Training in progress, epoch 1

config.json

@@ -1,39 +1,33 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
-    "1": "positive",
-    "2": "no impact",
-    "3": "mixed"
+    "1": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
-    "mixed": 3,
     "negative": 0,
-    "no impact": 2,
     "positive": 1
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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": "4.30.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a9dc879c676aad0d606c67bbb880bb0394d8eca88f4ec37c1f053cb8f3feed
-size 438014069
+oid sha256:84410a77dcd4b5e3f35ae8371787f2b98f5cab5046f220f23975a8560927278a
+size 267855533

runs/Jun24_13-57-35_783533aedfec/events.out.tfevents.1687615058.783533aedfec.3425.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2fd51e56392ffdd45229a03123cc3d6d83eb5ceb6826f64455f86ee45de9a3
+size 4332

tokenizer_config.json

@@ -8,6 +8,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9897432b2a70e9fcaf8fe9ed38de50ea43d0d812736d155442929a2188b8c5f9
+oid sha256:d71438b7cbed5085639978cb0ffb0a796c1da6c4b98ab187cf75606e87523f49
 size 3963