new model after training dataset expansion

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
+  "_name_or_path": "/home/jovyan/rugpt3large_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fb0fdbadf29a63f262ec84779b9b9be68663ddff4c722931cd9b8ab7937f4f
+oid sha256:32230bca665d11fde2d4f27b7e494d6182d3e570be354ef09c8b9802b2ad4ede
 size 3142000547

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>"}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "/home/jovyan/rugpt3large_based_on_gpt2", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c774fcdbc20671b06fe07847a4d3824eece12950fce72cbd689c111e0e98055
-size 1711
+oid sha256:a4a09256839b780db2224aa09f2081956dc20e0f47d66e3a520d4eeb5c2bef03
+size 1647