Training in progress, step 500

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
+  "_name_or_path": "loodos/electra-small-turkish-uncased-discriminator",
   "architectures": [
-    "BertForQuestionAnswering"
+    "ElectraForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "embedding_size": 128,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
@@ -13,14 +13,18 @@
   "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.15.0",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40cb49298c4f4fe280880be6fbd6e137d90eb265f904f4b37f261febbfa4b2cb
-size 50783921
+oid sha256:f31713e7d63534af31e315d0c180e57d561d2387a7a5a0d0167fed3b95980cde
+size 54776045

runs/Jan13_21-49-04_764a5bc1404f/1642110984.8803074/events.out.tfevents.1642110984.764a5bc1404f.74.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a5f17b3fae18edc8d310014966c74dcd4d0708ebb5d799e85bfc2f34bad219
+size 4940

runs/Jan13_21-49-04_764a5bc1404f/1642111026.2224245/events.out.tfevents.1642111026.764a5bc1404f.74.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92131b1169dcc95700c184699bcb8eded1d009fc51755dc23925fdcb3d112cbf
+size 4940

runs/Jan13_21-49-04_764a5bc1404f/events.out.tfevents.1642110984.764a5bc1404f.74.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e7c93129722861fa745a3055d6edd68c2e36d3e57c03f3d6b2175b71367598
+size 7385

tokenizer_config.json

@@ -1 +1 @@
-{"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, "special_tokens_map_file": null, "name_or_path": "microsoft/xtremedistil-l6-h256-uncased", "do_basic_tokenize": true, "never_split": null, "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": "/root/.cache/huggingface/transformers/444866c6552ed3ad4574d4ea6433149e5e30eef747074cfa66be2388dadf2646.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "loodos/electra-small-turkish-uncased-discriminator", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2977beef4031b58d526559e1c10320a65605051b01e6683fa623244507427f30
-size 3119
+oid sha256:9a0373ade938f5bfd372389cac2128de9169adf39e17695b4e6b573e011b3e1b
+size 3183