Training in progress, epoch 1

config.json

@@ -1,35 +1,35 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "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,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
   "id2label": {
     "0": "Consumer",
     "1": "Enterprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Consumer": 0,
     "Enterprise": 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,
+  "output_past": true,
   "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": "4.26.0",
-  "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 sha256:0d53884b142aa3c90afa896953ed2e5e4d61f2ed1ee2c43c0733e659cf0d29f3
-size 438007925
+oid sha256:134caca83e4571ac508131b624c84c73881d734c7ddef06cf5c3c7b2bcd3fb9b
+size 267855533

runs/Jan25_03-02-03_07f50fc0e54b/events.out.tfevents.1674615727.07f50fc0e54b.617.22

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eaaf05ccf08c8033380a829c1f0c7388d8e778fdc1a459c45b3a9a3e06f7346
-size 4278
+oid sha256:1d5252b7cbbc7c54aa6db38f7a33c50511f49c579a568874a1788307ef9545f8
+size 5601

runs/Jan25_03-04-25_07f50fc0e54b/1674615868.9819698/events.out.tfevents.1674615868.07f50fc0e54b.617.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e568e59fa5f8a6f3372a7286540ca4b3f8770dbf72d11e893d392c6d148a49a
+size 5697

runs/Jan25_03-04-25_07f50fc0e54b/events.out.tfevents.1674615868.07f50fc0e54b.617.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b32c9535739ebace6cdd66151f0a7bfd0a5efaa1302db052137d902503fa69
+size 4257

tokenizer_config.json

@@ -1,14 +1,16 @@
 {
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
+  "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,
   "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:e5d221323437e32fdfa1a8ea14fd9220a5fc6c155adbf4dbce488f6fdd560bd2
+oid sha256:7ffbadcf8848674decd5b74c0eac4319750e7c7f3638a6827e052cd4871d5206
 size 3515