Training in progress, epoch 1

config.json

@@ -1,14 +1,13 @@
 {
-  "_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": "fantasy",
     "1": "horror",
@@ -22,7 +21,6 @@
     "9": "thriller"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "action": 4,
     "adventure": 6,
@@ -35,17 +33,17 @@
     "scifi": 3,
     "thriller": 9
   },
-  "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": "4.28.0",
-  "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 sha256:461c84ead5d802673d7acd9a28ae2696531ef1f281be488f2f00fe03e30a9ef9
-size 438032501
+oid sha256:4424a35106929b8c827b2a6a887b72ef8af1c69ef5466cf84b880aa481091524
+size 267880109

runs/Jul05_11-30-25_cce1b16b8821/1688556627.706943/events.out.tfevents.1688556627.cce1b16b8821.176.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7f07fb1bc81ca4b096f7ae3dca624c6ea8a2c5313be15733adc3503fd0ddad
+size 5873

runs/Jul05_11-30-25_cce1b16b8821/events.out.tfevents.1688556627.cce1b16b8821.176.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a892df28ed27a411e25e4990baa96aacc1ddedf39401e87c432e649f0fdba6a0
+size 5548

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 sha256:94806a0b31e2a7f7260a01c61a112962d341fec2fde43e5e33cb041c3f6ee5c9
+oid sha256:c5a858f9bd396b8d9a21cfc4af5f2b34187fec20e2319f38065c98e1701977c0
 size 3579