+  Batch   240  of    378.    Elapsed: 0:01:50.
+  Batch   280  of    378.    Elapsed: 0:02:08.
+  Batch   320  of    378.    Elapsed: 0:02:26.
+  Batch   360  of    378.    Elapsed: 0:02:45.
+
+  Average training loss: 0.20
+  Training took: 0:02:53
+
+Running Validation...
+
+  Average test loss: 0.41
+  Validation took: 0:00:15
+              precision    recall  f1-score   support
+
+           0       0.82      0.91      0.87      2823
+           1       0.88      0.77      0.82      2351
+
+    accuracy                           0.85      5174
+   macro avg       0.85      0.84      0.84      5174
+weighted avg       0.85      0.85      0.85      5174
+
+
+======== Epoch 3 / 3 ========
+Training...
+  Batch    40  of    378.    Elapsed: 0:00:18.
+  Batch    80  of    378.    Elapsed: 0:00:36.
+  Batch   120  of    378.    Elapsed: 0:00:55.
+  Batch   160  of    378.    Elapsed: 0:01:13.
+  Batch   200  of    378.    Elapsed: 0:01:31.
+  Batch   240  of    378.    Elapsed: 0:01:50.
+  Batch   280  of    378.    Elapsed: 0:02:08.
+  Batch   320  of    378.    Elapsed: 0:02:26.
+  Batch   360  of    378.    Elapsed: 0:02:45.
+
+  Average training loss: 0.07
+  Training took: 0:02:53
+
+Running Validation...
+
+  Average test loss: 0.60
+  Validation took: 0:00:15
+              precision    recall  f1-score   support
+
+           0       0.86      0.89      0.88      2823
+           1       0.87      0.83      0.85      2351
+
+    accuracy                           0.86      5174
+   macro avg       0.86      0.86      0.86      5174
+weighted avg       0.86      0.86      0.86      5174
+
+
+Training complete!