Training in progress, step 5000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "rinna/japanese-gpt2-medium",
+  "_name_or_path": "huranokuma/es2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837923a8af02f2adb0f66e3cd11606accf7bc14f26179a545ccc000948e54d7e
+oid sha256:a059654dc696a983cd6770385c954fedc7f864a372db0bf8cb9caa13fc1a5422
 size 1369786201

runs/Aug12_10-33-28_3f0a2cf25cdb/1660301684.1191247/events.out.tfevents.1660301684.3f0a2cf25cdb.443.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3961fd7ff7097f35d56a8cffc6ac30cd18965493d32773a83aca3dc9735bec1f
+size 5364

runs/Aug12_10-33-28_3f0a2cf25cdb/events.out.tfevents.1660301684.3f0a2cf25cdb.443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7b8dc842bdcb19ca0c947688da68ba3a488ede02e563ecb3c1d59cb1901181
+size 5480

tokenizer_config.json

@@ -6,7 +6,7 @@
   "eos_token": "</s>",
   "extra_ids": 0,
   "mask_token": "[MASK]",
-  "name_or_path": "rinna/japanese-gpt2-medium",
+  "name_or_path": "huranokuma/es2",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d141a08ee9317cdfd02ce7302ce785a5cbb67a0d9851928e3a773c642418cb6
+oid sha256:09998fa01d96396f74606b5f2af8360a1ab986f5d2e7554ef08b94893457a891
 size 3375