added data ti sign, high loss

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
+  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -13,19 +13,22 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 2048,
-  "n_embd": 1536,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.8.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
   "use_cache": true,
   "vocab_size": 50258
 }

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8015eac40d007ab9f1f4d75167858c9e074be8e49ceb96efa849c689ec11a030
+size 1001901617

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440c3f22cec7b05a74a90bba2a3e7de14a2f31713c68a96e8518def59f092bd5
-size 3141992409
+oid sha256:6eaaf8ba37762c44e6d9b4d9492f28ccd291e9573a5eb8352b8386d92cfe781a
+size 551301353

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0afa24760ee197b045f4a77ec9a95e4dc33ea6d983bb7a276ad4ec3bc10bf3d
+size 623

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": "sberbank-ai/rugpt3small_based_on_gpt2", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9c5a78cb0246eace80a943fc646030dd99869b6e31a9d906da619f33b9ab9e
+oid sha256:48e8b80d4f6609a52e44765821ba572d119d71e7c05427702108da3bed2b4131
 size 1519