Training in progress, step 500

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_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": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +17,6 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -27,17 +25,17 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
-  "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": "4.19.4",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9b8bda00158a09e3c12ada1c8e7bd2fbc848c9b5b90ae3f29908b9c91e25bb
-size 433330541
+oid sha256:65ff3a6b2334feb1882372193c074500c47059513055889b16ea0cb9d5a0bc95
+size 267866609

runs/Jun13_15-02-17_a30db051be23/events.out.tfevents.1655133094.a30db051be23.928.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053edbac1f05ce0d90e9889f29a38564527c59b3451158acddd5c611faca4c1a
-size 40
+oid sha256:6e0694c1dc24a092883c5f0f34e3c72039d684960cce5170c97410a77d700322
+size 3786

runs/Jun13_15-19-05_a30db051be23/1655133583.4357321/events.out.tfevents.1655133583.a30db051be23.1311.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9dc4e2e81c33df4a232770d650e09cb01ba336dfee1e1754399bfa2e3993b5
+size 5175

runs/Jun13_15-19-05_a30db051be23/events.out.tfevents.1655133583.a30db051be23.1311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eea5140f048e41901b36542c6c17e3265a86bf3241e7c9f633c284499a7f2ab
+size 4360

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef08a385e05f14cdf61a6d4f590275fb07f2afd3fe360ac86a492d3670984d36
+oid sha256:63dd9b185ba543b9275cb9a3fa23f5ac94f613b5d0f74434d43630a266715fa9
 size 3183