Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "rinna/japanese-gpt2-small",
+  "_name_or_path": "rinna/japanese-gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -13,10 +13,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": 3072,
-  "n_layer": 12,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": 4096,
+  "n_layer": 24,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1477d7d2d2c719226a888d99505e0c90cd20a720d92fe8e654fce33c68b47f4
-size 454321385
+oid sha256:e86ff398dde37b11c462c74db23d499e784bdf3df13e6d0629ec7970583b6643
+size 1369804761

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "special_tokens_map_file": "/root/.cache/huggingface/transformers/96f1ddf7247675414b491c5c3ae4c7ac307cf28d0f90977b7cbdf13a8f84bfc8.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82", "tokenizer_file": null, "name_or_path": "rinna/japanese-gpt2-small", "tokenizer_class": "T5Tokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82", "tokenizer_file": null, "name_or_path": "rinna/japanese-gpt2-medium", "tokenizer_class": "T5Tokenizer"}