Training in progress, epoch 1

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
-  "activation": "gelu",
+  "_name_or_path": "fabriceyhc/bert-base-uncased-amazon_polarity",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -15,24 +16,24 @@
     "3": "LABEL_3"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2,
     "LABEL_3": 3
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
-  "vocab_size": 119547
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c30b30af4612172d4f29d5967dc07ff6d736980bdf93f2aa75d417d4e091df
-size 541323528
+oid sha256:973376800baa251512eb3f757e91080d535c7949a9a8d37e10f1e7466e4789f3
+size 437964800

runs/Apr30_15-23-08_969217bf108a/events.out.tfevents.1714490592.969217bf108a.144.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbfe341bc6b0c09fcc953283b7b466dd6c5c1dc700983a618c7e51df64537f3
+size 4845

runs/Apr30_15-44-12_969217bf108a/events.out.tfevents.1714491857.969217bf108a.144.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7a3aed4bba886e52f57632a9eda928bca61a9444d19206b858f018659a27cf
+size 9672

runs/Apr30_15-46-14_969217bf108a/events.out.tfevents.1714491977.969217bf108a.144.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ebb47e88334475a1d676e33afd761c8a5cf716efa1fe00d1e9f1790747b495
+size 5314

tokenizer_config.json

@@ -43,12 +43,10 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
+  "max_length": 250,
   "model_max_length": 512,
-  "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
   "pad_token_type_id": 0,
@@ -57,7 +55,7 @@
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c37ac1d3275cb0ef5106a8cc8d027576fc318cae47bff0914e835b64f6cd6556
-size 4920
+oid sha256:f08670c00c9cd5415cfc6856d405d3bd2cb5293490459a4042d7ef3ee2db9dac
+size 4984